ComfyUI Workflows
Browse real AI workflows from Flux, SDXL, Pony, ControlNet, video generation and commercial AI creators.
Wan VACE Clip Extender
ComfyUI Wan VACE Video ExtenderGithubThis workflow uses Wan VACE to generate new frames from a specified point in a video.What it DoesThis is a lightweight, (almost) no custom nodes ComfyUI workflow meant to quickly extend a video with Wan VACE and a minimum of fuss. Just load your video, specify the extend start point and the number of new frames to generate.DependenciesMy ComfyUI-Wan-VACE-Prep custom node package is required for this workflow. It replaces a large amount of awkward spaghetti workflow math, making this lightweight workflow version possible.In ComfyUI Manager, search for Wan VACE Prep or just load the workflow and then visit the Missing tab in Manager.This is a very lightweight package with no dependencies, so it is highly unlikely to break your system, if that is something you worry about.I have not tested this workflow or the custom nodes under the Nodes 2.0 UI.Configuration and ModelsYou'll need some combination of these models to run the workflow. As already mentioned, this workflow will not run properly on your system until you configure it properly. You probably already have a Wan video generation workflow that runs well on your system. You need to configure this workflow similarly to your generation workflow. The Sampler subgraph contains KSampler nodes and model loading nodes. Have your way with these until it feels right to you. Enable the sageattention and torch compile nodes if you know your system supports them. Just make sure all the subgraph inputs and outputs are correctly getting and setting data, and crucially, that the diffusion model you load is one of Wan2.2 Fun VACE or Wan2.1 VACE. GGUFs work fine, but non-VACE models do not.Wan 2.2 Fun VACEbf16 and fp8GGUFWan 2.1 VACEfp16GGUFKijai’s extracted Fun Vace 2.2 modules, for loading along with standard T2V models. Native use examples here.bf16GGUFTroubleshootingThe size of tensor a must match the size of tensor b at non-singleton dimension 1 - Check that both dimensions of your input videos are divisible by 16 and change this if they're not. Fun fact: 1080 is not divisible by 16!Brightness/color shift - VACE can sometimes affect the brightness or saturation of the clips it generates. I don't know how to avoid this tendency, I think it's baked into the model, unfortunately. Disabling lightx2v speed loras can help, as can making sure you use the exact same lora(s) and strength in this workflow that you used when generating your clips. Some people have reported success using a color match node before output of the clips in this workflow. I think specific solutions vary by case, though. The most consistent mitigation I have found is to interpolate framerate up to 30 or 60 fps after using this workflow. The interpolation decreases how perceptible the color shift is. The shift is still there, but it's spread out over 60 frames instead over 16, so it doesn't look like a sudden change to our eyes any more.Regarding Framerate - The Wan models are trained at 16 fps, so if your input videos are at some higher rate, you may get sub-optimal results. At the very least, you'll need to increase the number of context and replace frames by whatever factor your framerate is greater than 16 fps in order to achieve the same effect with VACE. I suggest forcing your inputs down to 16 fps for processing with this workflow, then re-interpolating back up to your desired framerate.If you can't make the workflow work, update ComfyUI and try again. If you're not willing to update ComfyUI, I can't help you. We have to be working from the same starting point.Feel free to open an issue on github. This is the most direct way to engage me. If you want a head start, paste your complete console log from a failed run into your issue.Changelogv1.0.0 Initial release.
MonK ComfyUI Workflow
My workspace is for working in the ComfyUI environment and processing the finished image using Inpaint.
ZImage Turbo Essentials workflow
Note: If you have ANY issues with nodes not downloading, read the notes or reach out. There's nothing that special about any of them that aren't core modules.⛔⚠️🛑✋ Read the notes completly before using. Most common install and node problems are listed in the directions也有中文说明This model is set up for Z-Image Turbo. I have a seperate model for BaseA complete user and troubleshooting guide inclusing a list of common error messages can be found here https://civitai.com/articles/24678/how-to-use-my-workflows-a-comprehensive-breakdownThis is a modification to my advanced workflow designed for beginners:Checkpoint option for merged modelsSeed variance enhancerUltimate Upscaler for prescaling and hi res fixDetailing Suite for face, hands, & eyesEssentials Post Production SuiteSmart Noise scrubberFull tutorial available.也有中文说明Check out my other models:Instagram: https://www.instagram.com/synth.studio.models/Buy me a☕ https://ko-fi.com/lonecatoneThis represents many of hours of work. If you enjoy it, please 👍like, 💬 comment , and feel free to ⚡tip 😉
Friendly Ideogram 4
Welcome to my 💫🌄 Friendly Ideogram 4✨ Less mess, more magic and controlFeel like a real designer with Ideogram 4 and my friendly workflow!I offer my workflow with LLM Enhancer & Prompt Builder modes. Edit everything you want in your generations.The latest version of ComfyUI is required.💻 System requirements:Minimum system requirements:RTX 3000-s, 8GB+ VRAM, 32GB+ RAM, 8-core processor, SSD, latest ComfyUI📌 Detailed tips and links to models in the workflow✨ Workflow features:Extremely user-friendly interfaceMaximum performance even on low-end systems with at least 8GB of VRAMLLM Enhancer and Prompt Builder implementationSupport for up to 2 LoraDetailed tooltips and links to modelsManual random seed for complete control over generationsModel overviewIdeogram 4.0 is a powerful, open-weight text-to-image model designed for professional-grade visual creation. It features a 9.3 billion parameter single-stream Diffusion Transformer (DiT) architecture that was trained entirely from scratchKey Capabilities & FeaturesProduction-Grade Typography: It offers crystal-clear, dense text rendering across multiple languages directly inside the composition, rather than as a fragile overlayNative Transparency: The model can generate images with native transparent backgrounds, eliminating the need for post-processing background removalHigh Resolution & Flexibility: It supports native 2K resolution output and flexible aspect ratios up to 2048 pixels on each sideAdvanced Controllability: The model is trained on structured JSON captions, providing unprecedented control over composition, style, lighting, and color palettes. It also allows for precise object and text placement using bounding box controls.Post-Generation Editing SuiteIdeogram 4.0 introduces a comprehensive suite of tools to revise and refine images after generation without starting from scratch:Layerize Text: Turns generated typography into editable layers so you can restyle, reposition, and refine the text afterward.Prompt Edit: Allows users to describe changes in plain language to revise specific parts of the image.Extend & Reframe: Grows the composition beyond its original crop or shifts it for different aspect ratios while maintaining the original focal point.Magic Fill: Adds new objects or replaces missing areas to seamlessly match the surrounding scene.Other Tools: The platform also includes native background removal, upscaling for sharper delivery, and remixing to explore new creative directions.🤗🙏🏼 Thanks to Ideogram AI and KijaiOriginal repo — GitHub
Nvidia PiD 4K Image Upscaler Workflow (Z-Image, Flux.1, Flux.2, SD3 compatible) by Smittie
Smittie's PiD Upscaler WorkflowDescriptionWith this workflow you can upscale low-resolution images (512, 1K) to much higher resolutions (2K, 4K) using Nvidia's PiD (Pixel Diffusion). It is a simple image to image (I2I) workflow.Install Instructions1. Update ComfyUI to latest build with PiD support2. Install all missing custom nodes via the ComfyUI Manager3. Download all needed modelsDiffusion modelAll availableFor Z-Image or Flux.1 like images in 1K resolution use pid_flux1_1024_to_4096_4step_bf16.safetensorsText encodergemma_2_2b_it_elm_bf16.safetensorsVAEae.safetensorsVideo InstructionsIf you don't know what to do, you can watch the Nvidia PiD Tutorial by AI Search. He works with a different workflow, which I have built upon.AcknowledgementMost credits goes to the Nvidia, ComfyUI and CivitAI team, as well as kijai and AI Search. Thank you guys!
FLUX.2 Klein 9B - Reference-Based Face Swap Workflow
FLUX.2 Klein 9B - Reference-Based Face Swap Workflow⚡ Production-tested workflow.This workflow originated from an internal automation pipeline capable of processing hundreds of images automatically through the ComfyUI API on a single NVIDIA T4 GPU.A highly consistent face swap workflow for ComfyUI built around FLUX.2 Klein 9B, latent references, and a dedicated face swap LoRA.Unlike traditional face swap methods, this workflow uses both a Target Reference and a Source Face Reference to preserve composition while transferring identity.RequirementsBefore loading the workflow, make sure you have:FLUX.2 Klein 9BFLUX2 VAEQwen 3 8B FP8 Mixed Text EncoderFace Swap LoRALanPaint Custom NodesRequired ModelsFLUX.2 Klein 9BPlace inside:ComfyUI/models/unet/ Model:flux-2-klein-9b.safetensors FLUX2 VAEPlace inside:ComfyUI/models/vae/ Model:flux2-vae.safetensors Qwen 3 8B FP8 MixedPlace inside:ComfyUI/models/text_encoders/ Model:qwen_3_8b_fp8mixed.safetensors Face Swap LoRAPlace inside:ComfyUI/models/loras/ Model:bfs_head_v1_flux-klein_9b_step3500_rank128.safetensors Required Custom NodesLanPaintThis workflow uses the LanPaint sampler.Install it through:ComfyUI Manager → Install Missing Custom NodesWorkflow OverviewThis workflow uses two different references:Target ReferencePreserves:CompositionPoseFramingPerspectiveScene structureLighting contextSource Face ReferenceTransfers:Face identityFacial proportionsHair characteristicsEyesSkin detailsBy combining both references, the workflow achieves significantly better consistency than traditional face swap approaches.How To UseStep 1 - Load The Source FaceNode:Source Face ImageThis image provides the identity that will be transferred.Recommended:✅ Front-facing portraits✅ High-resolution images✅ Clear facial visibility✅ Good lightingAvoid:❌ Motion blur❌ Heavy occlusions❌ Sunglasses❌ Extreme anglesStep 2 - Load The Target ImageNode:Target ImageThis image provides:BackgroundBodyClothingPoseCompositionFramingPerspectiveThe workflow attempts to preserve these elements while replacing the identity.Recommended:✅ Portrait photos✅ Medium shots✅ Visible face✅ Clear lightingAvoid:❌ Tiny faces❌ Hidden faces❌ Extreme side profilesStep 3 - Queue PromptPress:Queue PromptThe workflow automatically:Reads target dimensionsCreates target latent referencesCreates source face latent referencesApplies dual-reference conditioningGenerates the face-swapped resultPreserves original scene compositionNo additional setup is required.What This Workflow PreservesOriginal backgroundOriginal compositionOriginal lightingOriginal perspectiveOriginal poseOriginal framingOriginal camera distanceOriginal scene layoutIdeal Use CasesUGC Creator ReplacementInfluencer Face SwapsCharacter ConsistencyMarketing CreativesAI AvatarsPersonal BrandingDataset GenerationBatch Face Swap PipelinesPerformanceTested on:NVIDIA T4RTX 3060RTX 4070RTX 4090VRAM requirements will vary depending on image resolution.Batch AutomationThis public release contains the single-image workflow.Internally, I use a custom Python automation system connected directly to the ComfyUI API that can process large batches automatically.Example setup:1 source face400+ target imagesAutomatic queue managementAutomatic retriesOrganized output foldersGPU-friendly processingDesigned for T4 cloud instancesThis automation system is not included in the public release.Commercial ApplicationsThis workflow can be used for:UGC generationMarketing campaignsCreator replacementCharacter consistency projectsAI influencer pipelinesContent automationNeed Batch Processing?I also develop custom automation systems built around ComfyUI.Examples:Face swap automationFolder-based processingComfyUI API integrationsLarge-scale image generation pipelinesDataset creation workflowsCustom workflow developmentIf you're interested in automation or custom solutions, feel free to send me a direct message on Civitai.CreditsBuilt and tested using FLUX.2 Klein 9B, latent reference conditioning, and a dedicated face swap LoRA for high-consistency identity transfer.If you find this workflow useful, consider leaving a rating and sharing your results.
FLUX.2-Klein-GGUF-Multi-LoRA-dAIver-v1.5 – Optimized Low-VRAM Multi-LoRA Workflow for Flux.2 Klein 9B (GGUF)
Optimized Low-VRAM Multi-LoRA Workflow for Flux.2 Klein 9B (GGUF)A refined and enhanced workflow by Experimental_dAIver and adapted for Flux.2 KleinThis workflow delivers the full power of Flux.2 Klein 9B in GGUF format, specially optimized for GPUs with less than 8 GB VRAM, like my RTX 4050 with only 6 GB. The integrated CacheDiT_Model_Optimizer and PatchSageAttentionKJ (both optional!) provide a noticeable speed boost with almost no quality loss. Full NdSuperLoraLoader support for easy multi-LoRA stacking with automatic trigger-word integration, the intuitive selectLatentSizePlus aspect-ratio and resolution selector, plus a complete SEEDVR2 Video Upscaler Subgraph for stunning high-resolution results complete this elegant and highly flexible setup.Version 1.5 is my initial public release and brings significant improvements in speed, usability, multi-LoRA handling and upscaling quality — while remaining extremely VRAM-efficient (tested on RTX 4050 with only 6 GB).Key features in v1.5:Full adaptation to Flux.2 Klein 9B with dedicated GGUF loader setup and the new Qwen3-8B GGUF text encoderNdSuperLoraLoader with full multi-LoRA support, auto-fetch trigger words and easy strength controlselectLatentSizePlus — intuitive aspect-ratio and resolution selector with beautiful presets (including golden-ratio-friendly options) plus easy orientation swapFull SEEDVR2 Video Upscaler Subgraph — powerful DiT-based high-end upscaler that delivers stunning 4K+ results with intelligent resolution handling, Lab color correction and temporal settings. Works exceptionally well on still images tooImproved workflow organization, expanded notes with recommended settings, and more robust saving options via SaveImageExtendedCacheDiT and SageAttention integration for optimized performance on the smaller, faster Flux.2 Klein modelRequired Custom NodesComfyUI-GGUF (UnetLoaderGGUF + CLIPLoaderGGUF)ComfyUI-CacheDiT (CacheDiT_Model_Optimizer)comfyui-kjnodes (PathchSageAttentionKJ and related nodes)ComfyUi-MzMaXaM (selectLatentSizePlus)save-image-extended-comfyui (SaveImageExtended)ComfyUI-SeedVR2_VideoUpscaler (full upscaler subgraph)Models & Downloads (exact paths)The following list explains the base models I am most frequently using with this workflow. The list as well explains where to put each file after you downloaded it.1. Main Model (Flux.2 Klein 9B GGUF):File: flux2Klein-9B-Q4_1.gguf (or any other GGUF quant you prefer)Download: Community GGUF quants for Flux.2 Klein are available on Hugging Face (search “flux2 klein gguf” or check repositories by city96 and similar quantizers)Target folder: ComfyUI/models/diffusion_models/ (or Flux/ subfolder)2. Text Encoder (CLIP)File: Qwen3-8B-Q4_K_M.ggufDownload: https://huggingface.co/mradermacher/Qwen3-8B-Q4_K_M-GGUF/resolve/main/Qwen3-8B-Q4_K_M.gguf (or equivalent Qwen3-8B GGUF quant)Target folder: ComfyUI/models/clip/ or ComfyUI/models/text_encoders/3. VAEFile: full_encoder_small_decoder.safetensors (specific VAE for Flux.2 Klein setups)Download: Usually provided together with Flux.2 Klein GGUF packages or available from the ComfyUI community / workflow author collectionTarget folder: ComfyUI/models/vae/4. Upscalers4× Upscaler: 4x-UltraSharp → https://civitai.com/models/116225/4x-ultrasharp1× Skin-Contrast Upscaler: 1xSkinContrast-High-SuperUltraCompact.pth → https://huggingface.co/notkenski/upscalers/blob/main/1xSkinContrast-High-SuperUltraCompact.pthTarget folder: ComfyUI/models/upscale_models/5. LoRAs (for NdSuperLoraLoader – full multi-LoRA support)Any Flux-compatible LoRA (.safetensors)Target folder: ComfyUI/models/loras/6. SEEDVR2 Models (for the high-end upscaler subgraph – optional but recommended)DiT Model: seedvr2_ema_3b-Q8_0.ggufVAE: ema_vae_fp16.safetensorsDownload from the official ComfyUI-SeedVR2_VideoUpscaler repository or Hugging Face and place in the folders required by the custom node.Recommended SettingsSampler: EulerScheduler: Simple or BetaSteps: 4CFG Scale: 1~1.5Shift: 4–7Resolution: freely selectable via the selectLatentSizePlus node (many golden-ratio-friendly presets included, swap orientation with one click)How to use the workflowLoad the JSON in ComfyUI.Select your desired aspect ratio and resolution in the selectLatentSizePlus node.Enter your prompt in the Positive Prompt node (the NdSuperLoraLoader automatically handles trigger words from your LoRAs).Load one or more Flux-compatible LoRAs into the NdSuperLoraLoader.Generate. The workflow produces a high-quality base image.(Optional) Run the SEEDVR2 upscaler subgraph for beautiful high-resolution results on images or video.Use SaveImageExtended for full filename, metadata and folder control.You can bypass the upscaler group completely for fast testing. The workflow also works with regular .safetensors Flux.2 Klein checkpoints if you replace the GGUF loaders with the standard nodes (higher VRAM usage).This is a clean, fast and powerful base specifically tuned for the new Flux.2 Klein 9B model — perfect for quick iterations, multi-LoRA compositions and high-quality final outputs even on modest hardware.Huge thanks to WikkedAI for the original foundation and to the creators of CacheDiT, SageAttention, NdSuperLoraLoader, selectLatentSizePlus and SeedVR2 for making Flux.2 Klein so accessible on low-VRAM GPUs.If you have questions or want to share your results — I’m happy to hear from you in the comments. Enjoy the workflow!
FLUX-GGUF-Multi-LoRA-dAIver-v1.5 – Optimized Low-VRAM Multi-LoRA Workflow for Flux.1 Dev (GGUF)
Optimized Low-VRAM Multi-LoRA Workflow for Flux.1 Dev (GGUF)Another new, refined and enhanced workflow by Experimental_dAIverThis workflow delivers the full power of Flux.1 Dev in GGUF format, specially optimized for GPUs with less than 8 GB VRAM, like my RTX 4050 with only 6 GB. The integrated CacheDiT_Model_Optimizer and PatchSageAttentionKJ (both optional!) provide a noticeable speed boost with almost no quality loss. Full NdSuperLoraLoader support for easy multi-LoRA stacking with automatic trigger-word integration, the intuitive selectLatentSizePlus aspect-ratio and resolution selector, plus a complete SEEDVR2 Video Upscaler Subgraph (base provided by @LumaRift) for stunning high-resolution results complete this elegant and highly flexible setup.Version 1.5 is my first public release and brings significant improvements in speed, usability, multi-LoRA handling and upscaling quality — while remaining extremely VRAM-efficient (tested on RTX 4050 with only 6 GB).Key features in v1.5:NdSuperLoraLoader with full multi-LoRA support, auto-fetch trigger words and easy strength controlselectLatentSizePlus — intuitive aspect-ratio and resolution selector with beautiful presets (including golden-ratio-friendly options) plus easy orientation swapFull SEEDVR2 Video Upscaler Subgraph — powerful DiT-based high-end upscaler that delivers stunning 4K+ results with intelligent resolution handling, Lab color correction and temporal settings. Works exceptionally well on still images too, producing superior detail and coherenceImproved workflow organization, expanded notes with recommended settings, and more robust saving options via SaveImageExtendedCacheDiT and SageAttention integration for optimized Flux performance on low-VRAM hardwareRequired Custom NodesComfyUI-GGUF - https://github.com/city96/ComfyUI-GGUF - UnetLoaderGGUF + CLIPLoaderGGUFnd-super-nodes - https://github.com/HenkDz/nd-super-nodes - NdSuperLoraLoader with tags, trigger words & beautiful UIsave-image-extended-comfyui - https://github.com/thedyze/save-image-extended-comfyui - Advanced saving with metadata & dynamic filenamesComfyUi-MzMaXaM - https://github.com/MzMaXaM/ComfyUi-MzMaXaM - selectLatentSizePlusComfyUI-SeedVR2_VideoUpscaler - https://github.com/numz/ComfyUI-SeedVR2_VideoUpscaler - SEEDVR2 Video Upscaler SubgraphModels & Downloads (exact paths)The following list explains the base models I am most frequently using with this workflow. The list as well explains where to put each file after you downloaded it.1. Main Model (Flux.1 Dev GGUF):File: flux1-dev-Q5_1.gguf (or any other GGUF quant you prefer – Q4, Q5, Q6 or Q8 all work well)Download: https://huggingface.co/city96/FLUX.1-dev-gguf/resolve/main/flux1-dev-Q5_1.ggufTarget folder: ComfyUI/models/diffusion_models/ (or Flux/ subfolder)2. Text Encoder (CLIP)File: t5xxl_fp8_e4m3fn.safetensors + clip_l.safetensors (standard Flux pair)Download t5xxl: https://huggingface.co/comfyanonymous/flux_text_encoders/resolve/main/t5xxl_fp8_e4m3fn.safetensors Download clip_l: https://huggingface.co/comfyanonymous/flux_text_encoders/resolve/main/clip_l.safetensorsTarget folder: ComfyUI/models/clip/ or ComfyUI/models/text_encoders/3. VAEFile: ae.safetensorsDownload: https://huggingface.co/Comfy-Org/flux1-dev/resolve/main/split_files/vae/ae.safetensorsTarget folder: ComfyUI/models/vae/4. Upscalers4× Upscaler: 4x-UltraSharp → https://civitai.com/models/116225/4x-ultrasharp1× Skin-Contrast Upscaler: 1xSkinContrast-High-SuperUltraCompact.pth → https://huggingface.co/notkenski/upscalers/blob/main/1xSkinContrast-High-SuperUltraCompact.pthTarget folder: ComfyUI/models/upscale_models/5. LoRAs (for NdSuperLoraLoader – full multi-LoRA support)Any Flux-compatible LoRA (.safetensors)Target folder: ComfyUI/models/loras/6. SEEDVR2 Models (for the high-end upscaler subgraph – optional but recommended)DiT Model: seedvr2_ema_3b-Q8_0.ggufVAE: ema_vae_fp16.safetensorsDownload from the official ComfyUI-SeedVR2_VideoUpscaler repository or Hugging Face and place in the folders required by the custom node.Recommended SettingsSampler: Euler or Euler ancestral Scheduler: Simple, Normal or Beta Steps: 20–40 CFG Scale: 1.0 Flux Guidance: 3–6 Shift: 4–7 Resolution: freely selectable via the selectLatentSizePlus node (many golden-ratio-friendly presets included, swap orientation with one click)How to use the workflowLoad the JSON in ComfyUI.Select your desired aspect ratio and resolution in the selectLatentSizePlus node (enable swap_orientation if needed).Enter your prompt in the Positive Prompt node (the NdSuperLoraLoader will automatically pull trigger words from your LoRAs).(Optional) Load one or more Flux-compatible LoRAs into the NdSuperLoraLoader – strengths and triggers are handled elegantly.Generate. The first stage produces a high-quality base image.(Optional) Run the SEEDVR2 upscaler subgraph for beautiful 2–4× upscales or even video. It works great on still images too.The SaveImageExtended node gives you full control over filenames, metadata and folder structure.You can bypass the entire upscaler group if you just want fast test generations. The workflow also works with regular .safetensors Flux checkpoints – simply replace the UnetLoaderGGUF and DualCLIPLoader with the standard nodes.This is a clean, powerful and future-proof base for all your Flux.1 Dev work – whether you want fast single-LoRA portraits, complex multi-LoRA scenes or high-end upscaled output. I’ve been using it daily on my 6 GB card and it feels snappy and reliable.Huge thanks to WikkedAI for the original WikkedZITv4 foundation and to the creators of CacheDiT, SageAttention, NdSuperLoraLoader, selectLatentSizePlus and SeedVR2 for making low-VRAM Flux so enjoyable.If you have questions, feedback or want to share your results – I’m always happy to hear from you in the comments. Enjoy the workflow and happy creating!
LTX 2.3 Workflows (RuneXX workflows, remade by Stefan Falkok) + NSFW (Base I2V, First-Last frame, Controlnet, Edit, Add Audio + Lipsync, Foley, Extended Video)
all base workflows for ltx 2.3, remade by me, creator is RuneXXMy ComfyUI Build - https://huggingface.co/datasets/StefanFalkok/ComfyUI_portable_torch_2.11.0_cu130_cp313_sageattention_triton/tree/mainMy NSFW TG Channel - https://t.me/stefanfalkokmothMy TG Channel - https://t.me/StefanFalkokAIMy TG Chat - https://t.me/+y4R5JybDZcFjMjFi
Gemma 4 Text Generation ComfyUI workflow | Image-Text-Audio Analysis Tool
Transforms visuals and audio into intelligent, coherent text outputs fast.Who it's for: creators who want this pipeline in ComfyUI without assembling nodes from scratch. Not for: one-click results with zero tuning - you still choose inputs, prompts, and settings.Open preloaded workflow on RunComfyOpen preloaded workflow on RunComfy (browser)Why RunComfy first- Fewer missing-node surprises - run the graph in a managed environment before you mirror it locally.- Quick GPU tryout - useful if your local VRAM or install time is the bottleneck.- Matches the published JSON - the zip follows the same runnable workflow you can open on RunComfy.When downloading for local ComfyUI makes sense - you want full control over models on disk, batch scripting, or offline runs.How to use (local ComfyUI)1. Load inputs (images/video/audio) in the marked loader nodes.2. Set prompts, resolution, and seeds; start with a short test run.3. Export from the Save / Write nodes shown in the graph.Expectations - First run may pull large weights; cloud runs may require a free RunComfy account.OverviewThis workflow empowers you to create coherent text outputs guided by visual, audio, and video cues. You can analyze media, summarize reviews, or prototype lightweight chatbots with accurate context grounding. It integrates ComfyUI nodes for text, CLIP, and transcription tasks seamlessly. The setup boosts efficiency in LLM testing and multimodal research. Ideal for designers and developers seeking fast, context-aware AI text generation.Important nodes:Key nodes in Comfyui Gemma 4 Text Generation ComfyUI workflowTextGenerate (#1)Drives the final output and is where most tuning lives. Adjust how long the response can be and how exploratory it should feel by changing the maximum tokens and sampling temperature. Enable the optional reasoning mode if you want more step‑by‑step thinking before the answer. For implementation details, see the ComfyUI text generation node source code here.CLIPLoader (#3)Selects and loads the Gemma 4 E4B encoder package needed for text and multimodal understanding. If you maintain models locally, place the file under:ComfyUI/models/text_encoders/gemma4_e4b_it_fp8_scaled.safetensorsAfter selection, you rarely need to revisit this node unless you switch model variants.GetVideoComponents (#7)Useful when you want the model to consider video. It exposes frames and audio so you can condition TextGenerate on both. If your clip is long, choose a smaller set of frames for faster turnaround; if you need finer detail, increase the frame sampling at the cost of speed.NotesGemma 4 Text Generation ComfyUI workflow | Image-Text-Audio Analysis Tool - see RunComfy page for the latest node requirements.
TripoSplat image to 3D Gaussian Splats workflow in ComfyUI | Image2Model
Turn one image into 3D Gaussian Splats with TripoSplat.Who it's for: creators who want this pipeline in ComfyUI without assembling nodes from scratch. Not for: one-click results with zero tuning - you still choose inputs, prompts, and settings.Open preloaded workflow on RunComfyOpen preloaded workflow on RunComfy (browser)Why RunComfy first- Fewer missing-node surprises - run the graph in a managed environment before you mirror it locally.- Quick GPU tryout - useful if your local VRAM or install time is the bottleneck.- Matches the published JSON - the zip follows the same runnable workflow you can open on RunComfy.When downloading for local ComfyUI makes sense - you want full control over models on disk, batch scripting, or offline runs.How to use (local ComfyUI)1. Load inputs (images/video/audio) in the marked loader nodes.2. Set prompts, resolution, and seeds; start with a short test run.3. Export from the Save / Write nodes shown in the graph.Expectations - First run may pull large weights; cloud runs may require a free RunComfy account.OverviewThis ComfyUI workflow helps you turn a single image into a realistic 3D Gaussian Splat model ready for visualization or export. It automates background removal, depth conditioning, and splat rendering for efficient production. SPZ export and orbit-preview video are generated instantly. The workflow supports mesh conversion and runs smoothly with native TripoSplat integration. Perfect for designers creating 3D assets from minimal inputs.Important nodes:Key nodes in ComfyUI TripoSplat image to 3D Gaussian Splats workflowVAEDecodeTripoSplat (#55)Decodes diffusion latents into a full 3D Gaussian Splats representation. The num_gaussians control governs density and memory use. Higher values create denser splats and smoother silhouettes but take longer and require more VRAM; start modestly and scale until coverage and detail meet your needs.KSampler (#6)Drives TripoSplat inference using the conditioning and initial latent. Adjust seed for new structural variations from the same image. Keep other sampler choices stable while you evaluate changes in foreground extraction and subject composition.TripoSplatConditioning (#24)Builds the vision guidance that makes single‑image 3D feasible by combining DINO features with a VAE latent. Good results depend on a clean, centered subject and a mask that excludes busy backgrounds.RenderSplat (#75)Renders the resulting splats to images for the preview turntable. Tune output size for the balance between crispness and speed, and use the camera info input from CreateCameraInfo (#79) to control orbit style.SplatToMesh (#76)Converts the Gaussian representation to a polygonal mesh for GLB export. Expect lower fine detail than native splats; treat this as a convenience path when your target toolchain requires meshes.NotesTripoSplat image to 3D Gaussian Splats workflow in ComfyUI | Image2Model - see RunComfy page for the latest node requirements.
Stable Audio 3.0 Medium Base workflow in ComfyUI | Text-to-Audio
Turn prompts into rich, realistic audio and music instantly.Who it's for: creators who want this pipeline in ComfyUI without assembling nodes from scratch. Not for: one-click results with zero tuning - you still choose inputs, prompts, and settings.Open preloaded workflow on RunComfyOpen preloaded workflow on RunComfy (browser)Why RunComfy first- Fewer missing-node surprises - run the graph in a managed environment before you mirror it locally.- Quick GPU tryout - useful if your local VRAM or install time is the bottleneck.- Matches the published JSON - the zip follows the same runnable workflow you can open on RunComfy.When downloading for local ComfyUI makes sense - you want full control over models on disk, batch scripting, or offline runs.How to use (local ComfyUI)1. Load inputs (images/video/audio) in the marked loader nodes.2. Set prompts, resolution, and seeds; start with a short test run.3. Export from the Save / Write nodes shown in the graph.Expectations - First run may pull large weights; cloud runs may require a free RunComfy account.OverviewWith this official audio generation setup, you can turn text prompts into expressive, high-quality music and ambient audio. It supports extended playback, smooth tonal transitions, and flexible sound layering. Great for sound designers, musicians, or developers experimenting with text-to-audio generation. The workflow uses T5Gemma and Qwen3.5 encoders to enhance prompt accuracy and output quality. Its reproducible structure ensures consistent creative results for professional audio projects.Important nodes:Key nodes in Comfyui Stable Audio 3.0 Medium Base workflowComfySwitchNode (#34). Toggles between the original user_input and the Qwen-generated text. Turn it on for structured, length-matched rewrites or off for direct control.TextGenerate (#28). Runs Qwen3.5 with a category-specific system prompt to expand ideas. To customize the rewrite style, edit the category templates in JsonExtractString (#49) and the glue prompts in the adjacent Text Replace nodes.EmptyLatentAudio (#11). Sets clip length. Keep this aligned with the inserted AUDIO_LENGTH token so the synthesis time matches the textual intent.KSampler (#3). Governs the denoising trajectory for Stable Audio 3. Adjust seed for variations while keeping other settings stable to compare takes fairly.SaveAudioMP3 (#19). Controls the output filename prefix and format for quick library building from multiple runs.NotesStable Audio 3.0 Medium Base workflow in ComfyUI | Text-to-Audio - see RunComfy page for the latest node requirements.
Z Image Real Skin workflow in ComfyUI | Natural Texture Portraits
Creates portraits with real human skin texture and natural lighting.Who it's for: creators who want this pipeline in ComfyUI without assembling nodes from scratch. Not for: one-click results with zero tuning - you still choose inputs, prompts, and settings.Open preloaded workflow on RunComfyOpen preloaded workflow on RunComfy (browser)Why RunComfy first- Fewer missing-node surprises - run the graph in a managed environment before you mirror it locally.- Quick GPU tryout - useful if your local VRAM or install time is the bottleneck.- Matches the published JSON - the zip follows the same runnable workflow you can open on RunComfy.When downloading for local ComfyUI makes sense - you want full control over models on disk, batch scripting, or offline runs.How to use (local ComfyUI)1. Load inputs (images/video/audio) in the marked loader nodes.2. Set prompts, resolution, and seeds; start with a short test run.3. Export from the Save / Write nodes shown in the graph.Expectations - First run may pull large weights; cloud runs may require a free RunComfy account.OverviewThis advanced workflow helps bring out lifelike skin details in portraits, ensuring pores, freckles, and natural tones remain beautifully visible. It uses smart integration of turbo acceleration and realism-guided LoRA to prevent smoothing or plastic-like surfaces. Ideal for fashion, beauty, and editorial creators seeking authentic human texture. You can control light softness, contrast, and clarity while maintaining high-resolution rendering. Designed for artists who value genuine depth and realism, it makes each face expressive, rich, and true to life.Important nodes:Key nodes in Comfyui Z Image Real Skin workflowAILab_QwenVL (#308)Purpose: Converts a reference portrait into a concise prompt that preserves identity cues, wardrobe, lighting, and the “real skin” brief.Tips: Use a clean, well-lit reference. Shorter outputs skew toward broad style matches; more descriptive outputs steer composition and wardrobe more tightly.FluxGuidance (#166)Purpose: Balances textual obedience with model prior. Lower values breathe a bit more natural variance into skin; higher values enforce stricter prompt adherence.Tips: If pores fade or skin looks plastic, ease guidance down. If the model drifts from wardrobe or lighting, nudge guidance up.Lora Loader (#438) Unfiltered Realism v2Purpose: Restores microtexture and authentic tonal curve.Tips: Increase slightly for drier, crisper pores; decrease if grain or minor artifacts appear on cheeks or forehead.Lora Loader (#439) Kook Zimage Realistic Fantasy TurboPurpose: Adds a light editorial accent and cleaner color separation while keeping the “real skin” brief intact.Tips: Raise for a glossier magazine vibe; lower for a more documentary look.CFGNorm (#305)Purpose: Normalizes guidance so changes in text strength or LoRA weight do not swing exposure and saturation.Tips: Keep enabled when comparing sampler heads to ensure fair A/B judgments.KSampler heads (#251, #255, #478, #487)Purpose: Four parallel samplers with different scheduler flavors let you compare skin texture, micro-contrast, and bokeh behavior at a glance.Tips: Use the base branch for balanced realism, try the flow-matching branch when you want crisp pores with smooth gradients, use the SGM branch for softer rolloff, and pick the beta scheduler for moodier tonality.NotesZ Image Real Skin workflow in ComfyUI | Natural Texture Portraits - see RunComfy page for the latest node requirements.
LTX 2.3 Sulphur 2 Prompt Relay Workflow in ComfyUI | Image2Video Motion Control
Turns still images into cinematic motion-controlled videos instantly.Who it's for: creators who want this pipeline in ComfyUI without assembling nodes from scratch. Not for: one-click results with zero tuning - you still choose inputs, prompts, and settings.Open preloaded workflow on RunComfyOpen preloaded workflow on RunComfy (browser)Why RunComfy first- Fewer missing-node surprises - run the graph in a managed environment before you mirror it locally.- Quick GPU tryout - useful if your local VRAM or install time is the bottleneck.- Matches the published JSON - the zip follows the same runnable workflow you can open on RunComfy.When downloading for local ComfyUI makes sense - you want full control over models on disk, batch scripting, or offline runs.How to use (local ComfyUI)1. Load inputs (images/video/audio) in the marked loader nodes.2. Set prompts, resolution, and seeds; start with a short test run.3. Export from the Save / Write nodes shown in the graph.Expectations - First run may pull large weights; cloud runs may require a free RunComfy account.OverviewThis setup helps you turn static images into cinematic video clips enhanced by motion-aware prompts. It combines LTX 2.3 video generation with Sulphur 2 motion control for smoother transitions and lifelike camera moves. With segmented prompt sequencing, you can define micro-actions for each moment. It supports realistic lighting, expressive movement, and scene continuity. The system provides an efficient path to transform images into professional-level cinematic storytelling sequences.Important nodes:Key nodes in Comfyui LTX 2.3 Sulphur 2 Prompt Relay workflowPromptRelaySmartEncode (#610)Purpose: Translates your beat‑by‑beat “smart prompt” into properly timed text conditioning for the whole clip. Use global_prompt for unchanging details (style, subject, lighting) and smart_prompt for the action sequence. Two authoring styles are supported: inline segments separated by | with optional proportional tags like [0-50], or block headers like “Scene 1:” that weight segments by range. Keep one syntax per prompt to avoid ambiguity. Reference: ComfyUI‑PromptRelay.LTXVImgToVideoInplaceKJ (#617)Purpose: Locks the first frame’s look and gently propagates it through motion. If identity or wardrobe drifts, raise its image adherence; if motion seems constrained, lower it to allow more dynamics. Balance this with your Sulphur 2 LoRA strength so the reference remains stable without over‑freezing motion.LoraLoaderModelOnly (#628) — Sulphur 2 motion LoRAPurpose: Injects the Sulphur 2 fine‑tune to bias motion continuity, trajectory smoothness, and action staging. Increase strength_model to emphasize guided movement across segments; reduce it if you see over‑constraint or repeated patterns. Adjust in tandem with ImgToVideoInplace strength to keep subject fidelity and motion energy in harmony.LTXVConditioning (#164)Purpose: Consolidates positive/negative conditioning for LTX‑2.3 and sets the clip’s frame rate. If you lengthen the shot, revisit your Prompt Relay segment weights so the relative timing still matches the intended beats.SamplerCustom (#561)Purpose: Runs the denoising pass using your chosen sampler and schedule. If motion is jittery, try a slightly smoother schedule or a sampler known for temporal stability; if prompts under‑steer, modestly raise guidance while watching for over‑saturation. Use VisualizeSigmasKJ to sanity‑check the schedule’s shape before long runs.NotesLTX 2.3 Sulphur 2 Prompt Relay Workflow in ComfyUI | Image2Video Motion Control - see RunComfy page for the latest node requirements.
HiDream O1 Image ComfyUI Image Editing | Precision Reference Edit Workflow
Edit photos smartly while keeping the original style intact.Who it's for: creators who want this pipeline in ComfyUI without assembling nodes from scratch. Not for: one-click results with zero tuning - you still choose inputs, prompts, and settings.Open preloaded workflow on RunComfyOpen preloaded workflow on RunComfy (browser)Why RunComfy first- Fewer missing-node surprises - run the graph in a managed environment before you mirror it locally.- Quick GPU tryout - useful if your local VRAM or install time is the bottleneck.- Matches the published JSON - the zip follows the same runnable workflow you can open on RunComfy.When downloading for local ComfyUI makes sense - you want full control over models on disk, batch scripting, or offline runs.How to use (local ComfyUI)1. Load inputs (images/video/audio) in the marked loader nodes.2. Set prompts, resolution, and seeds; start with a short test run.3. Export from the Save / Write nodes shown in the graph.Expectations - First run may pull large weights; cloud runs may require a free RunComfy account.OverviewThis workflow empowers you to refine portraits, products, and interiors through prompt-guided image modifications that keep composition intact. It integrates an efficient loader, conditioner, and sampler structure for reproducible results. You can restyle images, adjust aesthetics, or test visual variations quickly. Every edit stays true to the original layout, ensuring consistency. Ideal for designers testing looks or visual directions without redoing entire compositions.Important nodes:Key nodes in Comfyui HiDream O1 Image ComfyUI Image Editing workflowHiDreamO1Sampler (#8)This is the heart of the pipeline where edits are synthesized. Parameters that matter most are output resolution, sampling steps, guidance scale, image-conditioning strength, and seed. Keep resolution aligned with your input’s aspect ratio, raise steps for tougher edits, and balance guidance with conditioning strength to trade off prompt obedience versus source fidelity.HiDreamO1Conditioning (#9)Defines what to change and what to avoid. Favor concise, unambiguous instructions in the positive prompt and reserve stylistic or artifact-avoidance terms for the negative prompt. When edits feel too strong or off-target, simplify the instruction or reduce conflicting style words.HiDreamO1ModelLoader (#2)Loads the HiDream O1 Image BF16 checkpoint used by the sampler. Use BF16 for a good balance of speed and memory usage, and switch checkpoints when you need a different aesthetic or domain. If you swap models, recheck guidance and conditioning strength, since optimal values can shift across checkpoints.NotesHiDream O1 Image ComfyUI Image Editing | Precision Reference Edit Workflow - see RunComfy page for the latest node requirements.
Zit Workflow Upscale Control Net and Ollama
This is my daily workflow for Zit. I think everything is pretty well organized with group bypassers so you only need to run what you need. The Lora Manager nodes and save nodes grab all relevant resources for posting to Civit saving the hassle of adding Metadata manually. There is a free Ram function at the end of the upscale because I noticed my pc holding it lol. Just delete it if you dont care. All of the nodes are pinned because I remote in from work on my phone and got sick of accidentally moving shit around. The couple of subgroups that are in the Workflow are for the save nodes so you will want to open them up and change your file names, or just expand them altogether, I like em, some people dont.Can't think of much more to say but if you have questions please ask and I'll try to help as much as I can.
Ideogram 4 PiD Upscale Workflow
All links to models are on a note in the workflowPiD reformulates the latent-to-pixel decoder as a conditional pixel-space diffusion model, unifying decoding and upsampling into a single generative module. It denoises directly in high-resolution pixel space and produces a super-resolved image in one pass.This workflow takes an Ideogram 4 generations latent from 512x512>2048x2048/1024x1024>4096x4096 or 16:9, 4:3, 3:4 aspect ratios.
Z-Image Base & Turbo Workflow I2I/T2I (Low or High VRAM)
This is an advanced workflow designed for those familiar with ComfyUI who want pro grade results. It is node heavy and has numerous options. I encourage you to take the time to learn it. If you feel overwhelmed, you can start with my simple model HERE也有中文说明Instagram: https://www.instagram.com/synth.studio.models/Buy me a☕ https://ko-fi.com/lonecatoneThis represents hundreds of hours of work. If you enjoy it, please 👍like, 💬 comment , and feel free to ⚡tip 😉Note: If you have ANY issues with nodes not downloading, read the notes or reach out. There's nothing that special about any of them that aren't core modules. Most issues can be resolved by updating everything⛔⚠️🛑✋ Read the notes completly before using. Most common install and node problems are listed in the directionsA complete user and troubleshooting guide inclusing a list of common error messages can be found here https://civitai.com/articles/24678/how-to-use-my-workflows-a-comprehensive-breakdownV14.0Because it is not in my nature to leave things alone....Gutted the stock face detailer nodes and replaced them with a SEGS suite for infinately better resultsNote: Yes, I will be going through all my workflows and replacing them, including teh NSFW onesControlnet Update.Added local bypass nodes so you don't have to zoom and scrollMajor update to notes, especially for detailersV13.0Overhauled the Controlnet:Now you can select the aspect ratio of the original image without having to "guess" it with the aspect ratio nodeLeft room for the resize node so you can choose which side to crop the image byRedid the dependencies so that every tie you shut it on and off, you don;t need to reset the switches so it will not give you an error 😡Massively improved the notes throughoutMinor layout tweaksV11.3Detailers are now able to handle float32 models, so I rewmoved the SDXL Based checkpoint.Please give me feedback with any issues on this, especailly RAM related.Added a crop section so you can...well... crop images easilyUpdated several areasAdded the ability to use a simple date with the metadata folderadded a "remove banned tags" nodeV8.0Removed Florence Prompt assist and replaced it with Qwen Advanced.Reorganized the controlnet section because it bugged me. Now it's easier to use.Added a LoRa controller for the detailer for better character facial and eye consistency as well as a localized promptGutted the backend of the post production suite and added 📷optical realism, giving a significantly better way to fine tune your images. Fixed some backend mathAdded a 📂 subfolder generator that seperates the metadata files according to the name you give the file for easier use.V7.0Added KSampler Configure Nodes so you can leave the setting in place for both ZIT and base without having to change themRemoved some problematic nodesRemoved Qwen Prompt enhancer. I refuse to put an API one in there.global scheduler and samplers for consistencyBetter mathImproved notes throughout.All in 1 workflow:ControlnetCheckpoint option for merged modelsI2IPrompt generationPrompt enhancementLora LoaderAdvanced KSamplerDraft mode for making corrections without having to rerun the workflow.Seed variance enhancerUltimate Upscaler for prescaling and hi res fixDetailing Suite for face, hands, eyes, and expressionsSeed VR2 Upscaler to get 4k on low VRAMMassive Post Production SuiteJPEG ScrubberSmart Noise scrubberFull tutorial available.也有中文说明Check out my other models:My NSFW version with Anantomy Correctors:https://civitai.com/models/2270894/zit-nsfw-anatomy-correctorFor ultimate Anime detail and control: https://civitai.com/models/2220766/zimage-ultra-anime-detail-workflow-get-the-most-out-of-your-generationsFor Realism and variety over the base model: https://civitai.com/models/2231181/z-image-ultra-real-workflow
LTX 2.3 Seed Hunter Multiroll Workflow
Change the way you approach LTX genning. We all know that prompt adherence with LTX is notoriously bad. The model treats your prompts more like suggestions that it can ignore at will. So I say, stop beating your head on the wall trying to prompt better. Instead, the path to success with the model is to see the outcomes of many seeds quickly, and be able to choose one to bring to finalization. This is the main workflow I use to produce my short films, and I hope you all enjoy it too.See my full tutorial video showing how to use the workflow here:
Illustrious/ Pony/ SDXL SFW & NSFW Pro Grade Workflow (Low and high VRAM)
Note: I spend a lot of time on these to make sure they are top notch. If you have ANY issues, I'm very responsive. hit me up and I'll resolve them for you.This is an advanced workflow. It is node heavy and designed for multiple options and to return professional high quality results. If you are looking for simpler workflows, they are here:An essentials one can be found here: https://civitai.com/models/2349309/illustriousponysdxl-essentialsA simple one can be found here:https://civitai.red/models/2600919/lonecats-simple-zitilluanimaflux-workflows?modelVersionId=2921603A complete user and troubleshooting guide inclusing a list of common error messages can be found here https://civitai.com/articles/24678/how-to-use-my-workflows-a-comprehensive-breakdownInstagram: https://www.instagram.com/synth.studio.models/Buy me a☕ https://ko-fi.com/lonecatoneThis represents hundreds of hours of work. If you enjoy it, please 👍like, 💬 comment , and feel free to ⚡tip 😉也有中文说明VER 10.1:Got tired of having to always mess with resolution, so I gave you the option to make it automaticMath node replacements to deal with the Linux errorsAdded psst... fast bypassers (you'll thank me).💡use the upgraded face yolo I added. much more accurate.Improved notes throughoutVer 8.0/ 9.0:Major overhaul to bring it up to speed with my other workflowsAdded second checkpoint metadataadded a prompt to hi-res fixadded Inpainting suite from the pro grade workflow by request.V7.0Apparantly , I forgot to hook up Face Swap in my last model and nobody told me until today, so a free major upgrade it is!Installed a sentence remover in the prompt assist area to help eliminate CivitAI 🚩Cleaned up some bugsResinstalled Qwen VL Prompt EnhancerUpgraded Face Swapalso upgraded notes on how to remove it.Minor changes to detailersAdded an inline crop tool in the post production suite.Ver 6.0:Major overhaul to bring it up to speed with my other workflowsAdded a refiner checkpoint that can easily be switched on or offAdded FaceID as well as a style and composition IP Adapter for character consistencyReowked the Detailers ro improve thembetter version of Hi Rez fixReworked the Save with Metadata to align with CivitAi and fix the Comfy update bug 🙄This is an all in one workflow:ControlnetI2I with prompt generationDual Model Loader: Better controlSage Attention: Speeds up productionUltimate upscaler: For prescale and hi-res fixDetailers: Face, eyes, hand, expressionNSFW Detailers: Male & Female anatomySeed VR2 Upscaler: Get up to 4k pics, even on low VRAMPost production suite: My pride and joy. Does everything.
Sillytavern Expressions Workflow
Another ST workflow, but hopefully not as big as some of the others I've seen. On my 3060, images take 15s to finish, and all 28 takes about 7 minutes. Updates are mostly to fix node problems. If yours works, there's no need to update. Works best on images with black backgrounds.There are more instructions in the workflow, but the most important thing to remember is to set the batch size to 28 to get all the emotes.Nodes aligned with NodeAligner:https://github.com/Tenney95/ComfyUI-NodeAlignerThis was made with a version of Comfy with an older version of Python (from 6/27/25). Newer versions have some crap about WAS Suite and whatever OpenCV is that prevents Comfy from launching properly.
LTX-2.3, simple workflow. T2V, I2V, I2V external audio, FFLF
Pretty simple workflow for LTXV with 3 modes so far and quite an early version. There is no prompt enchancer; in my opinion, it's useless garbage as a tool, and text LLM work mostly works very slow in ComfyUI. There is no latent upscaling. Almost the same useless garbage.Setting the full resolution will be faster and better than half resolution and latent upscaling with an interpolated result, but it requires resources like second generation. If your system is not powerful enough for the full resolution you set, almost certainly the server will run out of memory on the latent upscale stage. And that's even worse in IMG2video cases with the pixel upscaler itself.The workflow works fine on my 8GB VRAM videocard at 720p; I haven't tried higher resolution yet on FP8 dev model with distilled lora. There is a reason why VAE are separated into loaders and files, I haven't finished that part fully. Controlling it is the same as any other my workflow. If you try even one of my workflows, it will be similar.
Reed Anima T2I Workflow
Reed Anima T2I Workflow
IMG2PROMPT Workflow
A very simple image to prompt workflow.
Moody Minimal Zimage Workflow
I just made a new Telegram Group and Discord group drop in for chats, questions, feedbacks or just to share your work. 欢迎加入纸飞机和Discord群组。RH 体验地址：https://www.runninghub.ai/post/2062444041207373826/?inviteCode=cptpovgo喜欢我的作品吗？🎨 我会持续免费分享更多优质内容✨，欢迎支持一下，请我喝杯咖啡吧！💖 Like my work? 🎨 I share all my work for free ✨, so support me by buying me a coffee 💖!Ko-fi: ko-fi.com/catlover1937Fanvue: https://www.fanvue.com/catlover1937Please do not redistribute without consent. 如非作者同意禁止搬运。2026-06-04🚀 Moody Simple Workflow - Reborn! 🎉Guess what? 😆My Moody Simple Workflow has evolved so much over time that it's honestly not very "simple" anymore. 😂So I decided to create a brand new Minimal Workflow for everyone who:✨ Just wants to test ZImage quickly✨ Is completely new to ComfyUI✨ Wants an easy starting point without getting overwhelmed✨ Wants a small taste of what my full ZImage workflow can do 👀This workflow is intentionally kept as barebones and lightweight as possible 🪶✅ Minimal custom nodes✅ Beginner-friendly setup✅ Lots of notes and guides throughout the workflow✅ Easy to understand and modify✅ Great for learning the fundamentalsThink of it as the "starter pack" version of my full workflow — all the essentials, none of the chaos. 😎If you've ever opened my main workflow and thought:💀 "What am I even looking at?"This one is for you. 😂I hope this helps more people get started with ZImage and AI image generation without feeling overwhelmed.Have fun, and as always, happy generating! ❤️🔥🚀 Moody 简易工作流 - 重生啦！🎉猜猜怎么着？😆我的 Moody Simple Workflow 经过这么多次更新之后，已经进化到完全不「简单」了。😂所以我重新制作了一套全新的 极简版工作流，特别适合：✨ 想快速测试 ZImage 的朋友✨ 刚接触 ComfyUI 的新手✨ 不想一上来就被复杂节点吓到的人✨ 想先体验一下完整 ZImage 工作流能力的朋友 👀这套工作流刻意保持了 精简、轻量、易懂 的设计理念 🪶✅ 最少量的自定义节点✅ 新手友好✅ 内置大量注释和使用说明✅ 方便学习与修改✅ 快速掌握基础流程你可以把它理解成完整版工作流的「入门体验版」——保留核心功能，去掉各种花里胡哨的东西。😎如果你曾经打开我的完整工作流后：💀「这到底是什么天书？」那这套工作流就是为你准备的。😂希望它能帮助更多朋友轻松上手 ZImage 和 AI 绘图，不再被复杂的节点劝退。祝大家玩得开心！❤️🔥
Flux2 Klein 9b/4b simple workflow (TXT2IMG, IMG2IMG, Edit, Inpaint, metadata export for Civitai)
A simple workflow for Klein family models in the first row was developed for 9b and 4b distilled versions, but it should work for base models with minimal changes (such as replacing ConditioningZeroOut with negative conditioning).v3.3 Latent This is an experimental version of the workflow. It’s not intended for general use (though it might still work as a regular one). The main goal here is to slow down degradation when editing images individually by one-by-one editioning. Typically, using VAE decode artifacts appears after 3–5 edits, which can be addressed by simply removing the latent encoding/decoding steps via two nodes: Latent Loader and Latent Save. This approach fully bypasses VAE entirely for preview purposes—only to use it during editing previews.I implemented a chain of K-samplers and used a specific schema; while there are no visible artifacts, over time the colors fade slightly, but this is still better than the standard Edit mode. If you try it out, please provide feedback about this workflow (whether positive or negative). I recognize that other methods exist for restoring images, but they’re much more complicated—so I’m exploring this approach first.At least for now, changing the size in Latent Edit mode isn’t available. It’s possible, but it comes with many limitations; I didn’t find the way I like. So you’ll have the same size as what was saved (.latent file).
![[LTX 2.3] 4-Image Reference to Video (Manual Control + OmniNFT LoRA)](https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/2911664d-7470-4be9-b81a-6a4bc744f189/original=true/132770096.jpeg)
[LTX 2.3] 4-Image Reference to Video (Manual Control + OmniNFT LoRA)
🚀 Run this Workflow for FREE on Runninghub: https://www.runninghub.ai/post/2061355424439431169/?inviteCode=rh-v1497 (🎁 Tip: Sign up via the link above to get 1,000 free credits + 100 daily login points!) 🎥 Watch the Full Video Tutorial & Review: 🌟 OverviewReady to push LTX 2.3 to its absolute breaking point? This workflow is designed to handle 4 reference images, attempting to mimic the advanced multi-image capabilities of closed-source giants like Grok.Because pushing 4 images significantly increases the risk of consistency breakdown, this workflow uses Manual Nodes for the reference inputs. This gives you absolute granular control over how the global prompts and segmented prompts interact.🚀 Key FeaturesManual prompt relay Node Architecture: Built for power users who want strict control over 4 separate image indexes and text prompts.OmniNFT LoRA Included: Essential for maintaining character body proportions when feeding the model too much visual data. It helps keep the aesthetics clean even under heavy load.
LTX 2.3 3-Reference Image-to-Video
🚀 Run this Workflow for FREE on Runninghub: https://www.runninghub.ai/post/2061372745287553025/?inviteCode=rh-v1497(🎁 Tip: Sign up via the link above to get 1,000 free credits + 100 daily login points!) 🎥 Watch the Full Video Tutorial & Review: 🌟 OverviewMissing the multi-image referencing features from closed-source models like Seedance and Grok? This experimental workflow pushes the open-source LTX 2.3 model to handle 3 reference images simultaneously.By utilizing the smart nodes from Prompt Relay, we assign equal weights (1.0) and sequential index frames to smoothly blend multiple visual concepts into a single video generation.🚀 Key FeaturesSmart Prompt Relay: Uses the intuitive Prompt Relay smart node for clean and easy 3-image setup.Open-Source Alternative: A great starting point to mimic commercial multi-image video models.
NVIDIA PiD Flux1 — Smart 4× Detail Upscaler
A 1-click, 4-step upscaler built around NVIDIA's PiD (Pixel Diffusion) model on the Flux1 backbone. Feed it any image and it intelligently regenerates real, fine detail at 4× resolution — then supersamples it back down to a razor-sharp final image. An automatic captioner keeps the upscale faithful to your image's content, so you get crisp detail without hallucinated junk.✨ What makes this workflow differentWorks with ANY aspect ratio — 16:9, 9:16, square, anything. The input is auto-normalized to the model's native 1024px long-edge (e.g. a 1280×720 image becomes 1024×576), which is the #1 cause of broken/green-tinted PiD results. This is handled for you.Auto-prompting via Florence-2 — a vision model reads your image and writes a detailed caption automatically, guiding the upscaler to preserve the actual content. No manual prompting needed.Locked to the model's true 4× regime — PiD 1024→4096 is a fixed 4× model; this workflow targets exactly that for maximum sharpness (no blur from under/over-scaling).Supersampled final output — the 4096px result is Lanczos-downscaled back to 1024px, baking all 4× of generated detail into a clean, antialiased image with zero quality loss. You also get the full 4096px version saved.Side-by-side comparison — a built-in slider compares your original against the result.Fast — only 4 sampling steps (LCM).🔧 How to useInstall the 3 model files (links + folder layout below).Load the workflow, drop your image into the Load Image node.Hit Queue. That's it.Outputs:Full 4× image (e.g. 4096×2304) — saved via the first Save node.Supersampled 1024 image — crisp, detail-packed, saved via the second Save node.Tip: The PiD model is brightest/cleanest on near-square and landscape images. Extreme portrait crops can show mild color shifts — that's a known characteristic of the current distilled model, not the workflow.📥 Downloads Links Below:Gemma 2b: https://huggingface.co/Comfy-Org/PixelDiT/tree/main/text_encodersPiD models: https://huggingface.co/Comfy-Org/PixelDiT/tree/main/diffusion_modelsVAE: https://huggingface.co/Comfy-Org/z_image_turbo/tree/main/split_files/vae📂 ComfyUI/├── 📂 models/│ ├── 📂 text_encoders/│ │ └── gemma_2_2b_it_elm_bf16.safetensors│ ├── 📂 vae/│ │ └── ae.safetensors│ └── 📂 diffusion_models/│ └── pid_flux1_1024_to_4096_4step_bf16.safetensors📋 Required custom nodesComfyUI-Florence2 (auto-captioning)ComfyUI-Custom-Scripts (pythongosssss — ShowText / MathExpression)ComfyUI-easy-usergthree-comfy (Image Comparer)ComfyUI_Swwan (GetImageSizeAndCount)Requires a recent ComfyUI build with PixelDiT / PiD support. ~16GB VRAM recommended for the full 4096px pass.https://www.youtube.com/@AiMotionStudio
Ideogram-v4-workflow + Json Prompts
Ideogram-v4 workflow + Json prompts based on: https://blog.comfy.org/p/ideogram-4-day-0-support-in-comfyui{ "high_level_description": "", "style_description": { "aesthetics": "", "lighting": "", "photo": "", "medium": "", "color_palette": [] # hexadecimal values }, "compositional_deconstruction": { "background": "", "elements": [ { "type": "obj", # for object "bbox": [], # y_min, x_min, y_max, x_max "desc": "", "color_palette": [] # hexadecimal values }, { "type": "text", # for text "text": "", # the text to render "bbox": [], # y_min, x_min, y_max, x_max "desc": "", "color_palette": [] # hexadecimal values } ] } } Json prompts:https://huggingface.co/datasets/a3xrfgb/ideogram-v4-Json-prompts/tree/mainI'll keep adding more!for Sampler use 'Euler' instead of 'res_multistep' Otherwise you will get ugly noise artifacts.Example:{ "high_level_description": "A striking, editorial portrait features a woman whose eyes are obscured by a carefully arranged, overlapping composition of large, pale, fan-like seashells, set against a bright, diffused outdoor backdrop.", "style_description": { "aesthetics": "editorial portraiture, surreal", "lighting": "soft, natural daylight, diffused, creating gentle highlights on the shells and skin", "photo": "medium close-up portrait, high resolution", "medium": "digital photograph", "color_palette": [ "#A08D6B", "#D4C19A", "#2C3E50", "#E0E0E0" ] }, "compositional_deconstruction": { "background": "The background is an outdoor, slightly blurred scene suggesting a bright day near water, featuring soft tones of pale blue and muted grey-green.", "elements": [ { "type": "obj", "bbox": [ 0, 0, 400, 1000 ], "desc": "The distant background, showing a soft horizon line where muted blue sky meets a lighter, indistinct body of water or atmosphere, creating a shallow depth of field effect.", "color_palette": [ "#A9B8C2", "#DDEEFF", "#B0C4DE" ] }, { "type": "obj", "bbox": [ 270, 0, 820, 1000 ], "desc": "The woman's visible skin, covering her neck, shoulders, and mouth area. Her skin tone is deep and rich, with subtle highlights catching the light on her collarbone and cheekbones.", "color_palette": [ "#3D271D", "#5A382C", "#7A5A4E" ] }, { "type": "obj", "bbox": [ 100, 50, 670, 480 ], "desc": "A large, fan-shaped seashell positioned over the woman's left eye area. The shell is pale cream/beige, showing intricate, radiating ridges and a natural, organic texture. It is positioned slightly angled towards the viewer.", "color_palette": [ "#D4C19A", "#A08D6B", "#E0E0E0" ] }, { "type": "obj", "bbox": [ 150, 350, 670, 920 ], "desc": "A second, overlapping fan-shaped seashell positioned over the woman's right eye area. This shell is slightly larger and more centrally placed than the first, exhibiting similar pale, creamy tones and detailed radial ribbing.", "color_palette": [ "#D4C19A", "#A08D6B", "#B0A080" ] } ] } }
FLUX Power LoRA + ControlNet Pose + Face Detailer (Simple)
FLUX Power LoRA + ControlNet + Face Detailer (Simple)A clean and beginner-friendly FLUX workflow focused on realistic character generation.After testing numerous community workflows, I created this version with one goal in mind: keeping things simple while maintaining high-quality results.This workflow combines the tools I use most often for character photography and LoRA showcase generation:FLUX DevPower LoRA LoaderFlux ControlNetFace DetailerVRAM CleanupThe workflow is designed to be easy to understand, easy to modify, and practical for everyday use without unnecessary complexity.Ideal ForCharacter LoRAsPortrait PhotographyLifestyle ImagesFashion PhotographySocial Media ContentShowcase ImagesNotesA Face Detailer node is included and highly recommended for medium-distance and full-body generations. It helps maintain facial consistency and preserves smaller details that can become less defined at greater distances.This is the workflow used for many of the images featured on my IdentityLabs profile.Feel free to customize it and make it your own.
txt2img Prompt Assist Randomizer
Just like when you're looking for a recipe and you have to read through a 5 paragraph story about someone tasting some dish in another country and and how it reminded them of home, im going to put you guys through the same BS so you know why i made this nightmare prompt assistant. the last week ive been working on a new lora for illustrious and when i was going through it i found out if you shove abunch of wildcard style prompting into a text encode it seemed to work, i got multiple poses, camera angles, and as well as the thing i was training the lora on (vist the profile later or follow for updates). Well i thought why dont i make my own little prompt assistant tool that can help other people train loras as well? originally i was going to gate keep this to myself but after a friend asked if they could use my workflow as a reference for another workflow they were working on i thought well damn if he wants to use this then maybe other people would too. so here you guys are! the fruits of my madness using my original EZtxt2img workflow with a better upscaler than prior workflows. if you made it this far and those who havent checked out my other workflows here is the sales pitch for this one.ARE YOU TIRED OF WRITING THE SAME PROMPTS OVER AND OVER?INTRODUCING THE WILDCARD SELECTOR WORKFLOW — THE ULTIMATE PROMPT RANDOMIZER FOR COMFYUI!Featuring over 60+ INDIVIDUALLY TOGGLEABLE NODES across 17 CATEGORY GROUPS, this workflow puts TOTAL CONTROL at your fingertips!BUT WAIT, THERE'S MORE!EYES — 5 dedicated randomizers for color, shape, pupil shape, pupil color, and sclera! Want heterochromia with slit pupils and black sclera? FLIP A SWITCH!FACE — 5 randomizers covering face shape, details, expression, gaze direction, and makeup! NEVER GET SAMEFACE AGAIN!HAIR — 5 randomizers for color, length, style, bangs, and accessories! OVER 500 POSSIBLE COMBINATIONS!BODY — Type, skin, and detail controls! FROM PETITE TO MUSCULAR, WE GOT IT ALL!13 CLOTHING STYLES — Fantasy! Sci-Fi! Techwear! Gothic! Victorian! Cosplay! Office! Lingerie! Girlfriend! Vintage Housewife! AND MORE! Each one INDIVIDUALLY TOGGLEABLE!11 KEMONOMIMI SPECIES — Cat! Dog! Wolf! Fox! Rabbit! Deer! Horse! Dragon! MIX AND MATCH for chimera combos!7 OTHER SPECIES — Elf! Human! Succubus! Fairy! Ghost! Slime Girl! Goblin! Because why not!DUAL ENVIRONMENT MODES — Simple backgrounds for TRAINING DATASETS or detailed backgrounds for SHOWCASE GENERATION! Switch between them INSTANTLY!BODY VISIBILITY CONTROLS — Coverage level, anatomy emphasis, and exposure area toggles for building CLEAN TRAINING DATASETS! Get those attachment points and transition zones your LoRA ACTUALLY NEEDS!POSE & CAMERA — Pose, camera angle, and composition randomizers! Every gen a new angle!5 POSITIVE PROMPT BOOSTERS — Quality, color palette, material finish, mood, and art style!5 NEGATIVE PROMPT TEMPLATES — Quality cleanup, style control, anti-chimera, kemonomimi cleanup, and body cleanup! ALL TOGGLEABLE!POWERED BY IMPACT PACK'S WILDCARDPROCESSOR — ACTUAL randomization, not just vibes!COMPATIBLE WITH SDXL / ILLUSTRIOUS CHECKPOINTS!PERFECT FOR:LoRA dataset generationStyle explorationBatch variety generationPeople who are too lazy to write promptsOVER 10,000+ POSSIBLE PROMPT COMBINATIONS FROM A SINGLE WORKFLOW!ORDER NOW AND WE'LL THROW IN A FREE SET OF NEGATIVE PROMPTS ABSOLUTELY FREE!results may vary, not responsible for cursed generations, extra fingers sold separatelymay require additional LoRAs for optimal resultscreator is not liable for any unholy chimera abominations generated with the kemonomimi mixerthe "girlfriend cozy" preset will not get you an actual girlfriendside effects may include: prompt addiction, uncontrollable batch generation, hoarding 500GB of anime girls on your hard drive, and explaining to your power company why your electricity bill tripledsuccubus species toggle has been known to cause users to forget they were building a training datasetvintage housewife preset does not include cooking skillsbody visibility section is for SCIENCE and TRAINING PURPOSES ONLY wink winknot responsible for any GPUs harmed in the making of this workflowif your generations look cursed for more than 4 hours please consult a different checkpointcompatible with most SDXL/Illustrious checkpoints, your mom's laptop is NOT a supported platformno waifus were harmed in the development of this workflowby downloading this workflow you agree that cat ears improve everything
Easy Anima - Workflow for ComfyUI
Easy Anima Workflow v0.1 - (See installation requirements)This ComfyUI workflow is designed for Anima models. It features an all-in-one solution, with txt2img > hires fix > face detailer. The primary goal of this workflow is to provide an intuitive, easy-to-use UI that mirrors A1111 / Invoke, while remaining flexible for advanced use cases. The final image will include embedded metadata to make uploading to Civitai easier.Positive prompts now support wildcards and dynamic tags!Wildcards: Reference files from your ComfyUI custom nodes directory by enclosing the filename in double underscores (e.g., __filename__).Dynamic Tags: Create instant random variations directly in your prompt using curly brackets separated by vertical bars, like {blue|red} ball or {sitting|standing}.Wildcard preview: Use the 'Preview Wildcard' node to view the final prompt generated by your wildcards and dynamic tags.Installation RequirementsThis workflow requires the following model types:Anima Diffusion Model: ComfyUI/models/diffusion_modelsText Encoder - qwen_3_6b_base.safetensors: ComfyUI/models/text_encodersVAE - qwen_image_vae.safetensors: ComfyUI/models/vaeUpscale Model eg. remacri: ComfyUI/models/upscale_modelsThis workflow also requires these node packs in order to function, these can be easily installed via the built-in Custom Nodes Manager:
Ideogram 4 (LOW VRAM)
UPDATE COMFYUI TO THE LATEST UPDATE!Ideogram 4 is Ideogram's first open weight text-to-image model. It is a state-of-the-art foundation model trained from scratch — not a fine-tune of any existing model. It introduces a new structured JSON prompting interface, with best-in-class multilingual text rendering, deep language understanding, explicit bounding-box layout and color-palette controls, and native 2k resolution images. The easiest way to try the model is online at ideogram.ai.Diffusion Model (nvfp4) - REQUIRED!https://huggingface.co/Comfy-Org/Ideogram-4/blob/main/diffusion_models/ideogram4_nvfp4_mixed.safetensorsUnconditional Diffusion Model (nvfp4) - REQUIRED!https://huggingface.co/Comfy-Org/Ideogram-4/blob/main/diffusion_models/ideogram4_unconditional_nvfp4_mixed.safetensorsText Encoder (fp8)https://huggingface.co/Comfy-Org/Ideogram-4/blob/main/text_encoders/qwen3vl_8b_fp8_scaled.safetensorsVAE https://huggingface.co/black-forest-labs/FLUX.2-small-decoder/blob/main/full_encoder_small_decoder.safetensors requires both diffusion models. youll understand why when you see the workflow deconstructed. ive set this workflow up as i dont like the subgraph workflows. takes away from the joy of comfy imo <3
Eazy Regional Prompter - Illustrious Workflow for ComfyUI
Easy Regional v0.6 - (Please read the Prompt Guide & installation requirements)This ComfyUI workflow is designed for SDXL/Illustrious models, with built-in support for multi-character image generation. It features an all-in-one solution, with txt2img > hires fix > face detailer. The primary goal of this workflow is to provide an intuitive, easy-to-use UI that mirrors A1111 / Invoke, while remaining flexible for advanced use cases. The final image will include embedded metadata to make uploading to Civitai easier.Regional LoRA Support!Regional LoRAs are now supported. To add a LoRA to a region, type <lora:LORA_NAME:STRENGTH> [TRIGGER_WORD] into the region you wish the LoRA to apply to eg: (works best with characters)<lora:lauma_genshin_impact_ilxl_goofy:1.0> lauma \(genshin impact\)Prompt GuideCommon Prompt: Tags shared between regions such as, quality and background tags. Use this to define the amount of people and their gender eg. 2girls or 1boy, 1girl etc.masterpiece, best quality, absurdres, outdoors, park, bench, sunny, sunrays, 2girls, front view, straight onRegion 1: First character and/or specific details to this region (start this prompt with the gender of the character male or female NOT 1girl or 1boy)female, hatsune miku, aqua eyes, long hair, twin tails, hair orniment, white shirt, collard shirt, bare shoulders, black sleeves, pleated miniskirt, black thighhighs, sittingRegion 2: Second character and/or specific details to this region (start this prompt with the gender of the character)female, frieren, green eyes, pointy ears, twin tails, red earrings, capelet, striped top, white skirt, cuddlingNegative prompt: Standard negative prompt tags, nothing fancy going on herelowres, worst quality, bad quality, watermark, signatureSuggested Resolutions:1024 x 1024896 x 1152832 x 12161152 x 8961216 x 832Installation RequirementsIf the input fields on the nodes are in the incorrect place after installing the custom nodes, please redownload the workflow and the connections should be correct.This workflow requires the following model types:Base model: ComfyUI/models/checkpointsVAE eg. sdxl-vae-fp16-fix: ComfyUI/models/vaeUpscale Model eg. remacri: ComfyUI/models/upscale_modelsThis workflow also requires these node packs in order to function, these can be easily installed via the built-in Custom Nodes Manager:
![[NEW] ideogram 4 in Workflows collection](https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/8dc0a4eb-20a2-42e8-b82b-be2a7f58c3d6/original=true/132716249.jpeg)
[NEW] ideogram 4 in Workflows collection
RedCraft & DarkBeast workflows collection[NEW] ideogram 4 06/04/2026Ideogram 4 is Ideogram's first open-source text-to-image model. It is a state-of-the-art foundation model trained from scratch — not a fine-tune of any existing model.https://github.com/ideogram-oss/ideogram4https://github.com/Comfy-Org/ComfyUIDark Beast KLEIN 9b 🟦 V2.0 BFS 03/03/2026DBK v2 BFS最佳换脸工作流，配套模型：https://civitai.com/models/2242173?modelVersionId=2740209Dark Beast KLEIN 9b BFS 🟦 V2.0 LoRA Editionhttps://civitai.com/models/964312/redcraft-dark-beast-zandklein-exported-lora-editionThis is the next-level face-swap specialized evolution of the Dark Beast lineage, built on the lightning-fast FLUX.2 Klein 9B accelerated model from Black Forest Labs.Engineered with targeted optimizations for face swapping practices, it integrates BFS (Best Face Swap) technology to completely eliminate the rigid, unnatural look that plagued earlier face replacements — delivering seamless, lifelike integrations with preserved identity, expression, and lighting.It also fully fixes the portrait reference issue from the previous DB BlitZ versionsSpecial thanks to the scheme provider: https://github.com/alisson-anjos for the powerful BFS foundation that powers this breakthrough.🟦The author's In-site link: https://civitai.com/user/NRDXImportant notes:This version is exclusively designed around the Klein 9B accelerated edition — no base model exists.Usage is identical to Black Forest Labs' official FLUX.2 Klein 9B accelerated release: ultra-low steps (e.g., 4-5), CFG=1 fixed, blazing inference speed on consumer hardware.In one sentence: Dark Beast's ferocious soul meets BFS (Best Face Swap) technology — more natural, and truly unstoppable! 🟦for more infomation about BFS (Best Face Swap) :https://huggingface.co/AlissonerdxAlternatively, it can be directly applied to the entire Klein 9b/Qwen Edit base and Fine-tune models, through LoRA Adapter parameter injection.面部交换测试的源-人像来自Civitai用户图像和Moody Mix肖像风格。Source faces for the face-swapping test originated from Civitai user images and Moody Mix portraits styles.The gods have returned! KOLORS base model/Hyper 8steps/SDXL refinement/IPA Plus众神归位！快手底模/字节加速/SDXL精修/IPA风格Kolors DiT大模型COMFYUI工作流-AiARTiSTKolors DiT（GLM）ComfyUI 放大精修工作流7/8日 发布Kolors-DiT开源模型+ACG6XL放大精修-文生图工作流7/9日 发布Kolors-DiT开源模型+ACG6XL放大精修-垫图生图工作流7/10日 发布Kolors-DiT开源模型-单文件模型版+LoRA加速器+ACG6XL放大精修工作流7/11日 支持IPA-Plus节点，单一样本垫图风格导入，模型和组件包请在网盘下载原生采样器支持节点作者MinusZoneAI，非常感谢！https://github.com/MinusZoneAI/ComfyUI-Kolors-MZ单文件模型及存放路径已经上传至网盘，模型路径根据网盘路径存放SDXL-Hyper-8steps 蒸馏加速器LoRA\ACG6Hyper SDXL精修模型 同上增加 IPAdapter 模型及ComfyUI_IPAdapter_plus 组件包 存放路径 同上IPAdapter 开源模型：https://hf-mirror.com/h94/IP-AdapterComfyUI_IPAdapter_plus 项目：https://github.com/cubiq/ComfyUI_IPAdapter_plus项目开源地址：https://huggingface.co/Kwai-Kolors/KolorsComfyUI 加载器封装组件项目地址：https://github.com/kijai/ComfyUI-KwaiKolorsWrapperKolors：用于逼真文本到图像合成的扩散模型的有效训练Kolors是由快手Kolors团队开发的一种基于潜在扩散的大规模文本到图像生成模型。经过数十亿对文本图像的训练，Kolors在视觉质量、复杂的语义准确性以及中文和英文字符的文本渲染方面比开源和专有模型都表现出显著优势。此外，Kolors同时支持中文和英文输入，在理解和生成中文特定内容方面表现出色。开源Kolors，与开源社区合作，促进大型文本到图像模型的开发。该项目的代码是在Apache-2.0许可证下开源的。我们真诚地敦促所有开发者和用户严格遵守开源许可证，避免将开源模型、代码及其衍生物用于任何可能危害国家和社会的目的，或用于任何未经安全评估和注册的服务。请注意，尽管我们在训练过程中尽了最大努力确保数据的合规性、准确性和安全性，但由于生成内容的多样性和可组合性以及影响模型的概率随机性，我们无法保证输出内容的准确性和安全性，并且模型容易产生误导。对于因使用开源模型和代码而导致模型被误导、滥用、误用或不当使用而产生的任何数据安全问题、舆论风险或风险和责任，本项目不承担任何法律责任。----------------------------------------------------------------------模型用途声明：1. 您不得将此模型及其衍生版本（如融合模型版本）托管于计划赚取收入或捐赠的网站/应用程序。2. 您不得直接售卖此模型及其衍生版本（如融合模型版本），除非您对此模型进行了足够程度的人工修改，使其在法律意义上可以被完全判定为您的个人作品。如果您违反本条，所造成的一切法律后果由您个人承担，请恕本人概不负责。3. 您不能使用该模型故意制作或共享非法或有害的内容传播和输出，请您遵守公序良德，将此模型用于积极正面的用途。
Illustrious/ Pony/ SDXL Pro Grade Workflow (Low or High VRAM)
Note: I spend a lot of time on these to make sure they are top notch. If you have ANY issues, I'm very responsive. hit me up and I'll resolve them for you.This is an advanced workflow designed for people familar with Comfyui and who want pro grade results. I encourage you to learn it, but if it is overwhelming, the simple version can be found HEREA complete user and troubleshooting guide inclusing a list of common error messages can be found here https://civitai.com/articles/24678/how-to-use-my-workflows-a-comprehensive-breakdown也有中文说明Instagram: https://www.instagram.com/synth.studio.models/Buy me a☕ https://ko-fi.com/lonecatoneThis represents hundreds of hours of work. If you enjoy it, please 👍like, 💬 comment , and feel free to ⚡tip 😉V15.0Because it is not in my nature to leave things alone....Gutted the stock face detailer nodes and replaced them with a SEGS suite for infinately better resultsNote: Yes, I will be going through all my workflows and replacing them, including teh NSFW onesControlnet Update.Added local bypass nodes so ou don't have to zoom and scrollAdded a quality modifier prompt area that follows after Qwen so that they stay preserved.Major update to notes, especially for detailersV12.1Added an Inpaint areaModified controlnet so it doesn't fault out if a mask isn't loaded without resetting teh switchRemoved the sentence remover (it sucked)added "banned tag remover" at the metadata saver so you can still process normallyV11.1.2Updated 📝Prompt AssistUpdated ⚙️ main areaAdded back Qwen VL prompt enhancer (now that it's fixed)Updated 🔎 detailersUpdated 💾 Save area so that you can embed workflows as well as add a simple date to the folders so you aren't endlessly looking for them.Added an inline ✂️ crop tool in the 🎨Post Production SuiteVer 10Improved regional prompt suitesAdded IP Adapters for Face, style, and composition for Facial and pose consistencyImproved detailer suitereworked settings for easier useAdded CivitAI sentence ✂️Ver 9.0Qwen nodes keep getting mbroken due to updates. I removed them in V9Removed outdated sectionsAdded a 2nd KSampler & model option for refinementV 8.1 is included in the folderVER 8Created a really cool regional prompter.Works with controlnetUpgraded detailers to accomodate for it so you can detail each face seperatelyThis is an all in one workflow:Controlnet: background remove, canny, openpose, depth, canny/depthI2I prompt assistQwenV2 Prompt enhancer.Florence and Qwen prompt assistStyle selectorDual Model Loader: Better controlSage Attention: Speeds up productionUltimate Upscaler for prescaling and hi res fixDetailing Suite for face, hands, eyes, and expressionsmulti face detailerSeed VR2 Upscaler to get 4k on low VRAMMassive Post Production SuiteSmart Noise scrubberFull tutorial available.也有中文说明
Text2Img Workflow with Detailer Arrays
Hello Everyone!Have you ever created an image you like and would have kept, but and a face, or hand just came out wrong? You need a workflow that can take control address that.Ever make an image that had multiple characters, but when you tried to assign them the correct eye color or expression, the checkpoint got confused, and you had to play generation roulette? You need a workflow that lets you decide whose face has just came out like what.That is what this workflow, used properly, will allow you to do. This workflow is my daily driver T2I workflow for checkpoints based in SDXL, Illustrious and Pony. It is based upon my Img2Img SDXL Workflow + META, which I was only able to create thanks to bits taken from other workflows, particularly those of Legendaer and Yukichan_, and advice from Lonecatone23. Over several revisions, I have made a number of refinements to the workflow while at the same time striving to keep it simple so that even a beginner can take hold of this workflow and start generating.Main Features:✦ Text to Img Generation - That's what we're here for, text to image.Include Metadata / Embed Workflow Option. Stable 1 megapixel generation, or dare to increase it with Size Boost.✦ Metadata saving included — CivitAI ready. You can also embed the entire workflow into your images, by default this is turned off.✦ Upscaler with Color Matching - this is the feature that makes images go from good to great. Or use HiresFix for a quick increase in resolution✦ Quality Tags Presets Switch - instead of typing Masterpiece, best quality, etc. etc.✦ Two Segs Detailer Arrays - two SEGS pipelines (by default, hands and faces) that you can individually prompt or apply one prompt to all. Sophisticated tool created to handle individual details - your backstop for when the image has to be perfect.✦ Parallel development with I2I workflow - if you learn this one my Img2Img works essentially the same way.✦ CFG Controls - need more control, more CFG? It's handled automatically, crank it up to 10.✦ LoRA Manager — Search your LoRA database with style, I love this node. Dump it if you prefer something else.✦ Simple and reliable — Enter your prompt, hit run, let the segs previews populate, freeze the gen seed, and fill in prompts and run it again. That's it.New with 5.0 SESkipped 4.0, just becauseSeed JumpStyle Preset switchingAdded a toggle and Subgraph for exceeding native SDXL resolution on initial genFixed Typos for name of Face Detailer LoRA blocker nodesDoes not include Quality Tags Fast Switching, uses native concatenate nodes5.0.1 Changes:Changed Positive Text Box to Mira, which was already being used in this workflowChanged Wildcard ProcessorSeed controls Wildcard selection (Freezing seed freezes your wildcards too now)Added Final Prompt PreviewAdded a toggle and Subgraph for exceeding native SDXL resolution on initial genSlight rearrangement of Control Group, hopefully optimalNew with 3.0:With 3.0, the layout has changed and metadata flows have changed. The checkpoint loader is now the checkpoint selector, which should provide some convenience and added stability. The LoRA blocker no longer requires fiddling with the spaghetti string to toggle it, there is now a toggle switch. Sliders have been implemented throughout the Input center, including controls for the Upscaler.New with 2.2:Added toggles for including the workflow in the image's metadata.Added a means by which you can bypass the upscaler and still send the image (directly from phase 1 gen/hires fix) to the detailer, rather than being forced to use upscaler in order to access the detailer.Color Matching directly following Upscaler - I have found that some models have noticeable drift in color tone and this corrects that, works beautifully.New with 2.1:Detailer moved to the back of the order, after upscale, to ensure that full control over expressions remains with you, the artist. I'm very happy with this workflow in its current form, although there might be new versions or changes down the line.New with 2.0:Raise CFG without crushing the imageUpscaler with a third save nodeSomehow resists LoRA bleed, whether it's the scheduler / sampler combo or what I'd love to know. It's not perfect though!Preview KSampler - a game changer for skipping unsatisfactory seeds. Use it!You will need to download an upscaler model if you don't have one already.How this Workflow Came to BeI was using one of these massive workflows with all the bells and whistles and I ran into a snag. A LoRA was confounding the hand detailer and the hands were all coming out like macaroni alfredo. So, I turned off that LoRA. I was also running into a common problem: when two characters are in the frame, they end up with the same eye or hair color. The tags were blending across character BREAKs which is ultra common, and detailers that handle all bboxs in order cannot be instructed on each bbox individually. That's something that my I2I workflow was designed to do, and the mega huge T2I workflow with all its heft didn't have detailer separation as a feature.I don't think I could add to such a complex workflow without tripping up and it end up taking 2 hours. I thought if I'm going to modify a workflow it might as well be my own. It would keep things simple with only nodes I know I have, I'd finish in under 30 minutes, and then I would have complete control over faces.Saving the metadata is important too, however somehow in converting things and removing things that get concatenated (such as the natural language prompt), the metadata portion got a little scrambulated, and don't worry I fixed it -- but 30 minutes turned into a several hour affair. Under nine hours though, I'm pretty sure. The latter part was mostly testing and tweaking. I ended up making some changes to the detailer modules so that they don't spam the image feed, and upgraded that module to V1.1.During testing, I started with one figure, then two, and I soon discovered that this workflow is absolutely a beast at ensuring your faces all look great. Whether you have one face in the image or five, the detailer can make each one pop with high aesthetic quality and unique expressions, and the SEGS previewer keeps you in control.The hand detailer gives you per-segs control over hands although sometimes bad hands are going to happen, particularly when there are many in one image. Fingers in AI is always a little trickier, but the workflow allows you to add a hand detailer LoRA directly to the detailer, upping your chances of success dramatically. Do it. At the same time, that LoRA will be blocking other LoRAs that could create havoc on delicate fingers. I haven't seen this approach elsewhere, curious whether it holds up in your experience. Please let me know in the comments what you think about my LoRA blocker, if you have any aspects you think ought to be changed, bug fixes, etc. This is just version 1, it's bound to evolve.RequirementsYou will need a face bbox detector - like this oneYou will needs a hands bbox detector - like this oneYou might decide to add or replace a bbox detector for face or hands with one for eyes, or add another bbox array. For eyes, try this oneIn ComfyUI you may need to turn some safety features off to use pickletensors. Consult AI if you run into problems.Custom Nodes Used:rgthree-comfyComfyUI Impact PackComfyUI Impact SubpackComfyUI-Easy-UseComfyUI-Lora-ManagerComfyUI Image SaverComfyUI_essentialsComfyUI-KJNodescg use everywhere Anything EverywhereDynamic ThresholdingComfyui_MiraSkimmed_cfgefficiency-nodes-comfyuiComfyroll StudioComfyMath
Anima All in One workflow
ANIMA all in one workflow.V5.0 Releasei2i now works properly. However, please be careful when adjusting the image resolution.Inpainting is also fully functional. Please refer to the post for more detailed instructions.The Spectrum acceleration method has been replaced with a more stability-focused algorithm.Modulation Guidance has been added. Please enter your “meta tags” in the “positive 2” prompt field. This custom node is designed to help those meta tags work properly.V5.1 Minor UpdateChanged the position and default settings of TorchCompileModelAdvanced.The RuntimeError: Fault failed: 2 error should no longer occur.Added an option to upscale Highres latent images after converting them to images.Enabling the latent를 이미지로 변환 option can help prevent rough or broken-looking results in certain cases.More detailsNAIA2.0NAIA를 설치하지 않은 경우, Fast Groups Bypasser (rgthree)에서 "NAIA 사용"을 비활설화 하세요.4.5 이후는 스위치 토글을 사용합니다.If you have not installed "NAIA", disable "NAIA 사용"NAIA: https://github.com/DNT-LAB/NAIA2.04.5 ~rgthree 를 통해 그룹 단위로 bypass하는 대신, comfyUI의 스위치 노드를 사용해서 컨트롤 합니다. on off 토글을 통해 사용하지 않는 노드는 스킵됩니다.rgthree node has been changed to a comfy switch node. Unnecessary functions can now be turned on and off via toggle, and nodes that are not running will not cause compatibility issues.~3.0"4b. SeedVR" 와 "4a. HighRez" 그룹은 둘 중 하나만 활성화 하세요."4a. HighRez" 사용 시 "전신 디테일러"는 스킵하세요.Activate only one of the "4b. SeedVR" and "4a. HighRez" groups.Skip "전신 디테일러(Full Body Detailer)" when using "4a. HighRez".custom nodesKSampler (Spectrum + Mod Guidance Advanced)https://github.com/sorryhyun/ComfyUI-Spectrum-KSamplerDCWhttps://github.com/namemechan/ComfyUI-DCWSpectrumhttps://github.com/ruwwww/ComfyUI-Spectrum-sdxlComfyUI-Anima-LLLithttps://github.com/kohya-ss/ComfyUI-Anima-LLLiteNaia-bridgehttps://github.com/DNT-LAB/comfyui-naia-bridgeGuide(Korean)V1V2V3V4V5
LTX 2.3 Image and Text Video 10S Similarity Preservation Workflow
Watch the full video first if you want to understand how this LTX 2.3 image-and-text video workflow works in practice. The video shows how one reference image can be combined with text control, how the 10-second similarity system keeps the subject stable, and how to run the full workflow online without rebuilding a complex local ComfyUI environment.This ComfyUI workflow is designed for LTX 2.3 image-reference video generation with text-controlled motion and 10-second likeness preservation. Its main purpose is to let creators start from one image, describe the desired action or camera movement with text, and generate a controlled video while keeping the original subject, composition, and visual identity more stable across the clip.The workflow is built around the LTX 2.3 distilled 1.1 generation route. It uses the LTX 2.3 video checkpoint, Gemma3 fp8 text encoder, LTX Audio VAE, LTXVConditioning, LTXVImgToVideoConditionOnly, LTXVPreprocess, Image_Resize_longsize, LTX2_NAG, ManualSigmas, CFGGuider, SamplerCustomAdvanced, LTXVLatentUpsampler, LTXVConcatAVLatent, LTXVSeparateAVLatent, tiled decoding, and final video output. This makes the workflow more structured than a basic one-pass image-to-video graph.The image side provides the visual anchor. The reference image is resized, prepared through LTXVPreprocess, and injected into the generation process through LTXVImgToVideoConditionOnly. This helps the model preserve the character, object, scene, lighting, clothing, and composition from the original image. The text prompt then controls the motion direction, expression, camera movement, atmosphere, and cinematic behavior.The key update is the 10-second similarity preservation system. The workflow uses similarity and anchor-style guidance during the later stages, especially around the latent upscaling and HD refinement process. This helps reduce common image-to-video issues such as face drift, hairstyle changes, clothing inconsistency, subject deformation, background collapse, and unwanted identity changes. For creators making character videos, this is one of the most important improvements.The generation process is divided into three stages. The first stage builds the initial composition and motion base. The second stage performs latent-space upscaling while keeping stronger similarity control and weak anchor stability. The third stage applies final high-definition refinement with lighter similarity control, improving sharpness and detail while trying not to damage the established character identity.The workflow also includes LTX2_NAG and a universal negative prompt system. This helps suppress flicker, frame jitter, subtitles, watermarks, UI overlays, bad hands, broken mouth shapes, unstable motion, unwanted text, distorted audio artifacts, and sudden scene changes. Compared with ordinary image-to-video workflows, this version is better suited for publishable creator content because it combines reference image control, text-guided direction, similarity locking, staged sampling, and high-resolution refinement.This workflow is suitable for character animation, portrait-to-video, product motion shots, cinematic still animation, AI short clips, MV fragments, social media video, Bilibili demonstrations, YouTube showcases, RunningHub releases, and Civitai workflow publishing.Main features:LTX 2.3 image-and-text video workflowOne reference image + text motion control10-second similarity preservationLTX 2.3 distilled 1.1 checkpoint routeGemma3 fp8 text encoderLTX Audio VAE supportImage_Resize_longsize image preparationLTXVPreprocess reference preprocessingLTXVImgToVideoConditionOnly image guidanceLTX2_NAG universal negative guidanceThree-stage rendering structureLTXVLatentUpsampler high-resolution transitionAV latent concatenation and separationFinal HD video outputSuggested workflow:Prepare one clean reference image first. The subject should be clear, well-framed, and not blocked by complex foreground objects. Load the image into the workflow, then write a text prompt describing the motion, camera behavior, lighting, expression, atmosphere, and video style. Run the first stage first to check whether the image identity and motion direction are correct. If the character changes too much, keep the 10S similarity settings active and simplify the prompt. If the video is too static, make the motion instruction more explicit. After the base motion is stable, continue through latent upscaling and final HD refinement.⚙️ RunningHub WorkflowTry the workflow online right now — no installation required.👉 Workflow: https://www.runninghub.ai/ai-detail/2061688885712875521?inviteCode=rh-v1111If the results meet your expectations, you can later deploy it locally for customization.🎁 Fan Benefits: Register to get 1000 points + daily login 100 points — enjoy 4090 performance and 48 GB super power!📺 Bilibili Updates (Mainland China & Asia-Pacific)If you’re in the Asia-Pacific region, you can watch the video below to see the workflow demonstration and creative breakdown.📺 Bilibili Video: https://www.bilibili.com/video/BV1nVVr6QEd8/☕ Support Me on Ko-fiIf you find my content helpful and want to support future creations, you can buy me a coffee ☕.Every bit of support helps me keep creating — just like a spark that can ignite a blazing flame.👉 Ko-fi: https://ko-fi.com/aiksk💼 Business ContactFor collaboration or inquiries, please contact aiksk95 on WeChat.⚙️打开下方链接即可在线体验，无需安装。👉 工作流： https://www.runninghub.ai/ai-detail/2061688885712875521?inviteCode=rh-v1111如果觉得效果理想，你也可以在本地进行自定义部署。🎁 粉丝福利： 注册即送 1000 积分，每日登录 100 积分，畅玩 4090 体验 48 G 超级性能！📺 Bilibili 更新（中国大陆及南亚太地区）如果你在中国大陆或南亚太地区，可以通过下方视频查看该工作流的实测效果与构思讲解。📺 B站视频： https://www.bilibili.com/video/BV1nVVr6QEd8/我会在 夸克网盘 持续更新模型资源：👉 https://pan.quark.cn/s/20c6f6f8d87b这些资源主要面向本地用户，方便进行创作与学习。
Fabin LTXV 2.3 Simple workflow
Workflow for LTXV 2.3 v1.1 i2v and t2vupdate: 2026-05-22 v1.0AllInOne version include a workflow that you can use checkpoints AIO or diffusion models and you can use to I2V and T2V all in one workflow.the workflow also includes Random prompts and Load Img from Dir.update: 2026-06-03 v1.1I made some adjustments to the T2V section.
LTX 2.3 – Image/Text to Video – API Key Node Edition
Hello Community,Several users asked for my workflow, so I decided to share it with everyone. Maybe it will be useful for some of you as well.First Things First:The workflow is based on the original workflow available in ComfyUI → Templates → Video → Image to Video. I don't want to take credit for work that isn't mine. The original workflow structure comes from the ComfyUI team.What I Changed:I integrated the LTX API Node and removed the need for the heavy Gemma Text Encoder as well asthe Text Positive and Text Negative nodes. Since prompts can be entered directly into the API node, these additional nodes were no longer necessary. I also cleaned up the subgraph a bit to make it easier to understand and navigate (at least for me).Why I Made These Changes:The main reason was speed. By using the API node, the text encoding runs through the LTX server and is completed in just a few seconds. On my system this reduced the preparation time by roughly 10 minutes compared to my previous setup. For me, saving 10 minutes per generation is a significant improvement.Example Render Times:Measured on my system (see hardware section below) using 5-second clips:768 × 768 = 158.74 seconds1080 × 608 = 160.05 seconds1024 × 768 = 181.16 seconds1248 × 720 = 192.00 seconds1536 × 864 = 307.04 seconds1920 × 1080 = 459.06 secondsYour results may vary depending on hardware, settings, workflow configuration, and clip length.The workflow is also capable of generating 20-second clips at the above resolutions on my system.Hardware Used:AMD Ryzen 7 5700X64 GB DDR4 RAMNVIDIA RTX 4060 Ti 16 GBImage-to-Video and Text-to-Video:In the main view there is a switch node in the center of the workflow. Simply change it between True and False to switch between Image-to-Video (I2V) and Text-to-Video (T2V). No separate workflows are required.Important:Don't forget to enter your API key inside the subgraph. You can get a free API key here:https://docs.ltx.video/welcomeThen simply click "Get an API Key" (you have to sign up, but it's free).The required models are already listed on the left side of the workflow.Final Notes:This is not a completely new workflow. It is simply a practical modification of the original ComfyUItemplate that worked very well for me and significantly reduced my preparation time. Give it a try and let me know how it works on your system. Feedback, suggestions, and improvements are always welcome.
Wan 2.2 i2v Storyboard
ComfyUI Workflow (for testing)requires eclipse 3.5.36setup is nsfw sorry if that bother you xdthe workflow is a merge from @taek75799
【HiDream】IMG to IMG
✨ HiDream — Image to Image — Simple WorkflowA clean, all-in-one HiDream image-to-image workflow built entirely with the UmeAiRT Toolkit for ComfyUI.Only 8 nodes. No spaghetti wires. Just load your model, write your prompt, and hit generate.⚠️ IMPORTANT — Nodes 2.0 RequiredThis workflow is built for the Nodes 2.0 (Vue) interface of ComfyUI. If you don't enable it, the workflow may have display problems.How to activate Nodes 2.0:Open ComfyUIGo to Settings (⚙️ icon, bottom-left)Find "Use Nodes V2 (Vue)" and toggle it ONRefresh the pageLoad the workflowIf you prefer the classic interface, check out my Legacy version of this workflow instead (link).🎯 FeaturesImage-to-Image generationAutomatic download of models in auto versionBuilt-in SeedVR2 upscaler — high-quality tiled upscaling (toggleable on/off) Slower than a classic upscaler, but significantly better qualityFull metadata embedding — your images are saved with all generation parameters, ready for online publishing and remixing3 LoRA slots — with individual on/off toggles and strength control and you can connect as many other lora modules to each other for as many LoRA as you want.📦 Custom Node RequiredOnly one custom node to install:👉 ComfyUI-UmeAiRT-ToolkitInstall via ComfyUI Manager (search "UmeAiRT") or use the UmeAiRT Auto-Installer.The Toolkit packages everything internally — upscaler, face detailer, metadata saver. No other custom nodes needed.📂 Files you need (in manual version)24 gb Vram : base16 gb Vram: Q8_012 gb Vram: Q5_K_S<12 gb Vram: Q4_K_SFor base versionModel : hidream_i1_dev_fp8.safetensorsin ComfyUI\models\diffusion_modelsFor GGUF versionGGUF_Model : hidream-i1-dev-QX_K_S.ggufin ComfyUI\models\unetVAE : ae.safetensorsin ComfyUI\models\vaeCLIP : clip_l_hidream.safetensors, clip_g_hidream.safetensors, t5xxl_fp8_e4m3fn_scaled.safetensors and llama_3.1_8b_instruct_fp8_scaled.safetensorsin ComfyUI\models\clip
Eazy Illustrious - Workflow for ComfyUI
Easy Illustrious Workflow v0.4 - (See installation requirements)This ComfyUI workflow is designed for SDXL/Illustrious models. It features an all-in-one solution, with txt2img > hires fix > face detailer. The primary goal of this workflow is to provide an intuitive, easy-to-use UI that mirrors A1111 / Invoke, while remaining flexible for advanced use cases. The final image will include embedded metadata to make uploading to Civitai easier.Positive prompts now support wildcards and dynamic tags!Wildcards: Reference files from your ComfyUI custom nodes directory by enclosing the filename in double underscores (e.g., __filename__).Dynamic Tags: Create instant random variations directly in your prompt using curly brackets separated by vertical bars, like {blue|red} ball or {sitting|standing}.Wildcard preview: Use the 'Preview Wildcard' node to view the final prompt generated by your wildcards and dynamic tags.Installation RequirementsThis workflow requires the following model types:Base model: ComfyUI/models/checkpointsVAE eg. sdxl-vae-fp16-fix: ComfyUI/models/vaeUpscale Model eg. remacri: ComfyUI/models/upscale_modelsThis workflow also requires these node packs in order to function, these can be easily installed via the built-in Custom Nodes Manager:
LTX-2.3 Long Video Generation (Distilled GGUF) workflows
AcknowledgementsI have addressed all known bugs within this workflow (excluding those inherent to ComfyUI or specific custom nodes). As such, I am concluding regular updates for this project.I might still push occasional updates if the mood strikes me, but for now, consider this the final version. Thank you so much for the downloads and support. I hope this workflow helps your creative process - happy generating!OverviewA simple LTX-2.3 workflow. It uses the Distilled GGUF model for fast generation.Core FeaturesSingle / Extend Generation ModeYou can choose whether to generate the video once or extend it afterward.Three prompt input modesPrompt enhancement using OllamaNative LTX prompt enhancementPlain (no enhancement)If Ollama is not needed, you can disconnect it from the Ollama SubGraph node or simply delete the node.Optional FeaturesPreview Switch: Displays a preview during sampling.Audio-driven: Generates a video that matches an existing audio file.T2V Switch: Ignores the start image and generates the video using text-to-video.Full Mode: Generated using Steps 15 and CFG 3.0. This takes a very long time. While the camera work and motion may be slightly improved, the generation time is not practical.Double-Frame Mode: For use with intense motion. By rendering at twice the frame rate, facial distortion is less likely to occur.NoteIf you encounter the error, please update ComfyUI-KJNodes to the latest version.
Image to Image Video With Alpha Layer (WEBM format, wan2.2)
The Git Repo is here: https://github.com/therealkove-wq/img2imgVideoTransparency# img2img Transparent Video — ComfyUI WorkflowGenerates videos with a transparent background (WEBM + alpha channel) from a start and end frame using Wan 2.2 I2V with LightX2V LoRAs and rembg AI background removal.---## How it works1. You provide a start frame and an end frame (PNG images)2. The model generates the in-between frames3. rembg AI strips the background from every frame4. Output is a WEBM file with a real alpha channel, ready for compositing---## Required ModelsAll models are from [Comfy-Org/Wan_2.2_ComfyUI_Repackaged](https://huggingface.co/Comfy-Org/Wan_2.2_ComfyUI_Repackaged) on HuggingFace.| File | Destination folder ||------|--------------------|| wan2.2_i2v_high_noise_14B_fp8_scaled.safetensors | ComfyUI/models/diffusion_models/ || wan2.2_i2v_low_noise_14B_fp8_scaled.safetensors | ComfyUI/models/diffusion_models/ || wan2.2_i2v_lightx2v_4steps_lora_v1_high_noise.safetensors | ComfyUI/models/loras/wan/ || wan2.2_i2v_lightx2v_4steps_lora_v1_low_noise.safetensors | ComfyUI/models/loras/wan/ || umt5_xxl_fp8_e4m3fn_scaled.safetensors | ComfyUI/models/text_encoders/ || wan_2.1_vae.safetensors | ComfyUI/models/vae/ |> The workflow will show download buttons for missing models directly in ComfyUI.---## Custom Node SetupTwo custom node packages are required.### 1. wan_alpha_nodes (this repo)Provides the SaveWebmWithAlpha node used to export the final video.Copy the two files from this repo into ComfyUI:```ComfyUI/custom_nodes/wan_alpha_nodes/├── wan_alpha_nodes.py└── init.py```### 2. ComfyUI-rembgProvides the RembgBackgroundRemover node used for AI background removal. Install it via ComfyUI Manager or clone it into ComfyUI/custom_nodes/.---## Using the Workflow1. Open ComfyUI and load kove_img_to_img_transparent.json2. In the Start Frame node, upload your starting image3. In the End Frame node, upload your ending image4. Edit the Positive Prompt (see Prompting section below)5. In the WAN I2V Conditioning node, set width, height, and length (frame count)6. In the Save node, set your output filename and frame rate7. Click QueueThe output WEBM file will appear in ComfyUI/output/.---## Key Parameters| Parameter | Node | Notes ||-----------|------|-------|| Width / Height | WAN I2V Conditioning | Resolution of the output video. Default: 1024×1024 || Length | WAN I2V Conditioning | Number of frames. 61 frames @ 30 FPS ≈ 2 seconds || Filename | Save | Output file name. Existing files with the same name are overwritten without warning. || Frame Rate | Save | Playback FPS of the output WEBM || Codec | Save | VP8 (faster) or VP9 (better compression) || Quality | Save | 0–100. Default 20 is a good starting point |---## PromptingAlways include this phrase in the positive prompt:> "The character is isolated against a transparent background."Without it, rembg has less context and background removal quality drops.The negative prompt is pre-filled with blurry, distorted, low quality, static, no motion — leave it as-is unless you have a specific reason to change it.### Example promptsIdle character animation```The character is isolated against a transparent background.The lighting is constant and even throughout the sequence.The character breathes gently and sways slightly from side to side.Hair and clothing move subtly with the sway.The character does not speak. Slow movements. Idle animation.```Floating object```The character is isolated against a transparent background.A glowing orb floats gently up and down. Soft pulsing light. Smooth looping motion.```Abstract effect```The character is isolated against a transparent background.Colorful particles swirl and drift slowly. Ethereal. Cinematic quality.```---## TroubleshootingNodes missing after loading the workflow- Confirm both custom node packages are installed and ComfyUI has been restarted- Check the ComfyUI console for import errorsBackground not fully removed- Make sure the transparent background phrase is in your positive prompt- Try a different rembg model in the RembgBackgroundRemover node (e.g. isnet-anime for illustrated characters)CUDA out of memory- Reduce width/height or frame count- The two diffusion models are large (14B fp8); 16GB+ VRAM recommendedOutput file is overwritten unexpectedly- Change the filename in the Save node before each runWEBM won't play in browser/editor- Switch codec to VP9 in the Save node for broader compatibility
Anima Style Explorer & Prompt Workflow | Style Blending & Automated Artist Prompting
New attachment updated! It contains the new prompt templates for femboy and otokonoko. By using vocabulary isolation, it effectively prevents limb drift and helps the model better understand their body structures.🚀 [Major Update v2.5] ComfyUI Anima Style Explorer Prompt: The Palette & Automation Revolution!🚨 CRITICAL UPDATE NOTICE: PLEASE READ BEFORE RUNNING!IMPORTANT: This update introduces a deeply integrated Frontend JavaScript architecture. After updating via Git, you MUST restart your ComfyUI backend console AND hard-refresh your browser (Press Ctrl + F5) to clear old web cache. If you do not do this, the new interactive dropdown menus and buttons will not function correctly!🔥 New Core Node: [Anima 2B Dynamic Group Switcher]Say Goodbye to Manual Bypass Stress!Tired of manually clicking dozens of rgthree group toggles or managing messy text switches just to change your rendering style? We built the ultimate automation solution. The new Anima 2B Dynamic Group Switcher links directly to your canvas layout to handle everything seamlessly.🎛️ Dynamic Slot Scaling (➕/➖ Buttons): Click the native on-node buttons to dynamically scale your workflow from 1 to 30 custom text/style channels instantly.🧠 Automatic Group Name Detection: The moment you connect a slot to a style group on your canvas, the node dynamically reads the group's title and re-labels the input port natively (e.g., text_1 [femboy], text_2 [90s Anime]).⚡ Automatic Bypass Matrix Control: When you select an option from the native active_style dropdown menu, the chosen Group automatically activates (Normal mode), while all other connected unselected groups are instantly forced into Bypass mode (turned gray).🛡️ Zero-Crash Backend (VALIDATE_INPUTS Fix): Features a custom backend bypass validator to completely eliminate native ComfyUI Value not in list runtime errors when switching styles mid-generation.🎨 3 New Specially-Tuned Masterpiece Palette TemplatesWe have integrated three incredibly powerful, JoyCaption-optimized aesthetic templates into the core system to instantly elevate your generation textures:1. ❄️ Muted / Morandi / Desaturated Palette (冷调色 / 高级灰)Designed for an elegant, intellectual, and quiet gallery-grade aesthetic.Visual Formula: It strips away harsh or raw digital neon colors, replacing them with highly sophisticated, low-saturation tones (dusty rose, sage green, muted grayish blue) laid over soft grey undertones.Lighting: Simulates a beautifully diffused overcast lighting with minimal contrast and zero harsh shadows, adding deep atmospheric weight to character art.2. 🍂 Retro Vintage / 90s Anime Palette (暖调色 / 90年代旧画风)Recreates the golden era of hand-drawn cinematic animation.Visual Formula: It forces the AI rendering engine to ditch flat modern digital gradients in favor of an authentic 1990s cel-shaded aesthetic. It wraps the entire scene in rich, warm sepia undertones and beautifully faded nostalgia colors.Textures: Seamlessly injects optical vintage film grain and subtle chromatic aberration (lens edge color-bleeding) to make the image look like a classic animation cell.3. 🖤 Color Split / Selective Color Palette (漫画调色 / 局部色彩)Delivers extreme cinematic focus and high-impact visual drama, perfect for stylized manga covers or dark art.Visual Formula: It actively locks the entire environment, background, skin, and primary attire into a rich, high-contrast monochrome grayscale (deep ink blacks and crisp stark whites).The Contrast: It automatically isolates the single most striking visual focus item (such as vivid red lips, glowing gold jewelry, or magical eyes) and splashes it with piercing, high-saturation color against the silent, colorless world.🧩 The Expanded 4-Node EcosystemYour suite of tools has now evolved into a complete industrial-grade production pipeline:Anima 2B Dynamic Group Switcher (NEW!) —— Automated workflow traffic controller. Dynamically activates chosen style canvas groups and silences the rest.Artist Pre-Config Outline —— Handles macro-category wrapping and multi-artist nested weight blending.Anima 2B Prompt Template 1 —— Core parallel multi-weight artist channel generator.Anima 2B Prompt Template 2 —— High-end modifiers, time eras, structural evaluation, and prompt quality scoring.🛠️ How to Download & UpdateMethod A (Recommended): Direct ZIP Download from GitHubVisit the GitHub repository: ComfyUI-Anima-Style-Explorer-PromptClick the green Code button -> Select Download ZIP.Extract and overwrite the contents into your ComfyUI/custom_nodes/ folder. (Ensure the directory name remains exactly ComfyUI-Anima-Style-Explorer-Prompt without a -main suffix).Restart ComfyUI and press Ctrl + F5 in your browser!Method B: Via Git Command LineOpen your terminal inside the ComfyUI/custom_nodes/ directory and run:git clone https://github.com/mizukir0418-gif/ComfyUI-Anima-Style-Explorer-Prompt.git
ANIMA SFW/NSFW W/ Controlnet, Regional Prompt, & Realism enhancer
This is an advanced workflow for those who want to dail in an image at pro level grade. A simple version can be found HERENote: I spend a lot of time on these to make sure they are top notch. If you have ANY issues, I'm very responsive. hit me up and I'll resolve them for you.A complete user and troubleshooting guide inclusing a list of common error messages can be found here https://civitai.com/articles/24678/how-to-use-my-workflows-a-comprehensive-breakdown也有中文说明Instagram: https://www.instagram.com/synth.studio.models/Buy me a☕ https://ko-fi.com/lonecatoneThis represents Many of hours of work. If you enjoy it, please 👍like, 💬 comment , and feel free to ⚡tip 😉V9.0 Note: Both Controlnet & Regional Prompt nodes are in Beta testing. You will not find these to be as rigid as SDXL or Flux based ones, but they are fun to mess with. Added back draft mode by requestadded shhh.. nodes (You'll thank me)Made it so you can use the original image ratio.Super good for regional prompts and ControlnetAdded Regional Prompt (BETA)I'm still testing this out. Not sure how I feel about it.what it does do well: ARTwhat is sucks at: peopleReplaced math nodes to be compatible with Linux usersTweaks here and there.Ver 8.0added controlnetadded Klein enhancementreworked Post Production SuiteMinor tweaks.Ver 6.0Upgraded Prompt assist.Added an inline crop tool for easier image editing.inmproved the save option to include the option to add a date to the metadata file. name for beter organization.Minor note tweaks.Ver 5.2Updated for Comfyui changesAdded sentence remover to prevent CivitAi flagsMade some optimazation changes for Anima 3 previewreworked the user settings area.Ver 4.0:On a neverending quest for opions, I decided to tweak my Anima workflow to get relism and semi-realism out of it for the Anima2 modelAdded a detailer suite based on SDXL or Illustrious for realistic optionsNote: It's not gonna beat ZIT, but with the prompt adherence, It's cool for semi-realisticIncluded my full detailer suiteIncluded my full Post production suiteFine tuned Optical Realism to work with this model (in other words, don't mess with the settings)Ver 3.0 included in download for straight AnimeI had to make modifications as to how the Savenodes worked. ComfyUi broke them (again 🙄)What this workflow contains:Sage Attention: Speeds up productionUltimate Upscaler for prescaling and hi res fixDetailing Suite for face, hands, eyesSeed VR2 Upscaler to get 4k on low VRAMEssential Post Production SuiteJPEG ScrubberFull tutorial available.也有中文说明
Z-image turbo TXT2IMG, IMG2IMG, inpaint, controlnet, lora manager, caption, adetailer, SeedVR2.
A pretty simple workflow with a few common features. It is designed for 'legacy' mode. For now, I still think that Nodes 2.0 are mostly buggy and slower garbage, even though they have a few cool things. The metadata of a final image will not contain the diffusion model name; I still haven't found a good way to add it to the metadata. Fixed in v.1.2I didn't notice that Lora doesn't get into the metadata for automatic detection. Fixed in v2.0.
Z-Image Split-Sigma Workflow: ZiB to ZiT
Z-Image 5.0 EmberFrame Split-Sigma Workflow GuideFirst of all, a quick thank you again to the people behind ComfyUI, CivitAI, and all of the creators making nodes, checkpoints, LoRAs, workflows, tools, and helper scripts, then sharing them for everyone else to use. Without that community, this kind of workflow would not be possible, and it definitely would not be anywhere near as fun to build.This is the 5.0 EmberFrame update to my Z-Image Dual-Stage workflow. It is still very much the same basic idea: use ZiB for the first image pass, then use ZiT as the refiner. The difference with 5.0 is mostly cleanup, usability, and making the public release line up properly, but I also want to be clearer about how the dual-stage part is actually working.So this is not a huge new experimental release. It is a small, practical update. The workflow is cleaner, the helper nodes now live on GitHub, and the version jump to 5.0 fixes a mismatch between my local files, the GitHub repo, and the CivitAI version naming.Older 4.0 and 4.6 versions may still be available on this page for reference, but 5.0 is the version I recommend using now. It is the one I expect to build on going forward.The short version is this· You can still use the workflow very simply by writing a normal prompt.· ZiB / Base handles the first composition pass.· ZiT / Turbo handles the lower-sigma refinement pass.· This is a split-sigma workflow, not just a normal two-KSampler chain.· The main controls are gathered into the Global subgraph.· The Prompt / Prompt Builder can be used as a plain prompt box or as a wildcard prompt system.· Prompt enhancement is still available using Gemma4.· Image-to-image, ControlNets, post-processing, and upscaling are still optional.· The EmberFrame helper nodes are now in a public GitHub node pack instead of being treated as loose local extras.What this workflow doesThis workflow includes:· Text-to-image generation· Image-to-image· A dual-stage ZiB to ZiT generation path· Built-in ControlNet sections· A Prompt / Prompt Builder subgraph· Sequential and random wildcard prompt tools· Prompt enhancement using Gemma4· Prompt enhancement from a loaded image· Optional LG Noise Injection· Optional post-processing· Optional upscaling with SeedVR2 and Ultimate SD Upscale· CivitAI-friendly image saving and metadataImportant first step: custom nodes requiredThere are still a few custom node packs required. The easiest route is to install what you can through ComfyUI Manager. For the EmberFrame helper nodes, use the GitHub repo directly if it has not appeared in your Manager list yet.· EmberFrame Nodes: https://github.com/emberframe/emberframe-nodes - required for the new helper nodes· rgthree-comfy: https://github.com/rgthree/rgthree-comfy· ComfyUI-Image-Saver: https://github.com/alexopus/ComfyUI-Image-Saver· ComfyUI-Impact-Pack: https://github.com/ltdrdata/ComfyUI-Impact-Pack· ComfyUI-LG_SamplingUtils: https://github.com/LAOGOU-666/ComfyUI-LG_SamplingUtils· ComfyUI_essentials: https://github.com/cubiq/ComfyUI_essentials· ComfyUI-Easy-Use: https://github.com/yolain/ComfyUI-Easy-Use· ComfyUI-KJNodes: https://github.com/kijai/ComfyUI-KJNodes· RES4LYF: https://github.com/ClownsharkBatwing/RES4LYF· ComfyUI ControlNet Aux: https://github.com/Fannovel16/comfyui_controlnet_aux· ComfyUI-DepthAnythingV3: https://github.com/PozzettiAndrea/ComfyUI-DepthAnythingV3· ComfyUI-SeedVR2_VideoUpscaler: https://github.com/numz/ComfyUI-SeedVR2_VideoUpscaler· ComfyUI-Unload-Model: https://github.com/SeanScripts/ComfyUI-Unload-Model· ComfyUI_UltimateSDUpscale: https://github.com/ssitu/ComfyUI_UltimateSDUpscale· WAS Node Suite - Revised: https://github.com/ltdrdata/was-node-suite-comfyui· comfyui-vrgamedevgirl: https://github.com/vrgamegirl19/comfyui-vrgamedevgirlFor a manual install, custom nodes normally go here:ComfyUI/custom_nodes/For a Windows portable install, that is usually:ComfyUI_windows_portable/ComfyUI/custom_nodes/After installing or updating node packs, restart ComfyUI before loading the workflow.Model setupYou will still need to point the workflow at your own ZiB and ZiT model files. The Global subgraph is the first place to check after loading the workflow.· Base Model: your Z-Image Base / ZiB model· Turbo Model: your Z-Image Turbo / ZiT model· CLIP/text encoder and VAE: set these to the files used by your local Z-Image setup· Gemma4 text encoder: only needed if you use the Prompt Enhancer· ControlNet, SeedVR2, and upscale models: only needed if you use those optional sectionsThe cleaned example path style is:Z-Image\Base\z_image_base_model.safetensorsZ-Image\Turbo\z_image_turbo_model.safetensorsMain workflow overviewThe main graph is meant to be readable from left to right. The big pieces are deliberately grouped so you can start simple, then enable the extras only when you need them.· Image Saver· ZiB LoRA Loader· ZiT LoRA Loader· Prompt From Image· Prompt / Prompt Builder· Prompt Enhancer· Negative Prompt· Image 2 Image· Latent Switch· Global· LG Noise Injection· Post Processing· Optional ControlNets· Optional upscaling sectionsA note on the split-sigma approachThis is the part that is easy to miss if you only look at the workflow from a distance. It can look like a standard double KSampler setup, where one model makes an image and a second model refines it afterward. That is close enough to understand the broad idea, but it is not quite what this graph is doing.In this workflow, the scheduler creates the sigma schedule for the generation, then the workflow splits that schedule into two parts. The higher-sigma portion is used for the early, noisier part of the image formation, and the lower-sigma portion is used for the later refinement part. So instead of running two totally separate sampling jobs, the two Z-Image models are sharing one staged denoising plan.Practically, I think of it like this: ZiB gets the first pass where the image is still loose and structural, then ZiT takes over when the latent is already partly formed and the remaining work is more about polish, detail, and coherence. The handoff is controlled by the sigma split rather than just by sending a finished image or finished latent into a second sampler.In the Global subgraph, the chain is:1. BasicScheduler creates the full sigma schedule.2. SplitSigmas separates that schedule into high-sigma and low-sigma portions.3. Sigmas Resample reshapes the first-stage sigma path used by the ZiB pass.4. The first SamplerCustomAdvanced pass uses the ZiB model and the resampled high-sigma section.5. The second SamplerCustomAdvanced pass uses the ZiT model and the low-sigma section, using the latent from the first pass.I do not want to oversell the theory here. I am explaining it in practical workflow terms rather than pretending this is a finished technical paper. The important point for users is that the workflow is trying to let ZiB and ZiT do different parts of the same denoising journey, rather than simply stacking a generic refiner on top of a completed first result.Why use this approach? In my testing, it gives a useful blend of the two models' strengths. ZiB tends to be the more inventive composition model, so I like letting it handle the early, looser part of the generation. ZiT tends to bring the cleaner finish, so I like letting it take over for the later, lower-sigma refinement work.The main drawback is that you are still asking ComfyUI to work with two models instead of one. If your system can handle that, the tradeoff has been worth it for me: the workflow can run at a relatively low step count, not as low as a straight ZiT-only workflow, but usually not as high as I would expect from a ZiB-only setup either.As always, I am standing on the shoulders of much smarter people here. This workflow is my practical way of wiring the pieces together, not a claim that this is the only correct way to use these models.1. Global subgraphMost of the controls I reach for first are in the Global subgraph. This is where you set the two model paths, sampler, scheduler, seed behavior, aspect ratio, orientation, megapixels, batch size, and the core generation values.In simple terms:· ZiB / Base handles the first composition pass.· ZiT / Turbo handles the lower-sigma refinement pass.· Split-sigma generation lets the two stages do different jobs inside one staged denoising path.For a first run, I would keep the defaults close to the included setup and only change the model paths, aspect ratio, and orientation. Once you know it is running, then start playing with the rest.2. Prompt and negative promptYou can use the workflow with a normal prompt. You do not have to use wildcards, prompt enhancement, image prompting, or any of the extra toys on your first run. A plain positive prompt plus the included negative prompt is enough to test that everything is connected.The negative prompt is deliberately fairly general. It is not magic, but it gives the workflow a useful starting bias against low-quality image problems, text, logos, watermarks, and obvious anatomy issues.3. Prompt / Prompt Builder subgraphThe Prompt / Prompt Builder subgraph can be used in two ways: as a simple prompt box, or as a wildcard prompt builder. If you just want to type a prompt and run the workflow, use it like a normal prompt field. That is still completely valid.The wildcard side is there for people who like building batches of related ideas without rewriting the whole prompt every time. The system is made from three main parts:· Wildcard Rule Builder nodes· Wildcard Config Combiner· Wildcard Prompt AssemblerEach Rule Builder controls one source file and one token name. The Config Combiner gathers those rules together, and the Prompt Assembler turns the final resolved values into a usable prompt.A basic token prompt might look like this:{subject} in {location}, {lighting}, {camera_angle}A good way to test it is to enable one Rule Builder, run once, check the preview, then add another rule. Build it up slowly and it becomes much easier to see what each wildcard source is doing.4. Prompt From Image and Prompt EnhancerThe Prompt Enhancer is still built around Gemma4. You can feed it a written idea, an image-guided idea, or a simple subject, then let it expand that into a more complete prompt structure.The flow is basically:6. Write a simple prompt or build one with the Prompt Builder.7. Optionally load an image into Prompt From Image.8. Let Gemma4 enhance the prompt or image-guided idea.9. Send the enhanced text onward to the positive prompt conditioning.The Prompt Enhancer subgraph includes a Gemma4 CLIP loader, the TextGenerate node, the main enhancement instruction, and preview output for the generated prompt. The required Gemma4 text encoder should be placed in your ComfyUI text encoder folder.ComfyUI/models/text_encoders/gemma4_e4b_it_fp8_scaled.safetensors5. LoRAsThe workflow still includes two LoRA loaders in the main graph: one for Z-Image Base and one for Z-Image Turbo. You can leave them empty for a first test. Once the base workflow is generating correctly, add LoRAs back in one at a time so it is obvious what changed.6. Image-to-Image subgraphThe Image-to-Image section is still there for img2img. Load your source image, then use the Latent Switch to choose the image latent path instead of the empty latent path.Important:· Input 1 is the img2img path.· Input 2 is the empty latent path.· When using img2img, reduce the denoise value in the Global subgraph.For anime-to-realistic conversion, I usually start by loading the same reference into Image 2 Image and Prompt From Image, then let the enhancer build a more descriptive prompt. After that, the useful work is mostly denoise, prompt wording, and deciding whether ControlNet is helping or getting in the way.7. ControlNet subgraphThe ControlNet subgraph is optional. If you are doing a simple text-to-image test, leave it alone at first. Once the main workflow is behaving, you can enter the ControlNet subgraph and enable the groups you want to use.The built-in options include:· Depth Anything V3· Depth Anything V2· Canny· OpenPoseFor anime-to-realistic conversions, I usually try depth first. It gives the model structural guidance without forcing every line of the original image to survive.8. Post Processing subgraphThe post-processing subgraph is intentionally simple. It adds a little sharpen and a little film grain. Some images benefit from that. Some images look better without it. Treat it as a finishing option, not a required part of the generation.9. Upscaling optionsThere are still two optional upscaling paths. I would not turn either of them on for the very first test run. Make sure the base workflow works first, then add upscaling when you are happy with the generation path.SeedVR2 UpscaleSeedVR2 can be a very nice final enlargement path, but it has its own model requirements and settings. Use it after the base image is already working.Ultimate SD UpscaleUltimate SD Upscale is the second optional upscale route. It is still useful when you want a more traditional tiled upscale pass with familiar controls.10. Image saving and metadataThe Image Saver setup is one of the parts I care about most, because it makes the workflow easier to share, debug, and revisit later. The saved data is set up to include the important generation details where possible.That includes:· Checkpoints used· LoRAs used· Prompt-related information· Image dimensions· Sampler and scheduler information· The seed usedRecommended starting workflowIf you are loading the workflow for the first time, I would suggest this order:1. Install the required custom node packs.2. Install or update EmberFrame Nodes from GitHub, or from ComfyUI Manager if it is already listed for you.3. Restart ComfyUI.4. Load the workflow.5. Set your ZiB and ZiT model paths in the Global subgraph.6. Set your CLIP/text encoder and VAE paths.7. Leave LoRAs empty for the first test.8. Set aspect ratio, orientation, and megapixels in the Global subgraph.9. Write a simple prompt in Prompt / Prompt Builder.10. Run a basic text-to-image test first.After that, enable extras one at a time:· Prompt Enhancer· Prompt From Image· Wildcard Prompt Builder nodes· Img2Img· ControlNets· Post Processing· SeedVR2 Upscale· Ultimate SD UpscaleA few final notesThere are a lot of moving parts in this workflow. I know that. The best way to learn it is to start with the plain text-to-image path, then add one section at a time as you need it.Version 5.0 is mainly about making that experience cleaner and easier to maintain. The workflow naming is now lined up, the helper nodes are on GitHub, and this should be a more sensible starting point for anyone downloading it fresh.Most importantly: please enjoy it. I hope it helps you make cool things.If you use it, remix it, break it, improve it, or make something interesting with it, I would genuinely love to see what you make.Thanks for checking it out, and happy generating.
【HiDream】TXT to IMG
✨ HiDream — Text to Image — Simple WorkflowA clean, all-in-one HiDream text-to-image workflow built entirely with the UmeAiRT Toolkit for ComfyUI.Only 8 nodes. No spaghetti wires. Just load your model, write your prompt, and hit generate.⚠️ IMPORTANT — Nodes 2.0 RequiredThis workflow is built for the Nodes 2.0 (Vue) interface of ComfyUI. If you don't enable it, the workflow may have display problems.How to activate Nodes 2.0:Open ComfyUIGo to Settings (⚙️ icon, bottom-left)Find "Use Nodes V2 (Vue)" and toggle it ONRefresh the pageLoad the workflowIf you prefer the classic interface, check out my Legacy version of this workflow instead (link).🎯 FeaturesText-to-Image generationAutomatic download of models in auto versionBuilt-in SeedVR2 upscaler — high-quality tiled upscaling (toggleable on/off) Slower than a classic upscaler, but significantly better qualityFull metadata embedding — your images are saved with all generation parameters, ready for online publishing and remixing3 LoRA slots — with individual on/off toggles and strength control and you can connect as many other lora modules to each other for as many LoRA as you want.📦 Custom Node RequiredOnly one custom node to install:👉 ComfyUI-UmeAiRT-ToolkitInstall via ComfyUI Manager (search "UmeAiRT") or use the UmeAiRT Auto-Installer.The Toolkit packages everything internally — upscaler, face detailer, metadata saver. No other custom nodes needed.📂 Files you need (in manual version)24 gb Vram : base16 gb Vram: Q8_012 gb Vram: Q5_K_S<12 gb Vram: Q4_K_SFor base versionModel : hidream_i1_dev_fp8.safetensorsin ComfyUI\models\diffusion_modelsFor GGUF versionGGUF_Model : hidream-i1-dev-QX_K_S.gguf in ComfyUI\models\unetVAE : ae.safetensorsin ComfyUI\models\vaeCLIP : clip_l_hidream.safetensors, clip_g_hidream.safetensors, t5xxl_fp8_e4m3fn_scaled.safetensors and llama_3.1_8b_instruct_fp8_scaled.safetensorsin ComfyUI\models\clip
ComfyUI beginner friendly HiDream 01 Text-to-Image Workflow with Easy Prompt Saver by Sarcastic TOFU
This is a very simple workflow that helps you to save your HiDream 01 Text to Image Generation Data into a human readable .txt file. This will automatically get and write your metadata to the .txt file. You will find all the saved prompt files that it generated with the images inside the Archive (.Zip) that has the workflow. Also with the Image Saver Simple node used here you may embed the workflow itself with each saved image or save the image and workflow for your work separately.HiDream.ai was founded in 2023 by Dr. Mei Jianxiong, a prominent Chinese AI researcher and former expert at Baidu and Kingsoft, with the goal of creating advanced generative AI models for design and creativity. The HiDream-O1-Image open-source models were just released on May 8, 2026. The HiDream 01 architecture functions as a multimodal generative model that interprets natural language text prompts and translates them into highly detailed visual assets. It utilizes deep diffusion network technology to iteratively refine random noise into structured images based on the semantic meaning of your instructions. By analyzing vast datasets of paired text and imagery, the system predicts exactly where pixels should align to match your desired style, composition, and lighting effects.You can download your necessary model file used in this workflow from HuggingFace and LORA from CivitAI (Details are mentioned below). Make sure you have latest enough ComfyUI installation and install any necessary nodes for for this workflow using ComfyUI manager and place the correct files in correct places. Also check out my other workflows for SD 1.5 + SDXL 1.0, Pony, WAN 2.1, WAN 2.2, MagicWAN Image v2, QWEN, HunyuanImage-2.1, HiDream E, Ernie Image, KREA, Chroma, AuraFlow, NoobAI, Illustrious, Lumina2, Z-Image Turbo, Flux.2 Klein 9B & 4B, Flux.1 Dev and Kandinsky Image 5 Lite (T2I & I2I) models. Feel free to toss some yellow Buzz on stuffs you like.How to use this -#1. Just select your desired HiDream 01 model files first and#2. set your desired image dimensions to start#3. then input your desired image prompt.#4. select how many images you want (Change the number besides the "Run" button)#5. select image sampling methods, CFG, steps etc. settings#6. finally press the run button to generate. That's it..** LORA usage for this workflow is optional you can use it without any LORAs, use with 1 or 2 or any other number of LORAs, to add new LORAs press the L button on top to lunch LORA Manager on a new tab find your LORA and if you want to use that LORA just click the upward Kite button.Required Files============### Download Link for HiDream 01 models -++++++++++++++++++++++++++++++++++This HuggingFace page has all the HiDream 01 model (base & dev) files. By design from very inception of HiDream 01, it's image generation/editing process uses just a single any of of these all in one checkpoint files.. so you may download and use just one file from here for this workflow. https://huggingface.co/Comfy-Org/HiDream-O1-Image/tree/main/checkpointsI have used the fp8 scaled safetensors file for the HiDream 01 base ( hidream_o1_image_fp8_scaled ) for this workflow which is perfect for any 8GB VRAM GPU, if you have 16 GB or higher VRAM GPU you may use the bigger bf16 file.Also, You may use any external prompt enhancer like ComfyUI's default examples for base & dev models have shown if you know how to modify ComfyUI workflows, but for simplicity I opted not to use any prompt enhancer.LORA used on generated images -+++++++++++++++++++++++++++HiDream O1 - noir lighting style -https://civitai.com/models/2647859/hidream-o1-noir-lighting-style?modelVersionId=2973135
My 4-In-1 Klein Workspace
Pheeby's 4-In-1 Flux Klein WorkspaceWhat this is and what it does:I've assembled my most often-used workflows into a single "workspace" file, because it saves me having to open separate tabs for different tasks and keep track of all of them, and eliminates weird bugs like LoRAs from different workflows merging and screwing up image generations and edits, or whatever other funky things can go wrong when you have multiple workflows open at the same time.The workspace includes sections for image generation, compositing, editing, and upscaling. The first section is used for creating images out of nothing but text. The next section is used for compositing these images into new images and editing them together into a seamless whole. The third section is used for various minor editing tasks like changing the style or lighting, color correction, etc, and finally, the last section is used for upscaling to achieve a finished result.It's been really convenient and useful for me to have all of these tools together in one place, so I'm sharing this on the off chance that someone else will find at least some part(s) of it useful as well, if only in constructing their own more ergonomically-designed-for-themselves workflow(s).There are some custom nodes required for this to be of any use to anyone, but there's nothing all that exotic about any of it, the nodes are actually useful and are not poo-poo nodes made of cockadoodle, and the Manager fixes you right up in no time, if you've ever used it you'll know this already, blah blah blah zzzzz.Nodes you'll need to use everything as-is:rgthree-comfy (https://github.com/rgthree/rgthree-comfy)Pixaroma (https://github.com/pixaroma/ComfyUI-Pixaroma)JPS Custom Nodes for ComfyUI (https://github.com/JPS-GER/ComfyUI_JPS-Nodes)ComfyUI-ReferenceChain (https://github.com/remingtonspaz/ComfyUI-ReferenceChain)ComfyUI-GGUF (https://github.com/city96/ComfyUI-GGUF) <-- if using GGUF modelsNaturally, you will want to change some things around to make it all work for you, especially if you're not using GGUF models, but all of this setup works fine with regular models and with the 4B variant of Klein, you'll just have to swap out a couple of nodes. Refer to the README file if/when you get mysterious errors for no apparent reason. As always, YMMV, good luck, and have fun~!PS: I do very graciously accept tips, but I don't like annoying people by asking them for anything, because it just feels weird. Just know that if people tip me, I will have the resources to try my hand at training. I don't trust my 8GB VRAM to allow me to finish training a LoRA at home before I die of old age. XD
Not so simple (or is it?) Anima Workflow
⚡ Anima Workflow:🛠️ Purpose & Design PhilosophyThis workflow is designed for quality and autonomy, not speed. It follows an "all-in-one" philosophy: configure your settings, hit queue, and let the workflow handle everything from initial generation to high-res detailing in a single pass.Not for Speed: If you want rapid-fire generations, this is not the tool for you. A solid, much faster alternative created by darksidewalker can be found here.Personal Use: This was built for my personal production needs. It is not intended to be a "one-size-fits-all" solution, but I am sharing it for those who value the same high-fidelity results. Please adjust the settings to your preferences!Heavy Duty: Due to the multi-stage processing, this workflow can be resource-intensive. In my experience, the detailers are not usually needed. YMMV.On v1g and after: If the results are too blurry for you after USDU, you can try using the RTX nodes after it to help.v2 is compatible with AIO versions of Anima models. Note: You might have to select a random model in the Checkpoint Loader node even if you are not using it. This is because it references your models/checkpoints folder. The opposite may also be the case if you are using the Checkpoint Loader node but not the Model Loader in the Diffusion Model Loader group which references the models/diffusion_models folder.🚀 Key FeaturesBeyond standard generation and upscaling, this workflow integrates:Power LoRA Loader: Efficiently manage multiple LoRAs without spaghetti wires.Global Controls: Centralized Seed, Sampler, and Scheduler nodes for a unified experience.Bypass Control to toggle features on/off.Visual Validation: Integrated Image Comparer nodes to see exactly how your image evolves at every stage.Upscaling: 2-stage upscaling using standard image upscaling and Ultimate SD Upscale (optional).Triple Detailer Groups: 3-stage detailing using standard BBOX and SEGM detection models for faces, hands, and clothes.CivitAI Ready: Images are saved with full metadata (Model, LoRAs, Prompts) for easy site parsing.⚠️ Disclaimer & CompatibilityInstall at Your Own Risk: Updating ComfyUI or adding custom nodes can break your environment. I am not responsible for any installation issues.Portable Version: This was built and tested on the ComfyUI Portable version. Desktop app users may require additional troubleshooting."Your Mileage May Vary": Your environment is almost certainly different from mine. I do not guarantee 1:1 compatibility.Nodes 2.0: I strongly recommend disabling Nodes 2.0. It causes unpredictable behavior; I will not provide support for any issues arising from its use.🤝 Support & BoundariesNo DMs: Direct messages are disabled due to high volume. Please use the Discussions tab below. Check previous comments first (unless there aren't any yet), as most common questions may have already been answered.Custom Requests: I do not take private requests for custom workflows. If you need a specific solution built, please post a Bounty on CivitAI. There are many talented creators here who will be happy to assist you for a fee.Modifications: You are free to add or remove nodes as you see fit. However, if you change the internal logic, you are responsible for your own troubleshooting.The only place I am actively maintaining this workflow is here on civitai. If my current workflows are being posted and monetized elsewhere, whoever posted them is obligated to provide support to those users.I have not and never will monetize my workflow, since it was designed for me by me.
Anima Turbo w/ Negative Prompt Workflow
Anima Turbo + CFG 1 Negative promptA lightweight, beginner-friendly workflow for Anima Turbo that allows negative prompting at CFG 1 using NegPip.Turbo models are fast, but running at CFG 1 means the negative prompt box has no effect. This workflow solves that problem using NegPip, which allows you to apply negative concepts directly inside the positive prompt.How NegPip WorksInstead of using the negative prompt box, place unwanted concepts in the positive prompt with a negative weight:(blurry:-1)(low quality:-2)(text:-4)NegPip interprets these negative weights as negative conditioning, allowing you to steer the image away from unwanted features while keeping the speed benefits of CFG 1 turbo generation.Don't be afraid to use larger values. In my testing, weights up to ±4 can produce strong results with Anima without frying the image.Recommended SettingsCFG: 1Steps: 8–12Sampler: Euler / Euler Ancestral / ER-SDEResolution: Up to 1536×1536 works, but ~1.5 megapixels is a good sweet spot between quality and speed in my opinionIncluded FeaturesAnima Turbo LoRA preconfiguredNegPip integrationImpact Wildcard EncoderMetadata savingSimple single-pass generation pipelineEasy LoRA and wildcard expansionWildcardsCreate .txt wildcard files in:ComfyUI/custom_nodes/comfyui-impact-pack/custom_wildcardsThen call them in your prompt using:__WildcardName__Wildcard randomization is tied to the image seed by default for reproducible generations.LimitationsThis workflow is intentionally minimal. The goal is to provide a clean, reliable starting point for Anima Turbo users who want the speed of CFG 1 generation without giving up the control that negative prompting provides.
Rebels PiD (low vram)
PiD reformulates the latent-to-pixel decoder as a conditional pixel-space diffusion model, unifying decoding and upsampling into a single generative module. It denoises directly in high-resolution pixel space and produces a super-resolved image in one pass. This repository hosts the released decoder checkpoints, plus the encoder/decoder ("VAE") weights they depend on.WARNING: the distilled Flux Klein 4b and 9b workflows are experimental, they dont always provide the best results due to the distillation forcing too much detail in the pixel diffusion process. it can sometimes create artifacting as well. both BASE models for Klein handle PiD VERY well though!To install the ComfyUI-PiD custom node and utilize its automated model downloader, follow these steps specifically tailored for the ComfyUI Windows Portable environment.1. Custom Node InstallationDo not just drag and drop files. For a portable installation, you must use Git to ensure the node's internal structure and submodules remain intact.Navigate to your ComfyUI_windows_portable root folder.Open a terminal (CMD) in this folder.Navigate to your custom_nodes directory:DOScd ComfyUI\custom_nodes Clone the repository:DOSgit clone https://github.com/Merserk/ComfyUI-PiD Return to the root folder:DOScd ..\.. Install the required dependencies using the embedded Python:DOS.\python_embeded\python.exe -m pip install -r .\ComfyUI\custom_nodes\ComfyUI-PiD\requirements.txt LINK TO Z-Image Base Model Files:https://civitai.com/models/2342907/rebels-z-image-base2. Using the Auto-Download FeatureThe PiD nodes are designed to pull models automatically upon the first execution of a prompt.Restart ComfyUI completely.Load a workflow that utilizes the PiD Decode or PiD Prepare nodes.Ensure the auto_download parameter is set to True in the node properties.Queue your prompt.Monitor the Terminal: Watch the CMD window. You will see HTTP requests appearing as the node validates and begins downloading the required weights from Hugging Face.3. Troubleshooting "Stalls"Because there is no progress bar, a silent CMD window can look like a stall. However, if the download actually hangs (no new INFO lines for 5+ minutes):Kill the Process: Close the CMD window completely to force the download attempt to terminate.Restart ComfyUI: Open the terminal and restart ComfyUI to clear the failed request from your GPU/Network cache.Disable Auto-Download: Before queuing again, go into the PiD Decode node settings and set auto_download to False.Verify/Retry: With auto_download set to False, the node will skip the network request and attempt to load existing files. If you suspect the download partially finished before stalling, check ComfyUI\custom_nodes\ComfyUI-PiD\vendor\PiD\checkpoints to see if a folder has been created. If it is empty or incomplete, remove that partial folder before trying the download again.Pro-Tip: If the auto-downloader consistently fails, it is usually due to network timeouts on large files. If this happens, you must perform a manual download once to place the .pth file into the vendor directory as described in the repository's documentation. Once the file exists locally, you can keep auto_download set to False permanently.
ZIB-GGUF-dAIver-v1.5
Optimized Low-VRAM Workflow for Z-Image-Base (GGUF)Refined version of my ZIT workflow, modified to work with ZIBThis workflow delivers the full power of Z-Image-Base in GGUF format, specially optimized for GPUs with less than 8 GB VRAM, like my RTX 4050 with only 6 GB. The pre-selected Z-Image-Fun-LoRA provides a noticeable speed boost with almost no quality loss. Two intelligent upscaling stages, optional automatic trigger-word integration via the Super LoRA Loader, and an extended save node complete this elegant setup.Version 1.5 (previous versions were only my personal use) brings significant improvements in speed, usability, and upscaling quality — while remaining extremely VRAM-efficient (tested on RTX 4050 with only 6 GB).What’s new in v1.5:selectLatentSizePlus — intuitive aspect-ratio and resolution selector with beautiful presets (including 7:12 Tall Vista and other golden-ratio-friendly options) plus easy orientation swapFull SEEDVR2 Video Upscaler Subgraph — powerful DiT-based (.safetensors or GGUF) high-end upscaler that delivers stunning 4K+ results with intelligent resolution handling, Lab color correction, and temporal settings. Works exceptionally well on still images too, producing superior detail and coherenceCLIP switched to the abliterated Qwen3-4B-Instruct-2507.Q5_K_S.gguf (lumina2 type)Improved workflow organization, expanded notes, and more robust saving optionsRequired Custom Nodes (updated for v1.5):ComfyUI-GGUF - https://github.com/city96/ComfyUI-GGUF - UnetLoaderGGUF + CLIPLoaderGGUFnd-super-nodes - https://github.com/HenkDz/nd-super-nodes - NdSuperLoraLoader with tags, trigger words & beautiful UIsave-image-extended-comfyui - https://github.com/thedyze/save-image-extended-comfyui - Advanced saving with metadata & dynamic filenamesComfyUi-MzMaXaM - https://github.com/MzMaXaM/ComfyUi-MzMaXaM - selectLatentSizePlusComfyUI-SeedVR2_VideoUpscaler - https://github.com/numz/ComfyUI-SeedVR2_VideoUpscaler - SEEDVR2 Video Upscaler SubgraphModels & Downloads (exact paths)The following list explains the base models I am most frequently using with this workflow. The list as well explains where to put each file after you downloaded it.1. Main Model (Z-Image-Base GGUF):File: Juggernaut_Z_V1_by_RunDiffusion_q6_k-004.ggufDownload: https://huggingface.co/RunDiffusion/Juggernaut-Z-Image/resolve/main/Juggernaut_Z_V1_by_RunDiffusion_q6_k-004.ggufTarget folder: ComfyUI/models/diffusion_models/2. Text Encoder (CLIP)File: Qwen3-4B-Instruct-2507-abliterated.Q5_K_S.ggufDownload: https://huggingface.co/mradermacher/Huihui-Qwen3-4B-Instruct-2507-abliterated-GGUF/resolve/main/Huihui-Qwen3-4B-Instruct-2507-abliterated.Q5_K_S.ggufTarget folder: ComfyUI/models/text_encoders/ (or clip/)3. VAEFile: ae.safetensors (~335 MB)Download: Usually included with Z-Image-Turbo setups or available here: https://huggingface.co/Comfy-Org/z_image_turbo/resolve/main/split_files/vae/ae.safetensorsTarget folder: ComfyUI/models/vae/4. Upscalers4× Upscaler: 4xLSDIRplusN.pth (variant of 4x-UltraSharp) → https://civitai.com/models/116225/4x-ultrasharp1× Skin-Contrast Upscaler: 1xSkinContrast-High-SuperUltraCompact.pth Download: https://huggingface.co/notkenski/upscalers/blob/main/1xSkinContrast-High-SuperUltraCompact.pthTarget folder: ComfyUI/models/upscale_models/5. Pre-loaded LoRA (included in workflow):File: Z-Image-Fun-Lora-Distill-2603_UDCAI_ComfyUI.safetensorsDownload: https://civitai.com/models/2362961/z-image-fun-distill-lora (UDCAI Edit version)Target folder: ComfyUI/models/loras/6. SEEDVR2 Models (for the new high-end upscaler – optional but recommended):DiT Model: seedvr2_ema_3b-Q8_0.ggufVAE: ema_vae_fp16.safetensorsDownload from the official ComfyUI-SeedVR2_VideoUpscaler repository or Hugging Face and place in the folders required by the custom node.Key Nodes & Their FunctionsNdSuperLoraLoader with automatic trigger-word detection and clean tag interfaceselectLatentSizePlus → effortless aspect-ratio and resolution controlKSamplerAdvanced with proven settingsTwo-stage classic upscaler (4× LSDIR + 1× Skin-Contrast) in its own subgraph, orNew SEEDVR2 Video Upscaler Subgraph → for ultimate quality (optional, easily bypassed)SaveImageExtended with full metadata and dynamic filenamesRecommended Settings (already set in the workflow)Sampler: euler, dpmpp_sde or res_multistepScheduler: simple, normal, beta or ddim_uniformSteps: 8–12 (with Z-Image-Fun-LoRA)CFG Scale: 1.0–1.5Shift: 4–7Resolution: 1024×1536 (portrait) – perfectly balanced for the golden ratio and typical ZIB outputs - the upscaler will automatically upscale by a factor of 4How to Use the WorkflowInstall all required custom nodesLoad the workflowEnter your positive prompt (the pre-loaded Fun-LoRA trigger words are handled automatically)Adjust negative prompt if neededChoose aspect ratio and resolution via the Size SelectorGenerate (Euler + Simple recommended)Optionally upscale with SEEDVR2 for cinematic resultsDone — beautifully saved with metadataSpecial thanks to @LumaRift who provided the SeedVR2 subworkflow and some good advise on optimizing my setup.
Combined workflow (ComfyUI txt2img, Wildcards, LLMs/Ollama, Pony, SDXL, Illustrious, Flux, Qwen, Z-Image, Anima)
"Combined Workflow" v8.2 (20260531)This "Combined Workflow" (about 2MB and over 600 nodes) is a ComfyUI txt2img workflow that performs SDXL, Pony, Illustrious, Flux1D, Qwen and ZImageTurbo/Base, Anima and Flux2Klein generations with an optional prompt extension using LLMs/Ollama and Wildcards processing.Note: the workflow is not fast, on a 4090, a batch of two image can take 7 minutes.It will generate an upscaled 16MP image as the final result while staying as close as possible to the original generation and produce CivitAI compatible metadata for each stage of the image generation.- Stage 1: Generate the regular image using [Detail Daemon](https://github.com/Jonseed/ComfyUI-Detail-Daemon) sampler, pass it to a selector (can be bypassed for batch generation)- Stage 2: Upscale to 4MP using a model- Stage 3: Use "Ultimate SD Upscale" to redefine the components of the 4MP image using the original model and LoRAs' specific characteristics. An optional Flux.1D resampler is available followed by a Cleanup stage, then Faces, Hands and Eyes Detailer are then used on the resulting image.- Stage 4: That result is sent to SeedVR2 or HighresFix to generate the final 16MP image and a color matching step is performed to make it as close as possible as the initial upscaled image.The workflow contains a READ ME FIRST section that details some information about how it came to be, what it does and how to use it. Please refer to it for more details.FYSA: list (and count) of used custom nodes: 1 "cg-image-filter", 221 "comfy-core", 4 "comfy-image-saver", 2 "comfy-mtb", 18 "comfyliterals", 1 "comfyui_controlnet_aux", 12 "comfyui_essentials", 9 "comfyui_llm_party", 2 "comfyui_ultimatesdupscale", 12 "comfyui-crystools", 61 "comfyui-custom-scripts", 8 "comfyui-detail-daemon", 51 "comfyui-easy-use", 5 "comfyui-fbcnn", 69 "comfyui-image-saver", 41 "comfyui-impact-pack", 1 "comfyui-inspire-pack", 35 "comfyui-kjnodes", 7 "comfyui-lora-manager", 6 "comfyui-ollama", 4 "comfyui-qwenvl", 1 "comfyui-resolution-master", 13 "comfyui-rmbg", 75 "rgthree-comfy", 3 "seedvr2_videoupscaler"Previous releases:v8.1 (20260504): Updated to work with updated cg-image-filter.v8 (20260308): Added QwenVL as a local LLM (01a, 01b, 01z) + Added QwenVL based "image to prompt" extraction (01c) + Added a new post-positive prompt generation optimization (01z) + Added Detail Deamon for all Samplers and a couple resampler + Added ZimageBase and Animav7 (20260216): Added external LLMs capability + Added an "Automatic" system prompt with model specific rules + Added an optional Flux1.D Resampler (S3, 05a03) + Added a HiresFix "Cleanup" node right after the Resampler steps (S3, 05b01) + Split S3 into its core components (the largest block on the workflow) with many ways to compare from step to step + Added many additional "notes" to explain how to make better use of the workflowv6 (20260131): Improved Stage 3: Resampler (2-pass: Regeneration + Details enhancement) and Detailers to follow original conditioning + Continued improvement to "Ollama" logicv5 (20260124): Added "Advanced" Ollama prompt + Added a new "LoRA randomizer" group + Implemented SEGS for Detaillers using "small" Face/Eyes/Hands selection logicv4.1 (20260118): included setup requirements (diffusion models as checkpoints + Ultralytics required setup) in "READ ME FIRST" section + Changed to a common resolution selectorv4 (20260111): Addition of alternate samplers for Qwen and Z Image Turbo + removal of node failing to install on new Comfy installation + extended documentation: muted nodes-chain need to be manually selectedv3.1 (20251231): Hotfix for face/hand sizev3 (20251230): Additional detailers tweaks + alternative models for refiner/detailer stepsv2 (20251228): Trigger word selection + Detailers tweak + Usage clarificationsv1 (20251226): Initial releaseWork-in-Progress release:This workflow(Pony, SDXL, Illustrious only for now) is a Work-In-Progress combination, testing and tweaking of various elements from other workflows to generate an upscaled 16MP image as the final result while staying as close as possible to the original generation as generate CivitAI metadata for each stage of the image generation.- Stage 1: Generate the regular image, pass it to a selector (can be bypassed for batch generation)- Stage 2: Upscale to 4MP using HiResFix- Stage 3: Use Ultimate SD Upscaler (No Upscale) to redefine the components of 4MP image using the original model and loras' specific characteristics. Faces and Eyes Detailer are then used on the resulting image.- Stage 4: That result is sent to SeedVR2 to generate the final 16MP image.There are many nodes involved in this workflow. Because of that I made use of multiple subgraphs to keep the workflow organized and easy to navigate.Groups exists as organizational structure for the entire process and follow the Stage numbers.It "works for me" but it might not be the best way to do it. Feedback is welcome.PS: Despite my best effort, I still do not know how to have the "Nodes" used show on each image's page on CivitAI -- if someone knows how to please let me know.Older releases:The workflows I use with my Wildcards (see my account for those).Within the zip is a README.md that explains the various use cases:The SDXL, Illustrious and Pony compatible workflow is an extension of @DigitalPastel 's "Smooth Workflow" https://civitai.com/models/1598938/smooth-workflow-txt2imgThe txt2img Flux and Qwen workflow is an extension of @AlexLai 's "Atomix Workflow" https://civitai.com/models/878828/atomix-flux-txt2img-workflowThe Z-Image Turbo workflow is an extension of @MrSmith2025 's "Z-Image Turbo - T2I Workflow + Detailer + SeedVR2 Upscaler + Color Grading" https://civitai.com/models/2174733/z-image-turbo-t2i-workflow-detailer-seedvr2-upscaler-color-gradingEach workflow can work with Ollama (if available) to create a multi-line narrative. They use Ollama as part of the workflow, which might be a VRAM resource constraint (setting "keep alive" to 0 will unload the model immediately after the request finishes). The conversion model should be instruction-tuned.
Friendly LTX-2.3 T2V+I2V+FLF+Lipsync
Welcome to my 💫🎦 Friendly LTX-2.3 T2V+I2V+FLF+Lipsync✨ Less mess, more magic· Unified VIBE FLF - Lipsync all-in one version including First Last Frame mode with latest quality enhancers and VibeVoice implementation for voice cloningUnified Omni - Lipsync all-in one version with latest quality enhancers and OmniVoice implementation for voice cloningUnified ID - Lipsync all-in one better quality version with two-stage video generation and ID-Lora implementation for voice cloningUnified Light - Lipsync all-in one version with single-stage video generationLTX-2.3 is a state-of-the-art DiT-based (Diffusion Transformer) audio-video foundation model developed by Lightricks. It represents a significant evolution from LTX-2, delivering enhanced audio and visual quality alongside improved prompt adherence. The model is specifically designed to generate synchronized video and audio within a single unified architecture, making it a powerful tool for multimodal content creation.I offer my unique workflow with convenient options control and all-in-one structure (audio, t2v, i2v)💻 System requirements:Minimum system requirements for 540p i2v and 720p t2v:RTX 3000-s, 8GB+ VRAM, 45GB+ RAM, 8-core processor, SSD, latest ComfyUI🚀 Low VRAM optional optimization:For systems with low VRAM use --reserve-vram ComfyUI parameter in run_nvidia_gpu.bat: --reserve-vram 4 (or other number in GB).📌 Detailed tips and links to models in the workflow✨ Workflow features:Extremely user-friendly interfaceMaximum performance and optimization from 8GB of VRAM: GGUF or 8-step distilled model with fp4 or fp8 text encoderAll-in-one: i2v, t2v, and interpolationConvenient one-click mode switchingPrompt enhancer and sampler previewsGeneration time setting in secondsLora support (up to 3)Detailed tips and links to all necessary modelsManual random seed for complete control over generations🤗🙏🏼 Thanks to Lightricks TeamOriginal repo — GitHub