ComfyUI Workflows

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

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.

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.

IMG2PROMPT Workflow

A very simple image to prompt workflow.

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" ] } ] } }

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

[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。

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.

SD3.5 Large PiD Direct 4K Image Generation Workflow

Watch the full video first if you want to understand how this SD3.5 Large + PiD workflow works in practice. The video shows how a 1024 base image can be generated with SD3.5 Large, how the PiD enhancement stage pushes it toward 4K output, and how to launch the workflow online without building a local ComfyUI environment.This ComfyUI workflow is designed for SD3.5 Large direct 4K image generation using PiD as the high-resolution enhancement stage. Its main purpose is to create a clean SD3.5 Large base image first, capture the correct latent state during sampling, and then send that latent into a PiD 2K-to-4K refinement pipeline. The result is a more detailed and more production-oriented output than a simple native image generation pass.The workflow is built around sd3.5_large_fp8_scaled.safetensors as the main checkpoint. It uses a 1024×1024 EmptySD3LatentImage as the base canvas, CLIPTextEncode for positive and negative conditioning, PiDTextPrompt for unified prompt and caption handling, PiDKSamplerCapture for SD3 latent generation and PiD latent capture, PiDPrepare for preparing the captured latent, PiDSample for the PiD refinement pass, PiDFinalize for final image conversion, VAEDecode for native baseline output, and SaveImage for both comparison outputs.The first lane is the native SD3.5 Large generation route. The prompt is written into PiDTextPrompt, then sent into the positive prompt encoder and also used as the caption for PiD preparation. The negative prompt suppresses common image problems such as deformation, blur, low resolution, bad anatomy, extra fingers, JPEG artifacts, and watermarks. This makes the workflow suitable for both artistic generation and cleaner comparison testing.The key generation node is PiDKSamplerCapture. Unlike a normal KSampler, this node produces the final native latent while also capturing a PiD-ready latent at a selected capture step. In this workflow, the sampling setup uses 25 steps, CFG 4.4, Euler sampler, sgm_uniform scheduler, denoise 1.0, and capture_step 23. The captured PiD sigma is automatically sent into PiDPrepare, which helps the PiD stage receive the correct sampling-state information instead of relying on manual sigma guessing.After capture, PiDPrepare is configured with the SD3 backbone, 2kto4k PiD checkpoint type, scale 4, auto download enabled, and cleanup after prepare enabled. PiDSample then performs the enhancement pass with 4 PiD steps, CFG scale 1.0, fixed seed, aggressive cleanup, and sequential block offload. PiDFinalize converts the sampled PiD output into the final enhanced image.Compared with ordinary SD3.5 Large generation, this workflow is not just an external upscale. It captures an intermediate latent from the original generation process and uses PiD to rebuild high-resolution detail in a more integrated way. Compared with a standard upscaler, it is more closely connected to the model’s own latent structure and prompt caption, making it better for typography posters, detailed concept art, premium illustrations, product visuals, and high-resolution creative publishing.Main features:SD3.5 Large PiD direct 4K workflowSD3.5 Large fp8 scaled checkpoint route1024×1024 base latent generationPositive and negative prompt conditioningPiDTextPrompt unified prompt and caption inputPiDKSamplerCapture intermediate latent capture25-step Euler / sgm_uniform sampling setupCapture step 23 for PiD preparationAutomatic PiD sigma transferPiDPrepare with SD3 backbonePiD 2K-to-4K enhancement routePiDSample with 4 PiD stepsSequential block offload and aggressive cleanupNative baseline and enhanced output comparisonSuggested workflow:Start with a clear visual prompt that defines the subject, typography if needed, composition, lighting, color palette, texture, and final use case. Keep the base resolution at 1024×1024 for the first test. Run the native SD3.5 Large lane first and check whether the layout, text, and major structure are correct. If the native image is weak, fix the prompt before entering PiD. Once the base image is stable, let PiDKSamplerCapture send the captured latent and sigma into PiDPrepare. Then run PiDSample and compare the native baseline with the PiD enhanced output. If the final output becomes too heavy or unstable, keep PiD steps at 4 and rely on cleanup and offload settings rather than forcing more aggressive enhancement.⚙️ RunningHub WorkflowTry the workflow online right now — no installation required.👉 Workflow: https://www.runninghub.ai/post/2059961785033256961?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/BV1tsVH6kEBJ/☕ 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/post/2059961785033256961?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/BV1tsVH6kEBJ/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。

Wan 2.2 S2V Long Video Workflow Tutorial! Extend Wan 2.2 S2V Videos Indefinitely Workflow

ComfyUI inpaint workflow | Updated for anima

Anima workflow26/05/2026 - v0.9 initial releaseConverted XL workflow to work with anima. It works pretty much same as XL one, guide is relevant on that part.Inpaint workflow V2GUIDE FOR V2 WORKFLOW IS LOCATED HERE06/12/2025-Added ability to control mask opacity.-Changed sampler to prevent problems with generation.-Adjusted guide.04/12/2025-Added ability to do colormatch. Changing colormatch setting to 1 will try to match the color of the image.This is good if using VAE that changes color between encode/decode cycle or using different lora/model.Older:-Added differential diffusion-Cleaned the workflow-Created guide which can be found HERE-This should work with 1.5 too, did not test.Inpaint workflow XL V1.1Due to request updated to work with XL. It is somewhat barebones compared to 1.5. Does not have segmentation or controlnet models currently.I have a bit outdated comfyui, let me know if it is throwing some errors.

Clarity TagFlow

Clarity TagFlowThe intelligent, local-first image tagging and AI dataset curation powerhouse.original source code hereClarity TagFlow is a modern desktop application designed to streamline the process of tagging images for Machine Learning datasets, Stable Diffusion training, and digital asset management. Built with a strict focus on privacy, speed, and optimization, it runs state-of-the-art AI models entirely on your local machine.🚀 Project Status: ~85% Complete! All major bugs have been squashed, and video playback is now fully operational. We are currently optimizing performance before the next massive architectural leap.💬 We Need Your Feedback! Do you miss an old feature that was removed? Is there something you don't like, or an improvement you're dying to see? Leave a comment and let us know!🛠️ System RequirementsOS: Windows / LinuxRuntime: Java 21 (Note: Moving to native binaries soon!)AI Acceleration: Microsoft Visual C++ Redistributable (for ONNX Runtime on Windows)Tested Hardware: Fully tested and verified smooth on laptop RTX 5080 configurations.🌟 Key Features🤖 Local AI PowerhousePrivacy First: No images or data are ever uploaded to the cloud. All processing happens 100% offline.Multi-Model Support: Seamlessly switch between JoyTag (SOTA) and various WD14 tagging models (ConvNext, SwinV2, Eva02) to get the most accurate results for your specific content.Smart Thresholding: Fine-tune confidence thresholds to control exactly how strict the AI is when applying tags.⚡ Accelerated WorkflowBatch Processing: Auto-tag entire folders of images in minutes. Choose to Append new tags or Overwrite existing ones completely.Smart Autocomplete: Type faster with a context-aware autocomplete system that learns from your current dataset and standard tag libraries.Sidecar Compatibility: Reads and writes standard .txt sidecar files, ensuring seamless compatibility with Kohya_ss, OneTrainer, and other major training tools.🎨 Modern ExperienceSleek Dark UI: A refined, eye-friendly interface designed for long, focused dataset curation sessions.Visual Feedback: Features a "breathing" AI status indicator to let you know exactly when the system is processing.Drag & Drop: Easily reorder tags or drag new images directly into your active workflow.🛡️ Control & SafetyGlobal Blacklist: Automatically filter out unwanted tags (e.g., sensitive terms or specific formatting errors) across your entire dataset.Session Memory: Newly added AI tags are highlighted in Cyan, making it incredibly easy to review changes before committing to a save.🚀 What's New & ImprovedFixed Video Playback: The underlying issues causing intermittent video playback failures have been completely resolved.Total Bug Purge: Fixed all known memory leaks and stability quirks. The gallery navigation bug (where deleting an image reset you to page one) remains permanently fixed.Smart Booru Downloader: Automatically fetches associated tags when downloading from Booru sites, establishing an immediate 80-90% accuracy baseline.Seamless Generation Setup: The generation panel auto-starts in the background. No more manual configuration via .bat files.In-App Image Generation: Direct support for generating images right inside your tagging workflow.⚠️ Current Known Issues & Immediate FixesGemma 4 Support: We are aware of the current issues regarding Gemma 4 integration. A dedicated compatibility fix is actively being worked on and will be released shortly.🔮 The Grand Blueprint: Moving to Rust & BeyondWe are officially planning a massive architectural evolution, moving away from Java and rewriting the application core in Rust. This transition is all about native optimization, blistering speed, and breaking down dependencies.Here is what the Rust-powered future of Clarity TagFlow looks like:Native Cross-OS Performance: Moving to Rust unlocks a highly optimized, beautifully integrated native UI with seamless compatibility across Windows and Linux.Built-in Model & LoRA Training: Train your models and LoRAs directly within the app. Features a live visual training preview so you can monitor progress in real-time and know your model is turning out perfectly.All-in-One Image & Video Generation: Full, native image and video generation support built directly into the UI. Say goodbye to configuring complex, bloated ComfyUI workflows.Zero-Dependency Local LLM: We are eliminating the need for external tools like Ollama or LM Studio. The local LLM engine will be completely embedded out of the box.In-App Civitai Integration: Browse, search, and download Civitai resources directly inside the application—no more manual downloads or directory headaches.Interactive VR Anime Companions: Introducing a built-in VR anime character for interactive roleplaying. The AI will dynamically control the avatar, express distinct emotions, and react in real-time.External Engine Integration: Building the foundation for the embedded LLM to broadcast and connect with external 3D applications and game engines.

Microsoft Lens

Microsoft LensLens is a 3.8B-parameter foundational text-to-image model designed for efficient training and fast high-resolution generation. It combines dense-caption pre-training, mixed-resolution learning, GPT-OSS multi-layer text features, and the FLUX.2 semantic VAE to reach competitive quality with substantially less training compute than larger T2I models.Diffusion Modelbf16https://huggingface.co/Comfy-Org/Lens/tree/main/diffusion_modelsfp8https://huggingface.co/dummy9996/lens-mxfp8-comfyui/tree/mainEncoderhttps://huggingface.co/Comfy-Org/Lens/tree/main/text_encodersVaehttps://huggingface.co/Comfy-Org/Lens/tree/main/vaerequires PR pull:(run these commands in your "comfyui" folder where models, custom nodes, and output folders reside, NOT ROOT)git fetch origin pull/14077/head:pr-14077git checkout pr-14077once the model is native to comfy, you can just update your comfyui to the latest branch instead of utilizing the PR pull. for now this is what we have. probably today will be the day it gets approved into the master branch.TURBO MODEL REQUIRES 4 STEPS. DEV MODEL REQUIRES 20 STEPS. workflow is currently set to Dev model settings.Original Contributor notes:The model is released for research purposes only and is not intended for product or service deployment. Responsible AI considerations were incorporated throughout the development process, including data selection, model training, and evaluation. The training data includes a combination of public, licensed, and internal datasets that were processed to remove clearly identifiable personal information and reduce harmful content where possible. However, as the data is largely sourced from web-scale collections, it may contain biases or uneven representation. As a result, the model may generate outputs that are inaccurate, biased, or inappropriate under certain prompts, including content that could be misleading or raise copyright or IP-related concerns. Given these limitations, the model should be used in controlled research settings, with appropriate human oversight. Downstream users are responsible for applying additional safeguards, such as content moderation, validation, and compliance checks, before using the model in broader applications.

EZ_Txt2img

I was tired of looking up pixel sizes and aspect ratios for my image generating so I set out to make this easy workflow that has basic aspect ratios and resolution selector switches to solve this problem.I hope this is useful to others because trying to memorize pixels and ratio inputs or searching for ones online consumed too much time.select which ever checkpoint you like to use, add your loras, type in your prompts, select batch size and you're offV3 update: if you're just generating images keep the "highres pass" off when you find the image you want that needs alittle extra tlc click that (use last queued seed) button, turn on the "high res pass" and hit run again. i normally do 20 steps and .2 denoise sometimes when an image needs alittle more refinement ill turn it up to 30 steps and .25 denoise

Simple Reactor Video Faceswap

Fast video faceswapping, and possibly a base for more advanced workflows.On my Ryzen 4600G,16G RAM, RTX 4060 8GB:A 5 second, 608x1080 video @ 30fps, takes about 5 minutes. Versions used:ComfyUI Desktop 0.21.1Reactor 0.7.0-a2May work on other versions,but not guaranteed.Also, could break if something changes in ComfyUI or Reactor.You can always try to extend it with other nodes to generate faces, upscale,etc.

Full-Auto AI Video Translator: Multi-Speaker & BGM Separation

🚀 Run this Workflow for FREE on Runninghub: https://www.runninghub.ai/post/2056650178861559810/?inviteCode=rh-v1497(🎁 Tip: New users get 1000 points via the link above + 100 daily login points!)🎥 Watch the Full Video Tutorial (Beginner to Pro):🌟 OverviewWant a complete hands-free solution to translate foreign videos? this workflow allows you to upload a raw audio or video file and automatically handles transcribing, translating, voice cloning, and audio splicing in one single run.It is perfect for bulk translating content or quickly processing dialogue with multiple distinct speakers.🚀 Key Features & ArchitectureAll-in-One Processing: Simply upload your file, select your options, and let it cook. It splits the workflow into transcription, LLM translation (via Gemini API), and audio generation.80+ Languages Supported: Powered by FishAudio 2 for high-fidelity cross-lingual voice synthesis.BGM & Dialogue Separation: Its true secret weapon is keeping the original background music/audio track intact while automatically cloning and placing the translated dialogue.2-Speaker Detection: Capable of directly processing conversational audio with 2 speakers while attempting to match individual voice profiles.💬 Join the Community👉 [https://discord.gg/NmBhk9Vk8b]

Wan 2.2 S2V in ComfyUI: Talking Images (GGUF Model) Workflow

Local Prompt Reader (LPR) — Standalone Metadata Viewer

Local Prompt Reader (LPR) — Standalone AI Image Metadata Viewer (WebUI & ComfyUI)Important NoticeSome antivirus software may mistakenly flag the executable as suspicious due to the packaging method used. This is a false positive. The application works fully offline and does not require an internet connection.👉 Get the Full Version on Gumroad"Your prompts, readable in seconds."Instantly check the prompts and settings embedded in your AI-generated images — all on your PC, completely offline.🎁 This Free Edition (Lite Version)The file uploaded here is the Free Lite Version.Limitation: Allows up to 5 image parses total (PNG/JPG both count).After reaching the limit: New image parsing will pause, but you can still view your saved history unrestricted.Privacy-First: Runs 100% offline. No internet, no API, no data tracking.🚀 Get the Full Version (Unlimited Parsing)If you want to remove the limit and parse all your images without restrictions, get the Full Version ($5.00 USD) on Gumroad:👉 Get the Full Version on Gumroad💡 Key FeaturesInstant "Seconds-Fast" Checking Skip the boot wait. Just drag and drop your image to view settings instantly.WebUI & ComfyUI Dual Compatibility Parses complex ComfyUI workflows (linked nodes, wildcards) and WebUI settings (multi-group ADetailer, Hires Fix) into a clean, readable layout. Note: If an automatic parse fails on specific ComfyUI custom nodes, the dedicated "Raw" tab displays the raw metadata text so you never lose information.100-Item History with Thumbnail Cache Even if you delete or move the original images to save disk space, the metadata and 200px thumbnails remain safe inside LPR.Privacy-First (100% Offline) Runs completely offline. No internet connection, no API calls, and no data tracking. Your prompts stay private on your PC.No Python Required Standalone Windows application (.exe). Just double-click to launch.Multi-language & Theme UI Instantly switch between English and Japanese UI, or toggle between Light and Dark themes — all from the menu.💻 Specifications & RequirementsOS: Windows 10 / 11 only (macOS is not supported)File Size: ~22.5 MBLicense: Personal and Commercial Use. You may use the images you view and the prompts you retrieve with LPR for any purpose, including commercial projects. Redistribution, modification, and resale of the application itself are prohibited.⚠️ NoticeDue to PyInstaller packaging, Windows Defender may occasionally flag a false positive virus warning upon launch. LPR runs completely offline and contains no malware. Please test with VirusTotal if you have any safety concerns.As this is a digital product, all sales are final. Refunds and individual technical support are not provided. Please make sure to test your system compatibility with the free Lite version before making a purchase.

IMG to TXT Simple workflow

✨ TOOL — Image to text — Simple WorkflowA clean, all-in-one Image to text workflow built entirely with the UmeAiRT Toolkit for ComfyUI.Only 3 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-text generationAutomatic download of models📦 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.

Sony Woosh - Longer videos

Workflow OverviewThis workflow is designed to generate sound effects, ambient audio, and scene-based audio for videos using the Sony Woosh video-to-audio model inside ComfyUI.Since Sony Woosh only supports short video inputs of up to 8 seconds, this workflow automatically divides longer videos into smaller sections called segments. Each segment is processed individually and later merged into a complete audio track synchronized with the original video.The workflow supports both automatic and fully manual generation modes:Automatic Mode is designed for simplicity and speed. The workflow automatically analyzes the video and generates prompts for each segment with minimal user interaction.Manual Mode gives full creative control over every segment, allowing you to define custom prompts, segment lengths, seeds, and audio behavior for dynamic or complex videos.The workflow also includes several utility systems to simplify the generation process:Automatic prompt generation using Qwen3.5 vision analysisFrame visualization tools for precise segment timingAudio preview nodes for testing segments before final renderingSource audio mixing optionsOptional dialog suppression using SAM3 maskingThis workflow is especially useful for:Silent videosAI-generated videosVideos requiring custom sound designVideos with no usable original audioThe final result is a fully rendered video containing the generated Sony Woosh audio, optionally mixed with the original source audio depending on the selected mode.COMFYUI SECURITY ERROR FIXIf you hit a security level error while trying to install the Woosh custom node from ComfyUI manager:You need to temporarily change the security level in your config.ini file.If you are using the portable version, the file is located at:ComfyUI/user/__manager/config.iniChange the value to:security_level = weakIMPORTANT:Do NOT forget to restore it back to its original value, you should restore it afterward for safety reasons.Perform a hard restart of ComfyUI (completely stop it, then start it again).Install the custom node using ComfyUI manager and double-check that it is the official one. The link should point to:https://github.com/Saganaki22/ComfyUI-WooshRestart ComfyUI and check if the node works properly.Once everything is working properly, restore your original security level in the config.ini file and restart ComfyUI one final time.Detailed instructions are contained in the workflow itself:Red nodes are instructions and useful notes.Yellow nodes are configurable elements you can adjust to your needs.

NovelAI on Comfy

Workflow for the Novelai system I developed. It requires a subscription or anlas on account to use.It requires the custom nodes I created. > shirosaki33/NovelAI-API-Comfy: can use comfyui to generate novelai images using api with token key.The nodes that were available were very outdated or had many problems.The new system has been reworked with everything the API supports. It's now an easy way to configure the API, and it's possible to use it directly within in the workflow.for custom workflow >https://github.com/shirosaki33/shirotools

See-through| Auto-Split Anime to PSD Layers (Live2D / VTuber Prep)

🔗 Run this Workflow for FREE on Runninghub:https://www.runninghub.ai/post/2054381772124762113/?inviteCode=rh-v1497(🎁 Tip: New users get 1000 points via the link above + 100 daily login points!) 👉 Join our Discord for Prompts & Help: [https://discord.gg/NmBhk9Vk8b]Full tutorial in youtube:🔗Project URL https://github.com/shitagaki-lab/see-through 🔗Terry's node URL: https://github.com/jtydhr88/ComfyUI-See-throughAre you tired of spending hours manually cutting out anime characters in Photoshop? This ComfyUI workflow utilizes the ComfyUI-See-through plugin to automatically split a flat 2D anime character image into up to 24 independent, transparent layers!It doesn't just cut out the background—it intelligently separates front hair, back hair, face, eyes, clothes, and accessories, calculating the depth order and saving everything directly as a ready-to-use PSD file.This is the ultimate prep-tool for Live2D riggers, VTubers, and 2D-to-3D parallax animators.

Flat Image -> VR Workflow

This is a very simple and fast workflow which takes any folder of images, and uses Depth Anywhere v2 to turn them into stereoscopic 3D images that can be viewed in a VR headset.

LTX 2.3 Sulphur image to video workflow in ComfyUI | Cinematic Motion Creator

Turns still images into cinematic motion scenes fast and smooth.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 helps you turn a still image into cinematic motion sequences with refined camera control, expressive character movement, and realistic micro-expressions. It provides creators with full storytelling precision, enabling mood-rich transitions and dynamic visual continuity. Built for visual designers and animators, it ensures publish-ready, high-quality short videos. The workflow balances automation and artistic control for professional visual storytelling. Perfect for producing cinematic image-to-video shots efficiently.NotesLTX 2.3 Sulphur image to video workflow in ComfyUI | Cinematic Motion Creator — see RunComfy page for the latest node requirements.

ChatterBox TTS ComfyUI Workflow | Multilingual Voice & Dialog

Build lifelike voices, fast and easy, across any language or style.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 voice synthesis workflow, you can design natural speech, multilingual dialogs, and cloned voices in one efficient setup. The audio node suite offers both standard and Turbo TTS generation with reference-guided voice control. You can test and compare speech modes fast, making it ideal for prototyping narration, virtual character voices, or AI performance projects. Every setting is optimized to give creators flexibility in tone, accent, and pacing. Great for voice design experiments and creative storytelling through sound.NotesChatterBox TTS ComfyUI Workflow | Multilingual Voice & Dialog — see RunComfy page for the latest node requirements.

LTX 2.3 Movie Builder Workflow in ComfyUI | Multi-Scene AI Filmmaking

Turn prompts into full cinematic stories with total creative control.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 the LTX 2.3 Movie Builder system, you can build cohesive AI-driven films with multi-scene continuity and cinematic quality. It streamlines scene planning and prompt sequencing while maintaining character and motion consistency. You can create text-to-video, image-to-video, and audio-based narratives without complex manual setups. The system ensures smooth camera transitions and realistic pacing for longer film projects. Ideal for creators, it brings speed, structure, and creative control to your AI filmmaking process.NotesLTX 2.3 Movie Builder Workflow in ComfyUI | Multi-Scene AI Filmmaking — see RunComfy page for the latest node requirements.

Image to Prompt & Detection, Direct Chat, Variations, Timeline, Lyrics

ComfyUI WorkflowRequires: ComfyUI_Eclipse 3.5.xits a very basic workflow that uses nodes from Eclipse which supports 8 Backends:transformers, gguf (llama-cpp-python), ollama (docker), vllm (docker), sglang (docker), llama.cpp (docker), wd14 (onnx), yoloImage Description (VLM / WD14) + create variations or timeline prompts (e.g. wan)Text Input (LLM) + create variations or timeline prompts (e.g. wan)Detection (Face, Eyes, Hands, and other areas ;) using Florence2 and Yolo (qwen detections are usally meh... but works very good with huihui qwen 3.5 9b claude 4.6try claude for image to prompt descriptions / detection (also very good):ollama: huihui_ai/qwen3.5-abliterated:9b-Claude⚠️ Important Security Notice — Running LLMs Locally with ComfyUI

Rebels LongCat Image Edit + TURBO

VERSION 2TURBO MODEL that generates in 8 STEPS!UPDATE COMFY TO THE LATEST UPDATE!!!!files:TURBO modelhttps://huggingface.co/Comfy-Org/LongCat-Image/blob/main/split_files/diffusion_models/longcat_image_edit_turbo_bf16.safetensorsGGUF TURBO Modelhttps://huggingface.co/vantagewithai/LongCat-Image-Edit-Turbo-GGUF/tree/main BF16 base edit Modelhttps://huggingface.co/Comfy-Org/LongCat-Image/tree/main/split_files/diffusion_modelsGGUF base edit modelhttps://huggingface.co/vantagewithai/LongCat-Image-Edit-GGUF/tree/mainText Encoderhttps://huggingface.co/Comfy-Org/Qwen-Image_ComfyUI/blob/main/split_files/text_encoders/qwen_2.5_vl_7b_fp8_scaled.safetensorsVAEhttps://huggingface.co/Comfy-Org/z_image_turbo/blob/main/split_files/vae/ae.safetensors

Frame Interpolation workflow - smoother video playback

Adds frames to video, increasing the frames per second (fps), for smoother playback.Audio from the original can be piped into the final video or extracted and saved separately for further post processing.Auto calculates output frame_rate based on original frame rate and frame multiplier.

LTX 2.3 Outpainting in ComfyUI | Spatial Frame Expansion Workflow

Expand video scenes smoothly with consistent motion and perspective.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 advanced workflow, you can easily expand video frames beyond their original bounds while keeping motion and lighting continuity intact. It helps extend scenes horizontally or vertically, perfect for adjusting aspect ratios or creating panoramic effects. This process ensures visual harmony and smooth transitions across extended areas. The tool enhances creative control for cinematic storytelling. Ideal for designers and video creators seeking fluid, high-quality frame extensions.NotesLTX 2.3 Outpainting in ComfyUI | Spatial Frame Expansion Workflow — see RunComfy page for the latest node requirements.

AI Music Made EASY, FAST with Great Quality: Ace Step V1.5 AIO ComfyUI Tutorial (Beginner Friendly)

Rebels SenseNova-U1

SenseNova-U1 is SenseTime's open-source unified multimodal model running natively in ComfyUI through smthemex's custom node pack. One model, five modes, no VAE, no separate text encoder — the entire pipeline collapses into a single GGUF. 8B parameters of MoT (Mixture-of-Transformers) architecture handling text-to-image, image editing, VQA, and interleaved generation from the same checkpoint.USE 'EDIT' IMG MODE WITH REFERENCE FOR EDITING.USE 'EDIT' IMG MODE WITH NO REFERENCE FOR TEXT TO IMAGE.Two versions are available. The 8-step Turbo (distill) is the fast option — runs at 8 steps with cfg 1.0, lower VRAM, quick iteration. The Full Base Model is the quality option — 50 steps with cfg 4.0, more prompt adherence headroom. Do not mix these settings up. Turbo with cfg 4 will blow out, base with cfg 1 will look muddy. Match the settings to the checkpoint you downloaded.GGUFs come in multiple quant sizes. Q6_K if you have headroom, Q8_0 for max fidelity.Installation is straightforward. Clone the custom node into your ComfyUI custom_nodes folder:git clone https://github.com/smthemex/ComfyUI_SenseNova_U1Then install requirements using the portable embedded python from your ComfyUI root:python_embeded\python.exe -m pip install -r ComfyUI\custom_nodes\ComfyUI_SenseNova_U1\requirements.txtDrop the downloaded GGUF into ComfyUI/models/diffusion_models/ and restart ComfyUI. The SenseNova_SM_Model and SenseNova_SM_Sampler nodes will be available.Workflow is three nodes: Load Image (optional) → SenseNova_SM_Model → SenseNova_SM_Sampler → Save Image. In the Model node, set diffusion_models to none, pick your GGUF, leave attn_backend on auto. In the Sampler node, set img_mode to the task you want, then dial in steps and cfg per the version you're running.Settings cheat sheet: Turbo: cfg 1.0, steps 8 Base: cfg 4.0, steps 50 img_cfg 1.0, timestep_shift 3.0, do_sample onVRAM tip: prefetch_count 1 for low-VRAM cards (less memory, slightly slower). Only set prefetch_count to 0 if you have 32 GB or more VRAM.Links:Custom Node — https://github.com/smthemex/ComfyUI_SenseNova_U1GGUF Files (Turbo + Base) — https://huggingface.co/smthem/SenseNova-U1-8B-MoT-Merger-gguf/tree/mainCredits: Model by SenseTime (https://github.com/OpenSenseNova/SenseNova-U1), ComfyUI integration by smthemex, GGUF quantization by smthem on HuggingFace. License: Apache 2.0.https://youtu.be/SYJhzEdN1S0?si=2kRlRp1e7R4tT5bC

Ultimate Music Maker

Based on Ace 1.5 Turbo XLThis workflow is built to generate 8 Songs at once with the following options:- Single Lyrics/Keyscale/BPM/Duration/Song Name/LLM/Seed input- 2 Musical Style input- The output is 4 song using the 1st musical style with 2/4, 3/4, 4/4, 6/4 Time signature and 4 other songs using the 2nd musical style with 2/4, 3/4, 4/4, 6/4 Time signature.This helps generate 8 song with the same Lyrics/Keyscale/BPM/Duration/Song Name/LLM/Seed while having 2 different style variations with all available time signatures.Made for me by me. If you enjoy it makes me even happier!Samples from the default prompts/musical styles included:https://huggingface.co/WanApp/UltimateMusicMaker/blob/main/Song_G1_2-4_00001_.flachttps://huggingface.co/WanApp/UltimateMusicMaker/blob/main/Song_G1_3-4_00001_.flachttps://huggingface.co/WanApp/UltimateMusicMaker/blob/main/Song_G1_4-4_00001_.flachttps://huggingface.co/WanApp/UltimateMusicMaker/blob/main/Song_G1_6-4_00001_.flachttps://huggingface.co/WanApp/UltimateMusicMaker/blob/main/Song_G2_2-4_00001_.flachttps://huggingface.co/WanApp/UltimateMusicMaker/blob/main/Song_G2_3-4_00001_.flachttps://huggingface.co/WanApp/UltimateMusicMaker/blob/main/Song_G2_4-4_00001_.flachttps://huggingface.co/WanApp/UltimateMusicMaker/blob/main/Song_G2_6-4_00001_.flac

Ace Step 1.5 XL Turbo and SFT - TEXT to AUDIO model with Ollama

The Workflow was setup to have a clean "GUI" showing only parameters that matter, so you might want to toggle off Link visibility, like in above screenshot.V1.7 Ace Step 1.5. Turbo and SFT normal and XL model with Ollama. Text to Audio/Song (examples below).replaced the "save Mp3" nodes to allow ID3 tags to include data like artist name, bpm, genre, lyrics, etc.requires custom node: https://github.com/mattjohnpowell/comfyui-audio-expoadded a feature to save all relevant data (tags, lyrics, etc.) as a separate text (.txt) fileaudio render processing remains unchanged to previous versionKey features:Can use any Song, Artist as reference or any other description to generate tags and lyrics.Will output up to 4 songs, each by Turbo, SFT, Turbo XL and SFT XL model (or any merge or Base model).Keyscales, bpm and song duration can be randomized.able to use dynamic prompts.creates suitable songtitle and filenames with Ollama.Lora Loader included,V1.6 Ace Step 1.5. Turbo and SFT normal and XL model with Ollama.updated the settings for XL models and added a 3rd System Prompt for tags to chose, with more descriptive song descriptions.1.5 XL SFT pipeline now has an "Adaptive Projected Guidance" node and negative prompt.** See below some tips which model and settings to start with.V1.5 Ace Step 1.5. Turbo and SFT normal and XL model with Ollama:setup to create up to 4 tracks in a run, 2x Ace1.5 and 2x Ace1.5 XL, each with Turbo and SFT model, to compare (can be individually switched on/off)VAE changed to tiled Audio VAE decode, uses less Vram.V1.2 Ace Step 1.5. Turbo and SFT model with Ollama Text to Audio/Songsmall update to GUI, system prompts and SFT sampler "engine"V1.0 Ace Step 1.5. Turbo and SFT model with Ollama Text to Audio/SongAce Step uses TAGS and LYRICS to create a song. These can be generated by Ollama or by own prompts.Avoid sage attention in your comfyui starting parameters, avoid --lowvram setting, as this might force Texencoder to run very slow on CPU instead of GPU.Download Files:Ace Step 1.5 TURBO model: https://huggingface.co/Comfy-Org/ace_step_1.5_ComfyUI_files/tree/main/split_files/diffusion_modelsAce Step 1.5 SFT model: https://huggingface.co/ACE-Step/acestep-v15-sft/tree/main (download model.safetensor and rename it)Ace Step 1.5 XL Models: https://huggingface.co/Comfy-Org/ace_step_1.5_ComfyUI_files/tree/main/split_files/diffusion_modelsAce Step 1.5 XL Model merges (i.e. merge of turbo with SFT): https://huggingface.co/Aryanne/acestep-v15-test-merges/tree/main/xlTextencoder: https://huggingface.co/Comfy-Org/ace_step_1.5_ComfyUI_files/tree/main/split_files/text_encoders (Qwen_0.6b and Qwen_4b required, 1.7b is a smaller alternative to 4b)VAE: https://huggingface.co/Comfy-Org/ace_step_1.5_ComfyUI_files/tree/main/split_files/vaealternative VAE: https://huggingface.co/megagrump/Ace-Step-1.5-ScragVAE-ComfyUIOllama Models, required for tags, lyrics and songtitle, you can choose 1,2 or 3 different models, tags and lyrics might need a bigger model >7b, songtitle can use a smaller model:https://ollama.com/mirage335/Llama-3-NeuralDaredevil-8B-abliterated-virtuoso (allround model, fast, usable for tags, lyrics and songtitle, recommended)https://ollama.com/huihui_ai/qwen3-vl-abliterated (for tags and lyrics, able to use thinking)https://ollama.com/artifish/llama3.2-uncensored (small and fast for songtitle and tags)Alternative Turbo Models and merges (normal, non XL) :Turbo continuous: https://huggingface.co/ACE-Step/acestep-v15-turbo-continuous/tree/mainTurbo-Shift1: https://huggingface.co/ACE-Step/acestep-v15-turbo-shift1/tree/mainTurbo-Shift3: https://huggingface.co/ACE-Step/acestep-v15-turbo-shift3/tree/mainMerges of SFT, Turbo and Base model: https://huggingface.co/Aryanne/acestep-v15-test-merges/tree/mainGGUF Models "normal" and XL: https://huggingface.co/Serveurperso/ACE-Step-1.5-GGUF/tree/mainWhich models to start with ?My current choice for normal model: Turbo-SFT merge_ta_0.5 & Turbo-Shift1, using these settings:Turbo-SFT_merge model with sampler: er_sde, scheduler: beta57 (or beta), 22 stepsTurbo-Shift1 model with sampler euler, scheduler: normal, 138 stepsXL Model settings:XL Turbo-SFT merge model: sampler: er_sde, scheduler: sgm_uniform, 40 stepsalternative: sampler: res_s2, scheduler beta57 (requires RES4LYF custom nodes)XL SFT model: sampler: euler (or res_2s), scheduler: normal, 46 steps, CFG = 7.3, Adaptive Projected Guidance: eta = 1.05, norm_thresh= 1.3, momentum=0.0. Increase norm_thresh as the main parameter. These settings deliver "stabil" output for XL SFT,Base and their merges. The merges sound way better, pure SFT or Base introduce a lot of noise. I bypassed ModelSamplingAuraflow (see node next to model loader node). I think the base-turbo XL model merge fits well in that slot.Disable "generate_audio_codes" in "TextEncodeAceStep" node to get different results, it works very well for many genres and reduces process time.Ollama Model: Llama-3-NeuralDaredevil-8b-abliteratedMore infos on models see thread below in discussion.Save Location:📂 ComfyUI/├── 📂 models/│ ├── 📂 diffusion_models/│ │ └── acestep_v1.5_turbo.safetensors│ ├── 📂 text_encoders/│ │ ├── qwen_0.6b_ace15.safetensors│ │ └── qwen_4b_ace15.safetensors (or 1.7b)│ └── 📂 vae/│ └── ace_1.5_vae.safetensorsCustom Nodes used:https://github.com/rgthree/rgthree-comfyhttps://github.com/yolain/ComfyUI-Easy-Usehttps://github.com/stavsap/comfyui-ollamahttps://github.com/KoinnAI/ComfyUI-DynPromptSimplifiedhttps://github.com/mattjohnpowell/comfyui-audio-expo (as of V1.7)optional (use Beta57 scheduler for a bit more punch, requires RES4LYF): https://github.com/ClownsharkBatwing/RES4LYFExamples various styles:https://soundcloud.com/tele-joe/heartaches-vicioushttps://soundcloud.com/tele-joe/ride-the-concrete-tide_westhttps://soundcloud.com/tele-joe/wildfirehttps://soundcloud.com/tele-joe/burning-echoes-of-the-fallenhttps://soundcloud.com/tele-joe/electric-voodoohttps://soundcloud.com/tele-joe/firestorms_unleashed_turbo_000https://soundcloud.com/tele-joe/westsidevibesforever_funkhiphohttps://soundcloud.com/tele-joe/fractured-reality_hardcorehttps://soundcloud.com/tele-joe/revelation-home_glitchhttps://soundcloud.com/tele-joe/lonelyroadsoul_turbo_00001https://soundcloud.com/tele-joe/hangoverhttps://soundcloud.com/tele-joe/sft_secret-paradisehttps://soundcloud.com/tele-joe/cosmicdreamscapesynthpop_turbohttps://soundcloud.com/tele-joe/mindspin-synthpop_turbo_00001https://soundcloud.com/tele-joe/wildreckoning_thrashmetal_turbhttps://soundcloud.com/tele-joe/freeflight_metalcore_sft_00001Ollama help:Install Ollama from https://ollama.com/download a model: Go to a model page, chose a model , then hit the copy button, i.e. https://ollama.com/mirage335/Llama-3-NeuralDaredevil-8B-abliterated-virtuosoopen terminal and paste the model name, i.e.: ollama run huihui_ai/qwen3-vl-abliteratedmodel will be downloaded and can be selected in green comfy node "Ollama Connectivity". Hit "Reconnect" to refresh.

ComfyUI-3R3BOS-Pack

Please leave a star rating on GitHub if you have the time; it would be a great help. Thank you! ❤️ https://github.com/3R3BOS/ComfyUI-3R3BOS-Pack📦 WHAT IS IT?The ComfyUI 3R3BOS Pack is the essential toolkit designed to bring professional control and visualization to your workflows.Created to simplify complex interactions, this suite focuses on two main goals: "Human-in-the-Loop" efficiency and zero-latency visualization. It currently includes two core tools that will change how you interact with ComfyUI.🧠 TOOL 1: PROMPT SELECTOR — Your Prompt BrainStop using Notepad. Stop losing LoRA trigger words.This node turns ComfyUI into a fully interactive prompt database.DEMOKey Features:Built-in editor (create / rename / delete categories)Store prompts, styles, LoRA trigger wordsColor-coded system (NSFW, styles, etc.)Real-time prompt preview✏️ Live override without breaking your database⚠️ IMPORTANT — DATA SAFETYYour prompts are stored locally in:ComfyUI/custom_nodes/ComfyUI-3R3BOS-Pack/prompts_db.json👉 Always backup this file before:Updating the packReinstalling ComfyUIPulling new versions from GitHub❗ Losing this file = losing your entire prompt library.Result: faster prompting, cleaner workflows, zero chaos.🛑 TOOL 2: BATCH SELECTOR (CONTROL)Filter your generations like a Pro! The Batch Selector replaces the need for complex preview-and-cancel workflows.DEMO• Visual Selection: Pauses execution and lets you pick the best images from a batch.• Native UI: Draws directly on the node canvas (no ugly popups) with a smart responsive grid.• Resource Saving: Only passes the selected images to expensive Upscalers or Refiners.• Instant Cancel: A dedicated button to stop the workflow immediately if the batch is bad.Perfect for maximizing your hit-rate and saving GPU time.⚡ TOOL 3: IMAGE COMPARER SLIDER (VISUALIZATION)The ultimate A/B testing tool for your images. Compare Checkpoints, LoRAs, or "Before/After" Upscaling results with zero latency.DEMO• Dynamic Inputs: Connect up to 20 images; the node creates slots automatically.• Zero-Lag Scrubbing: 60fps performance using client-side caching.• Auto-Compaction: Smart inputs reorganize themselves to keep your graph clean.🎯 TOOL 4: ASPECT RATIO MASTER (ULTIMATE)The definitive resolution calculator. Stop guessing resolutions for modern models like Flux, Wan, or LTX.DEMO• Smart Database (2026): Native support for Hunyuan 2.1 (2K), Wan 2.2, Flux.2, LTX Video, Etc.• Magic Numbers: Automatically calculates exact pixel dimensions for VAE requirements (Mod16, Mod32, Mod64).• Visual Grid: Beautiful real-time preview of your aspect ratio and resolution directly on the node.• Labs Mode 🧪: Unlocks community "Sweet Spot" resolutions for maximum quality (e.g., 1.5MP for Flux).📥 INSTALLATIONOption A: ComfyUI Manager (Recommended)1. Open ComfyUI Manager.2. Search for 3R3BOS Pack.3. Click Install and Restart ComfyUI.###Option B: Manual (Git Clone)Clone the repository into your custom_nodes folder:cd ComfyUI/custom_nodes git clone https://github.com/3R3BOS/ComfyUI-3R3BOS-Pack.git###Option C: Direct Download (.rar)1. Download the .rar file available on this page (see "Download" button).2. Extract the archive.3. Move the ComfyUI-3R3BOS-Pack folder into your ComfyUI/custom_nodes/ directory.4. Restart ComfyUI.🔗 LINKS & SUPPORT• GitHub Repository: https://github.com/3R3BOS/ComfyUI-3R3BOS-Pack• Report Bugs: https://github.com/3R3BOS/ComfyUI-3R3BOS-Pack/issuesUpdate Logv1.0.6NEW: Prompt Selector (major feature)Full prompt database system inside ComfyUILive editing + category systemPremium canvas UIv1.0.5CRITICAL FIX: Solved Batch Selector freezing issue when switching browser tabs during generation.ROBUSTNESS: Implemented "Heartbeat" mechanism to ensure the UI never loses connection with the backend.STABILITY: Added crash protection for corrupt or incomplete images in the preview grid.v1.0.4NEW NODE: Introduced Aspect Ratio Master. The ultimate tool for calculating optimal resolutions for SDXL, Flux, Wan, LTX, Etc.FULL SYNC: Includes "Magic Numbers" for 2026 models (Hunyuan 2.1, Wan 2.2).STABILITY: Enforced strict Mod64/Mod32 constraints to prevent VAE artifacts.BUGFIX: Moved Batch Selector to the 3R3BOS/Image menu category for better organization.v1.0.3BUGFIX: Batch Selector now correctly scales images using 'contain' mode, preventing edge cropping on non-square images (Fixes Issue #3).v1.0.2NEW NODE: Introduced Batch Selector. A powerful replacement for the deprecated Visual Gatekeeper.REMOVED: Visual Gatekeeper (replaced by Batch Selector).UI OVERHAUL: Unified design language across all nodes (Sober/Monochrome aesthetic).PERFORMANCE: Native canvas rendering for Batch Selector eliminates HTML overlay issues.

SBS Convertor for Image and Video

Very simple, but it works quite well. I don't like the original workflow form by comfyui_stereoscopic's authors, so I built my own. Be aware that this won't be as good as reas SBS video, especially when it comes to transparent objects like glass or windows. Photo-realistic rendering works better than semi- or 2D, but it depends on the source. The examples I showed are not really good; I have better ones, but most of them were taken with real photos, and I can't put them here. Anyway, if you have some VR headset or even a cardboard one, you might try it out.

LTX 2.3 Cozy Felt in ComfyUI | Felt Style Text-to-Video Workflow

Turn your ideas into handmade felt-style videos effortlessly.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.OverviewDesigned for creators seeking a handcrafted visual style, this workflow transforms text prompts into cozy felt-inspired animations. You can easily adjust LoRA strength, prompts, and video parameters to maintain full creative control. With its pre-configured graph, audio-video VAE features, and one-click MP4 export, it streamlines text-to-video creation. Perfect for designers exploring tactile aesthetics and soft handcrafted looks. Experience precision, simplicity, and a unique, fabric-like visual texture for your next animation project.NotesLTX 2.3 Cozy Felt in ComfyUI | Felt Style Text-to-Video Workflow — see RunComfy page for the latest node requirements.

LTX 2.3 Prompt Relay in ComfyUI | Image-to-Video Workflow

Turn stills into smooth, story-driven cinematic clips 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 workflow helps you generate cinematic clips where each scene flows naturally into the next. Designed for creators who need more precise control over temporal prompts, it delivers smooth transitions between actions and segments. You can route multiple text prompts across video beats for refined storytelling. The integrated helper refines story cues before generation, making the process efficient and coherent. Ideal for designers seeking higher narrative consistency and time-saving video creation.NotesLTX 2.3 Prompt Relay in ComfyUI | Image-to-Video Workflow — see RunComfy page for the latest node requirements.

Sony Woosh Video to Audio in ComfyUI | Auto Sound Diffusion

Turns any silent video into realistic motion-synced sound.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 revolutionizes how you create synchronized audio from your videos. It automatically generates precise sound effects that follow on-screen motion and scene dynamics. You can transform silent clips into immersive soundscapes without manual Foley work. Ideal for filmmakers, animators, and digital creators, it enhances storytelling through realistic, motion-based sound design. With easy integration and accurate timing, projects feel more alive and cinematic.NotesSony Woosh Video to Audio in ComfyUI | Auto Sound Diffusion — see RunComfy page for the latest node requirements.

LTX 2.3 Edit Anything in ComfyUI | Prompt-Based Video Editing

Edit videos fast. Keep motion clear. Total visual control.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 helps you make targeted edits to AI-generated videos with full creative control. You can modify objects, clean up scenes, or apply visual restyling without regenerating the entire clip. It keeps motion and identity continuity across frames, ensuring natural transitions. Ideal for creators needing flexible visual adjustments, from object swaps to stylistic transformations. Get refined video edits with consistent fidelity and ease.NotesLTX 2.3 Edit Anything in ComfyUI | Prompt-Based Video Editing — see RunComfy page for the latest node requirements.

Ace Step 1.5 Tutorial: Create Fast and Great AI Music in ComfyUI (Beginner Friendly)

Add Copyright to Images

ComfyUI WorkflowRequires ComfyUI_Eclipse 3.3xSimple 2 Nodes Workflow that adds Watermark create with text or from a Photologo.

VoxCPM2 - Multiplayer - Voice Cloning _ Voice Design

Video tutorial:How to use:1. Fill in the dialogue content (in multi-character dialogues, use [spkn] to represent, for example [spk1], [spk2], [spk3])2. Choose whether to translate the speech into a dialect (turn on the switch if you want to translate into a dialect and select the corresponding dialect you want to translate into).3. Selection of Chinese dialects:Value 1 represents Sichuan dialect, value 2 represents Cantonese, value 3 represents Shanghainese, value 4 represents Northeastern Mandarin, value 5 represents Henan dialect, value 6 represents Shaanxi dialect, value 7 represents Shandong dialect, value 8 represents Tianjin dialect, and value 9 represents Minnan dialect.4. Whether to use text normalization (only use if your conversation contains Arabic numerals)5. Upload reference audio for your voice (mainly for voice cloning; those using voice design do not need to upload this, but do not delete the existing audio). If you need to use voice cloning, turn on the corresponding character's switch after uploading your reference audio.6. Role Control Instructions (Control Pitch, Emotion, Rhythm): When generating speech from text, control instructions are filled in according to (core identity, such as gender, age, and role; speech quality and pitch; emotion, rhythm, and scene).Example: A quiet, hoarse, elderly woman with a deep, noticeably grainy voice, accompanied by a slight tremor in her breathing. She speaks slowly in a very low volume, perfectly suited for historical narratives.Character control commands are optional; filling them in will activate them, while leaving them blank will disable them.We recommend trying it out online before downloading; it's completely free!Online experience address:https://www.runninghub.ai/post/2043960563025321986/?inviteCode=rh-v1058

VoxCPM2 - Voice Cloning _ Voice Design - Single Player

Video Tutorial:How to use:1. Upload timbre reference audio (mainly used for voice cloning, you can not upload the sound design using it, but do not delete the existing audio)2. Refer to whether the audio is effective (sound cloning when the switch is turned on, voice design when turned off)3. Fill in the content of the speech4. Control instructions (control tone, emotion, rhythm): When generating speech through text, the control instructions are filled in according to (core identity, such as gender, age and role, voice quality and tone, emotion, rhythm and scene).Example: A quiet, hoarse, older woman with a low and noticeably grainy voice accompanied by slight trembling breath. She emits a slow intonation at a very low volume, making it ideal for historical narratives.5. Whether it is necessary to translate into the dialect version (after turning on the switch, the original dialogue content will be translated into the corresponding dialect version according to the dialect you selected)6. Chinese dialect selection:Value 1 is: Sichuan dialect, value 2 is: Cantonese, value 3 is: Shanghainese, value 4 is: Northeast dialect, value 5 is: Henan dialect, value 6 is: Shaanxi dialect, numerical value 7 is: Shandong dialect, numerical value 8 is: Tianjin dialect, numerical value 9 is: Hokkien dialect7. Whether to use the ultimate clone (after turning on the switch, every sound detail will be faithfully preserved - timbre, rhythm, emotion and style according to the reference audio provided)8. Whether to use text normalization (only use when your dialogue content contains Arabic numerals)We recommend trying it out online before downloading; it's completely free!Online experience address:https://www.runninghub.ai/post/2042886943972794370/?inviteCode=rh-v1058

VoxCPM2 - Voice Cloning _ Voice Design - Single_Multiplayer Integrated Version

Video Tutorial:How to use:1. Mode Selection (Fill in the corresponding area after selecting the mode)2. Upload timbre reference audio (mainly used for voice cloning, you can not upload it if you use sound design, but do not delete the existing audio)3. Refer to whether the audio is effective (sound cloning when the switch is turned on, voice design when it is turned off)4. Fill in the content of the speech5. Control instructions (control tone, emotion, rhythm): When generating speech through text, the control instructions are filled in according to (core identity, such as gender, age and role, voice quality and tone, emotion, rhythm and scene).Example: A quiet, hoarse, older woman with a low and noticeably grainy voice accompanied by slight trembling breath. She emits a slow intonation at a very low volume, making it ideal for historical narratives.6. Whether it is necessary to translate into the dialect version (after turning on the switch, the original dialogue content will be translated into the corresponding dialect version according to the dialect you selected)7. Chinese dialect selection:Value 1 is: Sichuan dialect, value 2 is: Cantonese, value 3 is: Shanghainese, value 4 is: Northeast dialect, value 5 is: Henan dialect, value 6 is: Shaanxi dialect, numerical value 7 is: Shandong dialect, numerical value 8 is: Tianjin dialect, numerical value 9 is: Hokkien dialect8. Whether to use the ultimate clone (after turning on the switch, every sound detail will be faithfully preserved - timbre, rhythm, emotion and style - timbre, rhythm, emotion and style according to the reference audio provided)9. Whether to use text normalization (only use when your dialogue content contains Arabic numerals)We recommend trying it out online before downloading; it's completely free!Online experience address:https://www.runninghub.ai/post/2043612797136801793/?inviteCode=rh-v1058

(600 languages support dialects) OmniVoice long text voice cloning

🎙️ Flawless Long-Form Narration & Essay Dubbing!🚀 Try it out instantly on Runninghub! Run my exact YouTube dubbing setup in the cloud. Click the link below to register and get 1,000 FREE credits to test it out, plus 100 credits every day you log in! 👉 Get Started on Runninghub: https://www.runninghub.ai/post/2046520352058122242/?inviteCode=rh-v1497Stop your TTS from hallucinating or breaking down on long scripts! Fun fact: I used this exact workflow to clone my own voice for the entire voiceover of my YouTube video. Check it out: 📺 Watch the Tutorial Here: ✨ Core Features:Anti-Hallucination Long Text Generation: Built specifically for medium-to-long TTS (essays, audiobooks, video dubbing).Chunk Control: Uses a customizable words_per_chunk parameter (e.g., set to 100) to safely break down massive walls of text, ensuring the model stays perfectly stable from start to finish.Massive Language Capability: Full support for 600+ languages and regional dialects.Advanced Pronunciation Markup: Easily fix tricky words and polyphones using phonetic markup or Chinese Pinyin + tone numbers.

VoxCPM2 Voice Cloning_Voice Design

🚀 Try it out instantly on Runninghub! No crazy local hardware required. Click the link below to register and get 1,000 FREE credits to test it out, plus 100 credits every day you log in! 👉 Get Started on Runninghub: https://www.runninghub.ai/post/2046127758589304834/?inviteCode=rh-v1497🔥 Create Nuanced, Highly Personalized AI Voices!Welcome to the ultimate VoxCPM 2 workflow for voice cloning and design! If you want to see exactly how to use this to cook up amazing voices, check out the full tutorial on my channel: 📺 Watch the Tutorial Here: ✨ Core Features:Natural Language Voice Design: Ditch the rigid tags! Just type what you want, like "A young girl with a sweet, gentle voice and a slight rasp," and let the model invent it. Endlessly tweakable until you find the perfect tone."Ultimate Clone" Toggle: Want a dead-on clone? Set it to True (note: this ignores emotion prompts). Want to inject emotions like "cheerful" or "angry"? Set it to False to balance resemblance with dynamic expression.Built-in Denoise: Automatically wipes out background noise from your reference audio for cleaner outputs.Lazy-Genius Language Switching: No manual language selection needed. Throw a mix of English and Chinese at it, and it seamlessly switches back and forth!Safety First: Contains built-in copyright filters for celebrity IPs (produces silent files to prevent misuse). Please use cloning legally and ethically!

MusicMaker

MusicMaker is an APP Mode to make songs based on Ace 1.5Toggle Option to choose between 4b and 1.7b models.This is one of my favorite models :)

Rebels JoyAI Image Edit GGUF

🚀 JoyAI Image Edit: GGUF Setup GuideOptimize your ComfyUI workflow with the high-performance GGUF versions of JoyAI Image Edit. Perfect for balancing quality and VRAM efficiency.🛠️ Required Custom NodesTo use these models, you must install the following node set:Node: ComfyUI_JoyAI_Image by smthemexHow to install: Search for "JoyAI" in the ComfyUI Custom Nodes Manager and click install.📂 Critical Folder Installation[!IMPORTANT] Both the Transformer and the Text Encoder must be placed in the gguf folder. Do not place them in unet or text_encoders.If you do not have a gguf folder, you must create one manually. Your path should look exactly like this: ComfyUI_windows_portable\ComfyUI\models\gguf\📥 Download Links1. Transformers (Place in models/gguf)Choose the quantization level that fits your hardware:Download Q6_K (High Quality / Balanced)Download Q8_0 (Maximum Precision)2. Und-Merger Text Encoder (Place in models/gguf)Download Text Encoder Q6_K3. VAE (Place in models/vae)Download Wan2.1 VAE📋 Quick Setup Checklist[ ] Install ComfyUI_JoyAI_Image custom nodes.[ ] Create the models/gguf directory.[ ] Drop the Transformer and Text Encoder into models/gguf.[ ] Drop the VAE into models/vae.[ ] Refresh ComfyUI and load the JoyAI workflow!https://youtu.be/gq1w6YJQiB4?si=YFGpMy8DEMZzCMhp

Ace-Step-1.5_XL_2xAI

Step 1: Install the nodes. If some of them are not installed, search for them and install them manually. Step 2: Download everything you need and place it in the folders. Step 3: For Triton & Sage Install. There is a run_with_sage.bat file in the archive. This makes the generation process faster. Step 4: Run the process and model (warm up 1 or 2 times) acestep_v1.5_xl_sft_bf16.safetensorsComfyUI_t2.10 (Portable).

Video Post Processor

Post Processing workflow with two different kinds of upscalers, a fast upscale without a model and a slower upscale with model. also has an additional sharpen, color match, and interpolation option all able to be toggled on a switch panel. i have a batch manager as well to help prevent any OOM errors but will need to be dialed in on your end, if you have a high VRAM card you can probably turn this off. theoretically you can use this workflow for how ever long your video is with the batch manager but it does take some time to run.

ERNIE Image basic workflow (Base + Turbo)

Workflow descriptionThis is a very basic ERNIE workflow for ComfyUI, available in two variants: base and turbo.No prompt enhancers, no detailers, no extra nodes. Just the core setup to generate images.The goal is simple: give you a clean, stable foundation that you can expand yourself. Add your own prompt enhancers, detailers, LoRAs, or refinements on top of this.If you are getting started with ERNIE or want a minimal workflow without noise, this is exactly that.Access All My WorkflowsWant access to all my workflows, LoRA dataset training setups, and more?Check: https://huslyo123.carrd.co/You will find all details there. Fanvue members get automatic access to my private Discord.Models and setupDiffusion modelsBase:https://huggingface.co/Comfy-Org/ERNIE-Image/resolve/main/diffusion_models/ernie-image.safetensorsTurbo:https://huggingface.co/Comfy-Org/ERNIE-Image/blob/main/diffusion_models/ernie-image-turbo.safetensorsText encoderhttps://huggingface.co/Comfy-Org/ERNIE-Image/resolve/main/text_encoders/ministral-3-3b.safetensorsVAEhttps://huggingface.co/Comfy-Org/ERNIE-Image/resolve/main/vae/flux2-vae.safetensorsFolder structureComfyUI/ └── models/ ├── diffusion_models/ │ ├── ernie-image.safetensors │ └── ernie-image-turbo.safetensors ├── text_encoders/ │ └── ministral-3-3b.safetensors └── vae/ └── flux2-vae.safetensorsRecommended settingsBase modelSteps: 50CFG: 4.0Sampler: EulerTurbo modelSteps: 8CFG: 1.0Sampler: res_multistepSupported resolutions1024x1024848x12641264x848768x1376896x12001376x7681200x896More infohttps://huggingface.co/baidu/ERNIE-Imagehttps://huggingface.co/baidu/ERNIE-Image-TurboClip loader error? Update ComfyUI to the latest release. Reboot.Update both .bat and manager if problem still exists. Reboot.Access All My WorkflowsWant access to all my workflows, LoRA dataset training setups, and more?Check: https://huslyo123.carrd.co/You will find all details there. Fanvue members get automatic access to my private Discord.

Rebels Ernie Image (Turbo+Base)

SETTINGS FOR EACH MODEL ARE BELOWTURBO gguf (unet)https://huggingface.co/unsloth/ERNIE-Image-Turbo-GGUF/tree/mainBASE gguf (unet)https://huggingface.co/unsloth/ERNIE-Image-GGUF/tree/maintext encoder (text encoder)https://huggingface.co/realrebelai/Ministral_3-3b/blob/main/ministral-3-3b.safetensorsvae (vae)https://huggingface.co/black-forest-labs/FLUX.2-small-decoder/tree/mainTurbo SETTINGSMax Resolution:1024x1024Steps:8-10cfg:1.0Base SETTTINGSMax Resolution:1024x1024Steps:30-50cfg:4.0

ZRune Echo Driver

ZRune Echo Driver 是一张基于 EchoMimic V2的workflow，主要用于本地驱动视频口播、半身人物动作和音频驱动视频生成。定位是展示用分享，不是零依赖可复现整包。适用方向：- 本地驱动视频口播- 半身人物动作视频- 音频驱动人像视频- EchoMimic V2 的本地驱动流程参考特点：- 使用 EchoMimic V2- 使用本地 driver video 作为动作驱动- 适合做角色口播、半身动作和简单人物演示重要说明：- 依赖 EchoMimic V2、自定义节点和本地输入素材- 不附带输入图、音频、driver video 等私有素材

Ace-Step1.5 with 3x Sampling + Lora support & Audio Enhancer

Model used:acestep_v1.5_merge_sft_turbo_ta_0.5.safetensorsFor 1.5 XL use:acestep_v1.5_xl_turbo_bf16.safetensorsClip:qwen_0.6b_ace15.safetensorsqwen_1.7b_ace15.safetensors4b clip (for use with both XL and non-XL):Acestep-5Hz-lm-4B-GGUFVAE:ace_1.5_vae.safetensors