Workflow for Flux.1-dev ControlNet Upscaler
About this model
Workflows for using a Flux Upscaler ControlNet.
Specifically designed for jasperai / Flux.1-dev-Controlnet-Upscaler
Simple
Contains only Comfy Core nodes—requires an input image, upscale size, a prompt and the usual Flux settings.
Complex
Has some more features that may (or may not) achieve a better result.
Input image can optionally be scaled up to the target resolution (natively or via an Upscaling Model) which is then encoded into the input latent. Changing the denoise value will then vary how much Flux uses the original image vs the ControlNet. (denoise of 1.0 will ignore the pre-Flux upscale just like the Simple workflow, denoise of 0.0 will ignore the ControlNet). This may result in an image more consistent to the original, with Flux just smoothing out artifacts and filling in details.
There is an optional Negative prompt, which might be useful in some situations.
The WD14 Tagger node can be employed to generate tags for the positive prompt.
Related Models
Similar AI models you may like
ON-THE-FLY 实时生成!Wan-AI 万相/ Wan2.1 Video Model (multi-specs) - CausVid&Comfy&Kijai - workflow included
【WAN2.1】IMG to VIDEO
ComfyUI Image Workflows
UltraReal Fine-Tune
Hourglass Body Shape SD1.5/SDXL/PONY/FLUX | olaz
WAN 2.2 Workflow T2V-I2V-T2I (Kijai Wrapper)