Flux SUPER Workflow
This workflow is made for Flux and can do:
Text2Img (with or without autoprompt based on the input image)
Img2img (Flux Redux, Controlnet Union, Regular Img2img, everything accesible and easy tweakable with the main knobs)
Cnet Upscale (with noise injection / colormatch)
ExtraFace Detailer (with noise injection / mix / colormatch)
PostProcess (Eveything you need)
Nice Console Infos
Minimal clutter, Maximal features
Bypass groups
Caching Optimisations, Teacache for faster inference
You can now use FLUX KREA as base model
To enhance the image only, activate img2img with "img2img denoise" to 0. This will bypass the first inference to only use the upscaler and face detailer.
This method is way faster than something like SUPIR and give better details.
Use the "Control_end" as a strength parameter, higher value for lower strenght.
Use the noise "injection strenght" to add more details
Flux dev (scaled)
T5XXL
https://huggingface.co/comfyanonymous/flux_text_encoders/blob/main/t5xxl_fp16.safetensors
clip l
https://huggingface.co/comfyanonymous/flux_text_encoders/blob/main/clip_l.safetensors
vae
Flux Redux dev
https://huggingface.co/black-forest-labs/FLUX.1-Redux-dev/blob/main/flux1-redux-dev.safetensors
sigclip_vision_patch14_384.safetensors
https://huggingface.co/Comfy-Org/sigclip_vision_384/blob/main/sigclip_vision_patch14_384.safetensors
FLUX.1-dev-ControlNet-Union-Pro
Flux.1-dev-Controlnet-Upscaler
yolov8m-face.pt
https://github.com/akanametov/yolo-face?tab=readme-ov-file#models
face_yolov8n-seg2_60.pt
https://huggingface.co/jags/yolov8_model_segmentation-set/blob/main/face_yolov8n-seg2_60.pt
Yolo8 face segmentation models are in pickle serialization format and autoflagged as "unsafe" because this is not a secure format, just like ".ckpt"
Be sure to download your models from trusted sources by looking at the profiles and previous commits.
Description
FAQ
Comments (12)
How can i ADD loras in Pony Workflow ?
For the life of me I cant find where to write a write for Text2Image generation? Where is that node located?
I'm getting TeaCache node problems, didn't work with manager install or github cloning
My new fave (though the txt2img prompt could be more prominent, it definitely looks like i2v is the use case). any particular reason the PONY version isn't up on civitai?
First of all, huge thanks for the workflow. I managed to run it, however, when it gets to Face Enhancement Injection, I get an error.
FaceEnhancementPipelineWithInjection Array must not contain infs or NaNsThis section was red before I downloaded face_yolov8n-seg2_60.pt.
This workflow is incredible - the only complain I have is that the upscale image - excluding the face - looking very "grainy", and that has nothing to do with the "film grain" setting; is there a particular node I could tweak to fix this?
getting last error that i cant understand
SYLE_MODEL node: flux1-redux-dev file
I created style model folder and upload there redux file
but it doesnt work, also tried to put it to checkpoints. Please help. Where that file suppose to be to run this wf??
FluxControlnetSamplerWithInjection
mat1 and mat2 shapes cannot be multiplied (1x768 and 2816x1280)
how to fix it??
Hello, thanks for your wonderful workflow. Can you guide me on how and where I should install (put) "Depth-Anything" for the Smart Preprocessor Node?
It was working fine but now some grainy artifacts (and more than grain, it's kind of heavy) appear on all of the images
Text2Img doesn't work after first pass
for some reasons, it keeps using the example.png as img2img
I don't understand why there's no JSON file in the archive? Only PNG
Looks like we don't have an active mirror for this file right now.
CivArchive is a community-maintained index — we catalog mirrors that volunteers upload to HuggingFace, torrents, and other public hosts. Looks like no one has uploaded a copy of this file yet.
Some files do get recovered over time through contributions. If you're looking for this one, feel free to ask in Discord, or help preserve it if you have a copy.