Flux - Style Transfer + ControlNet + FaceSwap! Flux Tools Redux
5.0
0 reviews
Description
Table of Contents
This is a Redux workflow that achieves style transfer while maintaining image composition and facial features using controlnet + face swap!
The workflow runs with Depth as an example, but you can technically replace it with canny, openpose or any other controlnet for your liking.
Sadly I tried using more advanced face swap nodes like pulid, but having all three process in latent space seemed to really mess up the image quality. Therefore I resolved with a face swap node that processes things in pixel space.
Prerequisites:
- Update ComfyUI to the latest version
- Download flux redux safetensors file from: https://huggingface.co/black-forest-labs/FLUX.1-Redux-dev
- Place the redux model inside comfyui/models/style_models
- Doanload the clip vision model from: https://huggingface.co/google/siglip-so400m-patch14-384/tree/main
Link to the Flux Style Transfer workflows:
- Basic Redux Style Transfer: https://openart.ai/workflows/odam_ai/flux---finally-consistent-style-transfer-flux-tools-redux---beginner-friendly/pfHjGywXFNRb8tf05YpH
- Redux Style Transfer + Depth Controlnet for Portraits: https://openart.ai/workflows/odam_ai/flux---style-transfer-controlnet-flux-tools-redux---beginner-friendly/LWMhfWmaku6tdDWjkM8D
- Redux Style Transfer + Depth Controlnet + Face Swap: https://openart.ai/workflows/odam_ai/flux---style-transfer-controlnet-faceswap-flux-tools-redux/3OTbgYiccquUYF2a9G4g
- Redux Style Transfer + Canny Controlnet for Room Design: https://openart.ai/workflows/odam_ai/flux---style-transfer-canny-controlnet-for-room-design-flux-tools-redux---beginner-friendly/BNByZ4Hdb0VMmyIUYJ2h
Link to other Flux Tools beginner friendly workflows:
- Flux Fill (Inpaint) - https://openart.ai/workflows/odam_ai/flux-fill-inpaint---official-flux-tools-by-bfl---beginner-friendly/8wIPSZy0aOuXsGfdfIVp
- Flux Fill (Outpaint) - https://openart.ai/workflows/odam_ai/flux-fill-outpaint---official-flux-tools-by-bfl---beginner-friendly-edit/6CeBgmyrVDP35r4pO4S9
- Flux Depth ControlNet - https://openart.ai/workflows/odam_ai/flux-tools-best-depth-controlnet---official-flux-tools-by-bfl---beginner-friendly/2UDeSn35mPGIEqT1tgYu
- Flux Canny ControlNet - https://openart.ai/workflows/odam_ai/flux-tools-best-canny-controlnet---official-flux-tools-by-bfl---beginner-friendly/O8aLfWdCOKGCyJX79Jm0
- Flux Redux - https://openart.ai/workflows/odam_ai/flux-redux---official-flux-tools-by-bfl---beginner-friendly/tgGYqY7Kri5bMzaulHiI
Node Diagram
Discussion
🚀 Now you can Edit & Run it online (Fast & Error Free):
该工作流在线编辑运行地址：（速度快，不爆红）
https://www.runninghub.ai/post/1862067923450834945/?utm_source=openart
RunningHub – Highly reliable Cloud-Based ComfyUI, Edit and Run Workflows Online, no local installation required. Powered by RTX 4090 GPUs for faster performance and fully error-free node operation.
RunningHub - 超高可用性云端ComfyUI，本地免安装，标配RTX4090带来更快运行速度，站内已发布海量高质量工作流可一键运行，速度快，不爆红
-------------------------------------
👋🏻 Hello Stonelax@odam.ai,
I’m Spike from RunningHub. I hope this message finds you well! I wanted to kindly inform you that we’ve copied your workflow to RunningHub (with the original author clearly credited and a link to your OpenArt profile). The purpose is to allow more users who love your work to easily experience it online.
We’d love to hear from you at: spike@runninghub.ai
🎉 If you’re open to joining us, we can transfer the workflows we’ve uploaded to your RunningHub account and provide you with additional benefits as a token of our appreciation.
😞 However, if you’re not comfortable with this approach, we will promptly remove all the uploaded content.
Looking forward to your response!
nice job: Hello! I'm passionate about AI and new to exploring ComfyUI. I’m interested in using it for generating social media content but have been facing challenges while trying to run ComfyUI on Google Colab. Many workflows I find online tend to throw numerous errors. I’m seeking someone who can guide me in troubleshooting and resolving these issues. I'm happy to compensate you for your time and assistance.
hi you can email me at chicco4life@gmail.com with more details
Ok thanks, I am going to do that
Nicely done! I tried out the workflow and really liked the results.
I've been playing around with it for a few hours now, but I can't seem to get the workflow to only produce a clean and natural face swap without changing the rest of the input image. When I lower the denoise in Ksampler, I get an all-grey or black image result. Does anybody know how I can edit the workflow to achieve my goal of just doing a simple flux face swap?
(Edited)u mean u don't want to change the image at all? just input image + faceswap, and get the exact same output image but with a different face?
Exactly! I've tried several SDUpscale workflows but end result always is so so regarding quality , artifacts and such.
Node Details
Primitive Nodes (11)
CLIPTextEncodeFlux (2)
ControlNetApplySD3 (1)
DF_Get_image_size (1)
Image Comparer (rgthree) (1)
Note (4)
SetUnionControlNetType (1)
StyleModelApplyAdvanced (1)
Custom Nodes (20)
ComfyUI
- SaveImage (2)
- VAELoader (1)
- DualCLIPLoader (1)
- CLIPVisionLoader (1)
- CLIPVisionEncode (1)
- StyleModelLoader (1)
- EmptyLatentImage (1)
- LoadImage (3)
- PreviewImage (1)
- ControlNetLoader (1)
- ImageScale (2)
- KSampler (1)
- UNETLoader (1)
- VAEDecode (1)
- AIO_Preprocessor (1)
- ReActorFaceSwap (1)
Model Details
Checkpoints (0)
LoRAs (0)