#100 · Primary category: Image Generation
ComfyUI-Fluxtapoz
Nodes for image juxtaposition for Flux in ComfyUI
Project last updated:01/09/25
GitHub Stars
1.4K
Forks
57
Contributors
2
License
GPL-3.0
Why we included this project
This one is aimed at people who already work in ComfyUI and want to edit Flux images without moving to a separate tool. The core of it is rectified-flow unsampling: you take an existing photo, invert it back into a prompt, and then re-render or restyle it from there. Alongside that main route there is a faster inversion method, an inversion-free edit path for when you don't want to disturb the original composition, and RF-Edit as an alternative worth testing against the others. Regional prompting lets you steer what changes in specific parts of the latent space, which helps when an edit should only touch one area, and PAG and SEG guidance nodes add extra control over detail and sharpness. If you do semantic editing, style transfer, or prompt-based retouching with Flux, having all these techniques available as drop-in nodes beats stitching them together yourself.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
stable-diffusion-webui
Stable Diffusion web UI
ComfyUI
The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.
diffusers
🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch.
upscayl
🆙 Upscayl - #1 Free and Open Source AI Image Upscaler for Linux, MacOS and Windows.
InvokeAI
InvokeAI is a leading open-source creative engine for Stable Diffusion, offering an industry-leading web UI for generating and editing visual media.