[flux1-fill-dev] flux outpainting

This workflow is for Flux outpainting: it takes a source image and text conditioning, extends the image, and produces a preview image and a saved image.

It includes image loading, resizing, padding, inpaint conditioning, sampling, decoding, previewing, and saving.

It includes text encoding, dual CLIP loading, Flux guidance, and differential diffusion.

Provide a source image and text conditioning as inputs.

The outputs include a preview image and a saved image.

The listing says you can run this workflow without setting up a ComfyUI environment, and that it is free.

It is published by Nouvo Ai and lists Flux.1 D as its base model.

Named model files are ae.safetensors, clip_l.safetensors, flux1-fill-dev.safetensors, and t5xxl_fp8_e4m3fn.safetensors.

Processing components include CLIPTextEncode, DifferentialDiffusion, DualCLIPLoader, FluxGuidance, ImagePadForOutpaint, ImageResize+, InpaintModelConditioning, and KSampler.

Other named components are LoadImage, PreviewImage, SaveImage, UNETLoader, VAEDecode, and VAELoader.

Before use, verify that ae.safetensors, clip_l.safetensors, flux1-fill-dev.safetensors, and t5xxl_fp8_e4m3fn.safetensors are available in your environment.

Suggestion · non vérifié

If you use your own environment, verify that the listed workflow components are available there.

Suggestion · non vérifié