[flux1-fill-dev] flux inpainting — v1.0

[flux1-fill-dev] flux inpainting is for editing images: it takes an input image and a text prompt, guides an inpainting edit, and saves an edited image.

It loads the image, encodes the prompt, applies inpainting conditioning, loads the model, adds guidance, samples, decodes the result, and saves the image.

Use an input image and a text prompt; the output is an image saved by the workflow.

You can run it without setting up a ComfyUI environment, and the listing says it is free.

The listed model files are ae.safetensors, clip_l.safetensors, flux1-fill-dev.safetensors, and t5xxl_fp16.safetensors.

The workflow names these node types: CLIPTextEncode, DifferentialDiffusion, DualCLIPLoader, FluxGuidance, InpaintModelConditioning, KSampler, LoadImage, SaveImage, UNETLoader, VAEDecode, and VAELoader.

The listed base model is Flux.1 D, and the publisher is Nouvo Ai.

Before use, verify that the listed model files match the files available to you, especially flux1-fill-dev.safetensors.

Vorschlag · nicht geprüft

Before use, verify that your environment provides the listed node types.

Vorschlag · nicht geprüft