[Flux] gguf PuLID with Inpaint

[Flux] gguf PuLID with Inpaint is for editing an input image with PuLID and inpainting; it takes an image through LoadImage, includes mask handling, and saves an image output through SaveImage.

The listed stages cover image resizing, VAE encoding and decoding, mask handling, guidance, sampling, and image saving.

PuLID-specific processing uses ApplyPulidFlux, PulidFluxModelLoader, PulidFluxInsightFaceLoader, and PulidFluxEvaClipLoader.

Image and mask handling uses LoadImage, ImageResize+, VAEEncode, SetLatentNoiseMask, and MaskPreview+.

VAEDecode and SaveImage handle decoding and saving the image output.

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

It is listed with Flux.1 D as the base model and Nouvo Ai as the publisher.

Listed model files are: ae.safetensors, clip_l.safetensors, flux1-dev-Q8_0.gguf, pulid_flux_v0.9.0.safetensors, and t5-v1_1-xxl-encoder-Q8_0.gguf.

Listed node types include: ApplyPulidFlux, BasicGuider, BasicScheduler, CLIPTextEncode, DualCLIPLoaderGGUF, FluxGuidance, ImageResize+, ImpactGaussianBlurMask, KSamplerSelect, LoadImage, and MaskPreview+.

Additional listed node types are: PulidFluxEvaClipLoader, PulidFluxInsightFaceLoader, PulidFluxModelLoader, RandomNoise, SamplerCustomAdvanced, SaveImage, SetLatentNoiseMask, UnetLoaderGGUF, VAEDecode, VAEEncode, and VAELoader.

For denoise adjustments, the listing suggests trying a BasicScheduler value between 0.5 and 1.

Vorschlag · nicht geprüft

Before use, verify that t5-v1_1-xxl-encoder-Q8_0.gguf and pulid_flux_v0.9.0.safetensors are available under those exact filenames.

Vorschlag · nicht geprüft

Verify that your setup supports the listed node types before use.

Vorschlag · nicht geprüft