Inpaint anyone or anything into anywhere, doing whatever (nunchaku compatible) — v1.0

Use this workflow to inpaint an image: provide an image with a masked portion, and it inserts a character or object while generating content only in that portion.

Input: an image with a masked portion where a character or object should be inserted.

Output: generated content for only the masked portion of the image.

The workflow is published by GGardens and uses Flux.1 Kontext as its base model.

It is listed as a Workflows item, version v1.0.

Model files listed for this workflow: svdq-int4_r32-flux.1-kontext-dev.safetensors, flux1DevVAE_safetensors.safetensors, Long-ViT-L-14-BEST-GmP-smooth-ft.safetensors, t5xxl_fp8_e4m3fn.safetensors, and flux.1 turbo alpha.safetensors.

Node packs listed for this workflow: comfyui-easy-use, comfyui-logicutils, comfyui_essentials, comfyui-inpaint-cropandstitch, comfyui-logic, comfyui-rmbg, comfyui-nunchaku, pr-was-node-suite-comfyui-47064894, and comfyui-kjnodes.

The workflow lists these node-pack pins: comfyui-easy-use 54614079ca96fa66c8953ff89dc66ca77245f5db; comfyui-inpaint-cropandstitch 2.1.7; comfyui-kjnodes 1.1.2; comfyui-logic 1.0.0; comfyui-logicutils 1.7.2; comfyui-rmbg 2.5.1; comfyui-nunchaku 0.3.3; and comfyui_essentials 1.1.0.

Before running it, verify that the listed model files and node packs are available in your setup.

Suggestion · not verified

No license is specified for this workflow.