scraed/LanPaint
High quality training free inpaint for every stable diffusion model. Supports ComfyUI
This tool helps digital artists, graphic designers, and content creators easily modify images and videos by filling in or extending masked areas with new, coherent content. You input an image or video with a masked region and a text prompt, and it outputs a seamlessly altered image or video. It’s ideal for anyone working with Stable Diffusion models who needs high-quality inpainting or outpainting without complex training.
1,050 stars. Actively maintained with 9 commits in the last 30 days.
Use this if you need to realistically fill in missing parts of an image or extend its boundaries, or if you want to modify specific elements within a video while maintaining consistency, using existing Stable Diffusion models.
Not ideal if you are working with distillation models like Flux.dev and require high flux guidance, as performance may be degraded.
Stars
1,050
Forks
34
Language
Python
License
GPL-3.0
Category
Last pushed
Mar 03, 2026
Commits (30d)
9
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/scraed/LanPaint"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Compare
Related models
julienkay/com.doji.diffusers
A Unity package to run pretrained diffusion models with Unity Sentis
apapiu/transformer_latent_diffusion
Text to Image Latent Diffusion using a Transformer core
Aatricks/LightDiffusion-Next
Fastest Diffusion backend, WebUI, server. Pushing implementation and discovery of optimizations...
FMXExpress/Stable-Diffusion-Desktop-Client
Stable Diffusion Desktop client for Windows, macOS, and Linux built in Embarcadero Delphi.
CLOUDWERX-DEV/DiffuGen
DiffuGen is a powerful yet user-friendly interface for local\edge image generation. Built on the...