Skip to content
SPECIFICTION
Get listed

Inpaint Anything

github.com

WebWindowsSelf-hosted
Visit github.com
Spec score 7.4 #27 of 57 in Desktop Search Software

Spec sheet

Purpose
Inpaint Anything uses segmentation and inpainting models to edit images, videos, and 3D scenes.Read 9 Oct 2026 · github.com
Integrations
The README identifies Segment Anything, LaMa, Stable Diffusion, OSTrack, and STTN as models used or acknowledged by the project.Read 4 Oct 2026 · github.com
License
The repository includes an Apache License, Version 2.0, which grants no-charge copyright and patent permissions subject to its terms.Read 4 Oct 2026 · github.com
Founded
2023Read 28 Sep 2026 · github.com
3D processing
Remove Anything 3D tracks a selected object across source views, inpaints those views, and uses NeRF to synthesize novel views without the object.Read 4 Oct 2026 · github.com
Beta branch
The README describes the main_2026 branch as beta and says it requires Python 3.12 or newer, PyTorch 2.7 or newer, and CUDA 12.6 or newer.Read 4 Oct 2026 · github.com
Fill and replace
Text prompts guide filling selected objects with new content or replacing backgrounds.Read 9 Oct 2026 · github.com
Hardware
The repository says its defaults target a single 24GB GPU, and FLUX.1-Fill can require about 20GB of VRAM.Read 9 Oct 2026 · github.com
Hosted demo
The README links to a Hugging Face interface for trying Inpaint Anything online.Read 4 Oct 2026 · github.com
Image capabilities
The README lists support for any aspect ratio and 2K resolution.Read 4 Oct 2026 · github.com
Local interface
The repository says its demo can run as a local web UI; the main_2026 quick start launches it at localhost:7860.Read 9 Oct 2026 · github.com
Media support
The repository describes workflows for images, videos, and 3D scenes, with support for any aspect ratio and 2K resolution.Read 9 Oct 2026 · github.com
Model downloads
Users need to download model checkpoints and place them in the documented project directories to run the workflows.Read 4 Oct 2026 · github.com
Model licensing
The README notes that ProPainter and FLUX.1-Fill-dev are non-commercially licensed and says to check the terms for LaMa, SDXL, and SAM 3 before commercial use.Read 9 Oct 2026 · github.com
Models
The main_2026 branch uses SAM 3, LaMa, SDXL, and ProPainter by default in different stages, with other backends available.Read 9 Oct 2026 · github.com
Object removal
Users can select an object by clicking it or, on the main_2026 branch, naming it with a text prompt, then fill the removed area.Read 9 Oct 2026 · github.com
Prompted editing
Fill Anything uses a text prompt to generate content in a selected area, while Replace Anything uses a prompt to change the background.Read 4 Oct 2026 · github.com
Requirements
The main_2026 branch requires Python 3.12 or later, PyTorch 2.7 or later, and CUDA 12.6 or later for its default SAM 3 setup.Read 9 Oct 2026 · github.com
Research authors
The project lists Tao Yu, Runseng Feng, Ruoyu Feng, Jinming Liu, Xin Jin, Wenjun Zeng, and Zhibo Chen as authors.Read 9 Oct 2026 · github.com
Robotics workflow
The main_2026 branch includes batch hand removal from egocentric footage and mask export for Human-to-Robot pipelines.Read 9 Oct 2026 · github.com
Video processing
Remove Anything Video tracks a selected object across video frames and uses a video inpainting model such as STTN to fill it.Read 4 Oct 2026 · github.com
Windows setup
The original README gives a Windows installation path using Miniconda and a Windows-specific requirements file.Read 9 Oct 2026 · github.com

Where Specifiction places it

Alternatives to Inpaint AnythingAll alternatives →