- Home
- Desktop Search Software
- Inpaint Anything
On the recordRead 9 Oct 202622 facts
Inpaint Anything
On the record
- 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.github.com · read 4 Oct 2026
- 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.github.com · read 4 Oct 2026
- Fill and replace
- Text prompts guide filling selected objects with new content or replacing backgrounds.github.com · read 9 Oct 2026
- Hardware
- The repository says its defaults target a single 24GB GPU, and FLUX.1-Fill can require about 20GB of VRAM.github.com · read 9 Oct 2026
- Hosted demo
- The README links to a Hugging Face interface for trying Inpaint Anything online.github.com · read 4 Oct 2026
- Image capabilities
- The README lists support for any aspect ratio and 2K resolution.github.com · read 4 Oct 2026
- Integrations
- The README identifies Segment Anything, LaMa, Stable Diffusion, OSTrack, and STTN as models used or acknowledged by the project.github.com · read 4 Oct 2026
- License
- The repository includes an Apache License, Version 2.0, which grants no-charge copyright and patent permissions subject to its terms.github.com · read 4 Oct 2026
- Local interface
- The repository says its demo can run as a local web UI; the main_2026 quick start launches it at localhost:7860.github.com · read 9 Oct 2026
- Media support
- The repository describes workflows for images, videos, and 3D scenes, with support for any aspect ratio and 2K resolution.github.com · read 9 Oct 2026
- Model downloads
- Users need to download model checkpoints and place them in the documented project directories to run the workflows.github.com · read 4 Oct 2026
- 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.github.com · read 9 Oct 2026
- Models
- The main_2026 branch uses SAM 3, LaMa, SDXL, and ProPainter by default in different stages, with other backends available.github.com · read 9 Oct 2026
- 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.github.com · read 9 Oct 2026
- 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.github.com · read 4 Oct 2026
- Purpose
- Inpaint Anything uses segmentation and inpainting models to edit images, videos, and 3D scenes.github.com · read 9 Oct 2026
- 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.github.com · read 9 Oct 2026
- Research authors
- The project lists Tao Yu, Runseng Feng, Ruoyu Feng, Jinming Liu, Xin Jin, Wenjun Zeng, and Zhibo Chen as authors.github.com · read 9 Oct 2026
