facebookresearch / facebookresearch/segment-anything

SAM segmentation mask as condition for image generation.

Open
#124 0 comments 2 reactions 0 assignees View on GitHub
discussion
Dominant language
Jupyter Notebook
Stars
54.9k
Forks
6.4k
PR merge metrics
No merged PRs in 30d

Description

Thanks for the great work. We have trained a [ControlNet based on the SAM segmentation mask](https://github.com/sail-sg/EditAnything) for fine-grained image generation.
This model can help to use SAM for image generation and editing. We hope this side project can help to give SAM more applications. Looking for contributions and suggestions!
https://github.com/sail-sg/EditAnything

Contributor guide

Open the contributing guide

Research direction

Start by reviewing the linked EditAnything project to understand the proposed SAM segmentation-mask and ControlNet integration. This issue names no file, test, entry point, or acceptance criteria in the segment-anything repository, so the scope and definition of done need to be established before implementation can begin.

Written by the indexing model from the issue text.

Assessment

Domain
computer-vision, machine-learning
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
15/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.