segment-anything-with-clip
Lets you generate image masks by describing objects in natural language, combining SAM’s pixel‑accurate segmentation with CLIP’s text understanding.
- •You need to extract specific objects from photos without manually drawing masks.
- •You want to build a product feature that lets users search images by object description and retrieve the corresponding region.
- •You have a dataset of unlabeled images and want to auto‑segment items based on textual labels.
python demo.py --image_path ./my_photos/office.jpg --text "laptop on the desk"
Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.
Installs with a command or two; your AI agent can do it for you.
mkdir -p ~/.claude/skills/segment-anything-with-clip && curl -fsSL https://workflowstacks.com/api/skills/segment-anything-with-clip/claude-skill -o ~/.claude/skills/segment-anything-with-clip/SKILL.mdOpens the app with this repo with the prompt ready to go — no copy-paste needed.
Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.
Installs with a command or two; your AI agent can do it for you.
mkdir -p ~/.claude/skills/segment-anything-with-clip && curl -fsSL https://workflowstacks.com/api/skills/segment-anything-with-clip/claude-skill -o ~/.claude/skills/segment-anything-with-clip/SKILL.mdOpens the app with this repo with the prompt ready to go — no copy-paste needed.
Are you the creator of this tool? and earn 85% of every sale.
Show it off in your README:
[](https://workflowstacks.com/skills/segment-anything-with-clip?utm_source=github&utm_medium=badge)The five fastest-growing open-source AI skills, ranked by GitHub star growth. One email a week, unsubscribe anytime.
Related skills
More ai-agent tools founders pair with this one.