detecting-tips-zones

SKILLWorkflowcommunity
v0.0.0oaustegardMITUpdated 4d agoSource →

Text-prompted image zone detection using TIPSv2 B/14 on CPU. Produces `focus_targets` / `focus_edges` bbox lists from natural-language labels, ready to feed into `svg-portrait-mode`. Use when you want automatic foreground/background separation from prompts like "dog face" + "wooden floor" instead of

Community-submitted skill. Not yet reviewed by the Forge team. Full prompt content may not be available.Request review →
137Repo stars
1Clients
1Formats
4d agoLast update
Skill
Authoroaustegard
Version0.0.0
LicenseMIT
CategoryWorkflow
Formatsskill.md
PromptNot published
Compatibility
Claude✓ Supported
Cursor
Copilot
ChatGPT
Gemini
About

Text-prompted image zone detection using TIPSv2 B/14 on CPU. Produces `focus_targets` / `focus_edges` bbox lists from natural-language labels, ready to feed into `svg-portrait-mode`. Use when you want automatic foreground/background separation from prompts like "dog face" + "wooden floor" instead of hand-annotating bboxes.

Keywords
skillclaude