10 actions in 10 pieces of software · ranked by words, meaning and measured trust · 666 ms
modelrecord121,756 downloads/month
- feature-extraction
Task: feature-extraction
- feature-extraction
modelrecord
- zsxkib/jina-clip-v2
Jina-CLIP v2: 0.9B multimodal embedding model with 89-language multilingual support, 512x512 image resolution, and Matryoshka representations
- zsxkib/jina-clip-v2
modelrecord109,377 downloads/month
- sentence-similarity
Task: sentence-similarity
- sentence-similarity
modelrecord
- zylim0702/controlnet-v1-1-multi
clip interrogator with controlnet sdxl for canny and controlnet v1.1 for the others
- zylim0702/controlnet-v1-1-multi
modelrecord
- openai/clip
Official CLIP models, generate CLIP (clip-vit-large-patch14) text & image embeddings
- openai/clip
MCP serverrecord
- deduplicate_images
Get top-k semantically unique images (URLs or base64-encoded) using Jina CLIP v2 embeddings and submodular optimization. Use this when you have many visually similar images and want the most diverse subset.
- deduplicate_images
modelrecord
- andreasjansson/clip-features
Return CLIP features for the clip-vit-large-patch14 model
- andreasjansson/clip-features
modelrecord
- zsxkib/clip-age-predictor
Age prediction using CLIP - Patched version of `https://replicate.com/andreasjansson/clip-age-predictor` that works with the new version of cog!
- zsxkib/clip-age-predictor
modelrecord23,650 downloads/month
- text-ranking
Task: text-ranking
- text-ranking
modelrecord
- krthr/clip-embeddings
Generate CLIP (clip-vit-large-patch14) text & image embeddings
- krthr/clip-embeddings
Labels are the instruments' verdict and are never changed by ranking. Agents and robots get this same answer as JSON at /api/v1/find?q=…&answer=1 and through the MCP server.