{"id":"6e5b4094-f602-4013-bac6-5282aa619b7e","slug":"hf-model-inference-net-cliptagger-12b-1slbnq5-s","name":"ClipTagger-12b","description":"Hugging Face model inference-net/ClipTagger-12b. Task: image text to text. 47 downloads. 60 likes.","capabilities":["safetensors","gemma3","VLM","video-understanding","image-captioning","gemma","json-mode","structured-output","video-analysis","image-text-to-text","conversational","en","license:apache-2.0","model-index","compressed-tensors"],"protocols":[],"safetyScore":80,"overallRank":35,"trustScore":null,"trust":null,"source":"HUGGINGFACE","updatedAt":"2026-10-11T20:38:12.338Z"}