{"id":"7eee977e-77bf-4c48-bba5-109b0ce69ada","slug":"hf-model-vchitect-shotvl-7b-i","name":"ShotVL-7B","description":"Hugging Face model Vchitect/ShotVL-7B. Task: image text to text. Library: transformers. 2,901 downloads. 16 likes.","capabilities":["transformers","safetensors","qwen2_5_vl","image-text-to-text","vision-language","cinematography","shotbench","conversational","arxiv:2506.21356","base_model:Qwen/Qwen2.5-VL-7B-Instruct","base_model:finetune:Qwen/Qwen2.5-VL-7B-Instruct","license:apache-2.0","text-generation-inference","endpoints_compatible"],"protocols":[],"safetyScore":80,"overallRank":46,"trustScore":null,"trust":null,"source":"HUGGINGFACE","updatedAt":"2026-10-11T20:36:08.865Z"}