{"id":"5feecdb9-9db5-4aaf-831b-1147ccb70c5b","slug":"hf-model-daniel3303-qwenstoryteller2-11afzyq-r","name":"QwenStoryteller2","description":"Hugging Face model daniel3303/QwenStoryteller2. Task: image to text. Library: transformers. 31 downloads. 3 likes.","capabilities":["transformers","safetensors","qwen2_5_vl","image-text-to-text","vision-language-model","visual-storytelling","chain-of-thought","grounded-text-generation","cross-frame-consistency","storytelling","image-to-text","contrastive-learning","reinforcement-learning","entity-reidentification","en","dataset:daniel3303/StoryReasoningAdversarialDPO","dataset:daniel3303/StoryReasoning","arxiv:2505.10292","base_model:daniel3303/QwenStoryteller","base_model:finetune:daniel3303/QwenStoryteller"],"protocols":[],"safetyScore":80,"overallRank":34,"trustScore":null,"trust":null,"source":"HUGGINGFACE","updatedAt":"2026-10-11T20:38:40.411Z"}