ShutterMuse

ShutterMuse is a Qwen3-VL based multimodal large language model for capture-time photography guidance, associated with the paper ShutterMuse: Capture-Time Photography Guidance with MLLMs.

• Paper page: https://huggingface.co/papers/2606.25763
• arXiv: https://arxiv.org/abs/2606.25763

Model Details

• Architecture: Qwen3VLForConditionalGeneration
• Model type: qwen3_vl
• Processor: Qwen3VLProcessor
• Precision: bfloat16
• Format: safetensors sharded checkpoint

Usage

from transformers import AutoProcessor, Qwen3VLForConditionalGeneration

model_id = "ShutterMuse/ShutterMuse"
processor = AutoProcessor.from_pretrained(model_id)
model = Qwen3VLForConditionalGeneration.from_pretrained(
    model_id,
    torch_dtype="auto",
    device_map="auto",
)

Citation

If you use this model, please cite the associated paper:

@misc{li2026shuttermuse,
  title         = {ShutterMuse: Capture-Time Photography Guidance with MLLMs},
  author        = {Li, Jiayu and Fang, Yixiao and Hu, Tianyu and Cheng, Wei and Huang, Ping and Fan, Zheheng and Yu, Gang and Ma, Xingjun},
  year          = {2026},
  eprint        = {2606.25763},
  archivePrefix = {arXiv},
  primaryClass  = {cs.CV},
  url           = {https://arxiv.org/abs/2606.25763}
}