Instructions to use ShutterMuse/ShutterMuse with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ShutterMuse/ShutterMuse with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("image-text-to-text", model="ShutterMuse/ShutterMuse")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("ShutterMuse/ShutterMuse")
model = AutoModelForMultimodalLM.from_pretrained("ShutterMuse/ShutterMuse")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use ShutterMuse/ShutterMuse with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ShutterMuse/ShutterMuse"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ShutterMuse/ShutterMuse",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/ShutterMuse/ShutterMuse

SGLang

How to use ShutterMuse/ShutterMuse with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "ShutterMuse/ShutterMuse" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ShutterMuse/ShutterMuse",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "ShutterMuse/ShutterMuse" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ShutterMuse/ShutterMuse",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Docker Model Runner
How to use ShutterMuse/ShutterMuse with Docker Model Runner:
```
docker model run hf.co/ShutterMuse/ShutterMuse
```

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}
}

Downloads last month: 20

Safetensors

Model size

9B params

Tensor type

BF16

Model tree for ShutterMuse/ShutterMuse

Base model

Qwen/Qwen3-VL-8B-Instruct

Finetuned

(332)

this model

Space using ShutterMuse/ShutterMuse 1

Paper for ShutterMuse/ShutterMuse

ShutterMuse: Capture-Time Photography Guidance with MLLMs

Paper • 2606.25763 • Published 3 days ago • 44