Instructions to use hustvl/DiffusionVL-Qwen2.5VL-3B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use hustvl/DiffusionVL-Qwen2.5VL-3B with Transformers:

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

pipe = pipeline("image-text-to-text", model="hustvl/DiffusionVL-Qwen2.5VL-3B", trust_remote_code=True)
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 AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("hustvl/DiffusionVL-Qwen2.5VL-3B", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use hustvl/DiffusionVL-Qwen2.5VL-3B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "hustvl/DiffusionVL-Qwen2.5VL-3B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "hustvl/DiffusionVL-Qwen2.5VL-3B",
		"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/hustvl/DiffusionVL-Qwen2.5VL-3B

SGLang

How to use hustvl/DiffusionVL-Qwen2.5VL-3B 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 "hustvl/DiffusionVL-Qwen2.5VL-3B" \
    --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": "hustvl/DiffusionVL-Qwen2.5VL-3B",
		"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 "hustvl/DiffusionVL-Qwen2.5VL-3B" \
        --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": "hustvl/DiffusionVL-Qwen2.5VL-3B",
		"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 hustvl/DiffusionVL-Qwen2.5VL-3B with Docker Model Runner:
```
docker model run hf.co/hustvl/DiffusionVL-Qwen2.5VL-3B
```

Add pipeline tag and library name

by nielsr HF Staff - opened Dec 18, 2025

base: refs/heads/main

←

from: refs/pr/1

Discussion Files changed

-0

nielsr

Dec 18, 2025

This PR improves the model card by adding the library_name: transformers and pipeline_tag: image-text-to-text to the metadata.

The library_name will enable the "Use in Transformers" widget on the model page, providing a quick code snippet for users. The pipeline_tag will ensure the model is correctly categorized on the Hugging Face Hub, making it easier for users to discover models performing similar tasks.

Please review and merge this PR if everything looks good.

Add pipeline tag and library namedbc8d29d

xiazhi changed pull request status to merged Dec 19, 2025

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment