Instructions to use wj-inf/MagicAssessor-7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use wj-inf/MagicAssessor-7B with Transformers:

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

pipe = pipeline("image-text-to-text", model="wj-inf/MagicAssessor-7B")
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, AutoModelForImageTextToText

processor = AutoProcessor.from_pretrained("wj-inf/MagicAssessor-7B")
model = AutoModelForImageTextToText.from_pretrained("wj-inf/MagicAssessor-7B")
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

vLLM

How to use wj-inf/MagicAssessor-7B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "wj-inf/MagicAssessor-7B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "wj-inf/MagicAssessor-7B",
		"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/wj-inf/MagicAssessor-7B

SGLang

How to use wj-inf/MagicAssessor-7B 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 "wj-inf/MagicAssessor-7B" \
    --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": "wj-inf/MagicAssessor-7B",
		"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 "wj-inf/MagicAssessor-7B" \
        --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": "wj-inf/MagicAssessor-7B",
		"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 wj-inf/MagicAssessor-7B with Docker Model Runner:
```
docker model run hf.co/wj-inf/MagicAssessor-7B
```

Improve model card for MagicAssessor-7B: Add pipeline tag, library name, and links

by nielsr HF Staff - opened Sep 15, 2025

base: refs/heads/main

←

from: refs/pr/1

Discussion Files changed

+11

-10

Files changed (1) hide show

README.md +11 -10

README.md CHANGED Viewed

@@ -1,18 +1,19 @@
 ---
-license: mit
 base_model:
 - Qwen/Qwen2.5-VL-7B-Instruct
 ---
-Paper:
-MagicMirror: A Large-Scale Dataset and Benchmark for Fine-Grained Artifacts Assessment in Text-to-Image Generation
-https://arxiv.org/abs/2509.10260
-Dataset:
-https://huggingface.co/datasets/wj-inf/MagicData340k
-Model:
-https://huggingface.co/datasets/wj-inf/MagicAssessor-7B
-Benchmark:
-https://github.com/wj-inf/MagicMirror

 ---
 base_model:
 - Qwen/Qwen2.5-VL-7B-Instruct
+license: mit
+pipeline_tag: image-text-to-text
+library_name: transformers
 ---
+# MagicAssessor-7B
+MagicAssessor-7B is a Vision-Language Model (VLM) developed for fine-grained artifact assessment in text-to-image generation. It is a core component of the comprehensive **MagicMirror** framework, which aims to systematically evaluate the perceptual quality and identify various anatomical and structural flaws in generated images.
+The model was introduced in the paper [MagicMirror: A Large-Scale Dataset and Benchmark for Fine-Grained Artifacts Assessment in Text-to-Image Generation](https://arxiv.org/abs/2509.10260).
+*   **Paper**: [arXiv:2509.10260](https://arxiv.org/abs/2509.10260) | [Hugging Face Papers: 2509.10260](https://huggingface.co/papers/2509.10260)
+*   **Project Page**: https://wj-inf.github.io/MagicMirror-page/
+*   **Code / GitHub Repository (MagicMirror Benchmark)**: https://github.com/wj-inf/MagicMirror
+*   **Dataset (MagicData340K)**: https://huggingface.co/datasets/wj-inf/MagicData340k
+*   **Model (MagicAssessor-7B - this repository)**: https://huggingface.co/wj-inf/MagicAssessor-7B