Instructions to use damoncao/Anime_Image2Prompt with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use damoncao/Anime_Image2Prompt with Transformers:

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

pipe = pipeline("image-text-to-text", model="damoncao/Anime_Image2Prompt")
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("damoncao/Anime_Image2Prompt")
model = AutoModelForMultimodalLM.from_pretrained("damoncao/Anime_Image2Prompt", device_map="auto")
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 damoncao/Anime_Image2Prompt with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "damoncao/Anime_Image2Prompt"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "damoncao/Anime_Image2Prompt",
		"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/damoncao/Anime_Image2Prompt

SGLang

How to use damoncao/Anime_Image2Prompt 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 "damoncao/Anime_Image2Prompt" \
    --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": "damoncao/Anime_Image2Prompt",
		"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 "damoncao/Anime_Image2Prompt" \
        --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": "damoncao/Anime_Image2Prompt",
		"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 damoncao/Anime_Image2Prompt with Docker Model Runner:
```
docker model run hf.co/damoncao/Anime_Image2Prompt
```

Anime_Image2Prompt

File size: 1,145 Bytes

6b19e2a

{
  "model_name": "Anime_Image2Prompt",
  "task": "anime_image_to_prompt",
  "system_prompt": "You are an image tagging model. Analyze the image and return only one valid JSON object. Do not add Markdown, explanations, comments, or hidden reasoning. Preserve tag spelling. For each non-empty category, use a JSON array containing exactly one string and join all unique tags inside that string with commas and no spaces after commas. Use an empty array for an empty category. Never repeat a tag. Close every JSON array and the JSON object, then stop immediately.",
  "user_prompt": "Identify the Danbooru tags visible or attributable to this image. Return exactly these three keys: general_tags, character_tags, copyright_tags. Put all tags for each non-empty category in one comma-separated string inside a single-element JSON array. Use an empty array when a category cannot be identified.",
  "tag_fields": [
    "general_tags",
    "character_tags",
    "copyright_tags"
  ],
  "assistant_end_token": "<|im_end|>",
  "assistant_end_token_id": 248046,
  "image_pixels": {
    "min": 200704,
    "max": 401408,
    "low_vram_max": 301056
  }
}