Instructions to use void-2024/PosterCopilot with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use void-2024/PosterCopilot with Transformers:

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

pipe = pipeline("image-text-to-text", model="void-2024/PosterCopilot")
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("void-2024/PosterCopilot")
model = AutoModelForMultimodalLM.from_pretrained("void-2024/PosterCopilot", 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 void-2024/PosterCopilot with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "void-2024/PosterCopilot"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "void-2024/PosterCopilot",
		"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/void-2024/PosterCopilot

SGLang

How to use void-2024/PosterCopilot 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 "void-2024/PosterCopilot" \
    --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": "void-2024/PosterCopilot",
		"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 "void-2024/PosterCopilot" \
        --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": "void-2024/PosterCopilot",
		"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 void-2024/PosterCopilot with Docker Model Runner:
```
docker model run hf.co/void-2024/PosterCopilot
```

PosterCopilot-7B

Layout reasoning for professional graphic design. Give the model a set of layer assets and a canvas size; it returns the poster layout as JSON — a bounding box and stacking order for every layer.

Accepted to ECCV 2026.

📄 Paper · 🌐 Project Page · 💻 Code · ▶️ Video

Model details


Base model	Qwen/Qwen2.5-VL-7B-Instruct
Parameters	7B (bfloat16, ~15.5 GiB)
Input	2–25 RGB layer assets + target canvas size + optional design brief
Output	One JSON object: `canvas_size` + per-layer `x, y, w, h, order, category`
Training	Perturbed SFT → RL for visual-reality alignment → RL from aesthetic feedback

Usage

This checkpoint expects a specific image preprocessing pipeline — each layer is flattened onto an auto-selected contrasting background, scaled to a 28-pixel aligned canvas, and letterboxed with grey. Use the reference implementation rather than feeding raw images:

git clone https://github.com/JiazheWei/PosterCopilot.git
cd PosterCopilot
conda env create -f environment.yml && conda activate postercopilot

python infer.py --model <path-to-this-checkpoint> \
    --assets ./my_layers --width 1200 --height 1600 -o layout.json

python render.py --layout layout.json --assets ./my_layers -o poster.png

The repository also contains the renderer that composites the predicted layout and the original layers into the finished poster (PNG or editable PSD).

Prompt format

The model was trained with a fixed system prompt and this user turn:

Please process the following {N} RGB PNG layer assets and compose a single,
aesthetically pleasing poster. The canvas size is {W} x {H} (width x height).

optionally followed by Structure Requirements: {brief}. Both strings live in postercopilot/prompts.py in the code repository; paraphrasing them moves the input off the training distribution.

Notes

Decoding is greedy with repetition_penalty=1.05. Coordinates are emitted digit by digit, so a single flipped digit re-rolls the rest of the layout — expect different-but-comparable results across GPUs, dtypes and attention kernels. Evaluate over a set of samples rather than one generation.
Requires ~20 GB of free VRAM in bfloat16.
transformers>=4.55 — the config uses the nested text_config schema that older releases predate.

Citation

@article{wei2025postercopilot,
  title={PosterCopilot: Toward Layout Reasoning and Controllable Editing for Professional Graphic Design},
  author={Wei, Jiazhe and Li, Ken and Lao, Tianyu and Wang, Haofan and Wang, Liang and Shan, Caifeng and Si, Chenyang},
  journal={arXiv preprint arXiv:2512.04082},
  year={2025}
}

License

Apache 2.0, inherited from the Qwen2.5-VL-7B-Instruct base model.

Downloads last month: -

Safetensors

Model size

8B params

Tensor type

BF16

Model tree for void-2024/PosterCopilot

Base model

Qwen/Qwen2.5-VL-7B-Instruct

Finetuned

(1163)

this model

Paper for void-2024/PosterCopilot

PosterCopilot: Toward Layout Reasoning and Controllable Editing for Professional Graphic Design

Paper • 2512.04082 • Published Dec 3, 2025 • 14