GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
void-2024
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Run this model inference with full control and performance in your environment.
Model Details
Model Provider
void-2024
Model Tree
Qwen/Qwen2.5-VL-7B-Instruct
Input Modalities
Output Modalities
Supported Functionality
| 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 |
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:
bash
git clone https://github.com/JiazheWei/PosterCopilot.gitcd PosterCopilotconda env create -f environment.yml && conda activate postercopilotpython infer.py --model <path-to-this-checkpoint> \--assets ./my_layers --width 1200 --height 1600 -o layout.jsonpython 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).
The model was trained with a fixed system prompt and this user turn:
markdown
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.
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.transformers>=4.55 — the config uses the nested text_config schema that
older releases predate.bibtex
@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}}
Apache 2.0, inherited from the Qwen2.5-VL-7B-Instruct base model.