🎨 PosterCraft:
Rethinking High-Quality Aesthetic Poster Generation in a Unified Framework
🌐 Website | 🎯 Demo | 📄 Paper | 🤗 Models | 📚 Datasets | 🎥 Video | 🤗 HF Demo
News & Updates
- 🔥 [2025.06] PosterCraft has been accepted by ICLR 2026!
- 📦 [2025.09] We have released our Poster100K dataset on HuggingFace!
- 🖥️ [2025.06] We have pushed our work on MeiGen-AI, where you can explore not only our project but also the work of other colleagues. Feel free to check it out for more insights and contributions.
- 🧩 [2025.06] Community user @AIFSH has successfully integrated PosterCraft into ComfyUI!
You can check out the full workflow here: PosterCraft-ComfyUI Example
Big thanks to the contributor — this will be helpful for many users! See Issue #6 for details. - 📖 [2025.06] Our Chinese article providing a detailed introduction and technical walkthrough of PosterCraft is now available!
Read it here: 中文解读｜高质量美学海报生成框架 PosterCraft - 🔥 [2025.06] We have deployed a demo on Hugging Face Space, feel free to give it a try!
- 🚀 [2025.06] Our gradio demo and inference code are now available!
- 📊 [2025.06] We have released partial datasets and model weights on HuggingFace.
Let me know if this works!
👥 Authors
Sixiang Chen1,2*, Jianyu Lai1*, Jialin Gao2*, Tian Ye1, Haoyu Chen1, Hengyu Shi2, Shitong Shao1, Yunlong Lin3, Song Fei1, Zhaohu Xing1, Yeying Jin4, Junfeng Luo2, Xiaoming Wei2, Lei Zhu1,5†
1The Hong Kong University of Science and Technology (Guangzhou)
2Meituan
3Xiamen University
4National University of Singapore
5The Hong Kong University of Science and Technology*Equal Contribution, †Corresponding Author
🌟 What is PosterCraft?
PosterCraft is a unified framework for high-quality aesthetic poster generation that excels in precise text rendering, seamless integration of abstract art, striking layouts, and stylistic harmony.
🚀 Quick Start
🔧 Installation
# Clone the repository
git clone https://github.com/ephemeral182/PosterCraft.git
cd PosterCraft
# Create conda environment
conda create -n postercraft python=3.11
conda activate postercraft
# Install dependencies
pip install -r requirements.txt
🚀 Quick Generation
Generate high-quality aesthetic posters from your prompt with BF16 precision:
python inference.py \
--prompt "Urban Canvas Street Art Expo poster with bold graffiti-style lettering and dynamic colorful splashes" \
--enable_recap \
--num_inference_steps 28 \
--guidance_scale 3.5 \
--seed 42 \
--pipeline_path "black-forest-labs/FLUX.1-dev" \
--custom_transformer_path "PosterCraft/PosterCraft-v1_RL" \
--qwen_model_path "Qwen/Qwen3-8B"
If you are running on a GPU with limited memory, you can use inference_offload.py to offload some components to the CPU:
python inference_offload.py \
--prompt "Urban Canvas Street Art Expo poster with bold graffiti-style lettering and dynamic colorful splashes" \
--enable_recap \
--num_inference_steps 28 \
--guidance_scale 3.5 \
--seed 42 \
--pipeline_path "black-forest-labs/FLUX.1-dev" \
--custom_transformer_path "PosterCraft/PosterCraft-v1_RL" \
--qwen_model_path "Qwen/Qwen3-8B"
💻 Gradio Web UI
We provide a Gradio web UI for PosterCraft.
python demo_gradio.py
📊 Performance Benchmarks
📈 Quantitative Results
Method
Text Recall ↑
Text F-score ↑
Text Accuracy ↑
OpenCOLE (Open)
0.082
0.076
0.061
Playground-v2.5 (Open)
0.157
0.146
0.132
SD3.5 (Open)
0.565
0.542
0.497
Flux1.dev (Open)
0.723
0.707
0.667
Ideogram-v2 (Close)
0.711
0.685
0.680
BAGEL (Open)
0.543
0.536
0.463
Gemini2.0-Flash-Gen (Close)
0.798
0.786
0.746
PosterCraft (ours)
0.787
0.774
0.735
🎭 Gallery & Examples
🎨 PosterCraft Gallery
Adventure Travel
Post-Apocalyptic
Sci-Fi Drama
Space Thriller
Cultural Event
Luxury Product
Concert Show
Children's Book
Movie Poster
🏗️ Model Architecture
A unified framework for high-quality aesthetic poster generation
Our unified framework consists of four critical optimization stages in the training workflow:
🔤 Stage 1: Text Rendering Optimization
Addresses accurate text generation by precisely rendering diverse text on high-quality backgrounds, also ensuring faithful background representation and establishing foundational fidelity and robustness for poster generation.
🎨 Stage 2: High-quality Poster Fine-tuning
Shifts focus to overall poster style and text-background harmony using Region-aware Calibration. This fine-tuning stage preserves text accuracy while strengthening the artistic integrity of the aesthetic poster.
🎯 Stage 3: Aesthetic-Text RL
Employs Aesthetic-Text Preference Optimization to capture higher-order aesthetic trade-offs. This reinforcement learning stage prioritizes outputs that satisfy holistic aesthetic criteria and mitigates defects in font rendering.
🔄 Stage 4: Vision-Language Feedback
Introduces a Joint Vision-Language Conditioning mechanism. This iterative feedback combines visual information with targeted text suggestions for multi-modal corrections, progressively refining aesthetic content and background harmony.
💾 Model Zoo
We provide the weights for our core models, fine-tuned at different stages of the PosterCraft pipeline.
Model
Stage
Description
Download
🎯 PosterCraft-v1_RL
Stage 3: Aesthetic-Text RL
Optimized via Aesthetic-Text Preference Optimization for higher-order aesthetic trade-offs.
🔄 PosterCraft-v1_Reflect
Stage 4: Vision-Language Feedback
Iteratively refined using vision-language feedback for further harmony and content accuracy.
📚 Datasets
We provide four specialized datasets for training PosterCraft workflow:
🔤 Text-Render-2M
Text-Render-2M: Multi-instance text rendering with diverse selections
A comprehensive text rendering dataset containing 2 million high-quality examples. Features multi-instance text rendering, diverse text selections (varying in size, count, placement, and rotation), and dynamic content generation through both template-based and random string approaches.
🎨 HQ-Poster-100K
HQ-Poster-100K: Curated high-quality aesthetic posters
100,000 meticulously curated high-quality posters with advanced filtering techniques and multi-modal scoring. Features Gemini-powered mask generation with detailed captions for comprehensive poster understanding.
👍 Poster-Preference-100K
Poster-Preference-100K: Preference learning pairs for aesthetic optimization
This preference dataset is sourced from over 100,000 generated poster images. Through comprehensive evaluation by Gemini and aesthetic evaluators, we construct high-quality preference pairs designed for reinforcement learning to align poster generation with human aesthetic judgments.
🔄 Poster-Reflect-120K
Poster-Reflect-120K: Vision-language feedback pairs for iterative refinement
This vision-language feedback dataset is sourced from over 120,000 generated poster images. Through comprehensive evaluation by Gemini and aesthetic evaluators, this dataset captures the iterative refinement process and provides detailed feedback for further improvements.
Dataset
Size
Description
Download
🔤 Text-Render-2M
2M samples
High-quality text rendering examples with multi-instance support
🎨 HQ-Poster-100K
100K samples
Curated high-quality posters with aesthetic evaluation
👍 Poster-Preference-100K
100K images
Preference learning poster pairs for RL training
🔄 Poster-Reflect-120K
120K images
Vision-language feedback pairs for iterative refinement
📝 Citation
If you find PosterCraft useful for your research, please cite our paper:
@article{chen2025postercraft,
title={PosterCraft: Rethinking High-Quality Aesthetic Poster Generation in a Unified Framework},
author={Chen, Sixiang and Lai, Jianyu and Gao, Jialin and Ye, Tian and Chen, Haoyu and Shi, Hengyu and Shao, Shitong and Lin, Yunlong and Fei, Song and Xing, Zhaohu and Jin, Yeying and Luo, Junfeng and Wei, Xiaoming and Zhu, Lei},
journal={arXiv preprint arXiv:2506.10741},
year={2025}
}
🙏 Acknowledgments
- 🏛️ Thanks to our affiliated institutions for their support.
- 🤝 Special thanks to the open-source community for inspiration.
📬 Contact
For any questions or inquiries, please reach out to us:
- Sixiang Chen:
schen691@connect.hkust-gz.edu.cn - Jianyu Lai:
jlai218@connect.hkust-gz.edu.cn