🎨 PosterCraft:
Rethinking High-Quality Aesthetic Poster Generation in a Unified Framework

[![arXiv](https://img.shields.io/badge/arXiv-2506.10741-red)](https://arxiv.org/abs/2506.10741) [![GitHub](https://img.shields.io/badge/GitHub-Repository-blue)](https://github.com/ephemeral182/PosterCraft) [![HuggingFace](https://img.shields.io/badge/🤗-HuggingFace-yellow)](https://huggingface.co/PosterCraft) [![Website](https://img.shields.io/badge/🌐-Website-green)](https://ephemeral182.github.io/PosterCraft/) [![Video](https://img.shields.io/badge/🎥-Live_Demo-purple)](https://www.youtube.com/watch?v=92wMU4D7qx0) [![HF Demo](https://img.shields.io/badge/🤗-HF_Demo-orange)](https://huggingface.co/spaces/Ephemeral182/PosterCraft)

### [**🌐 Website**](https://ephemeral182.github.io/PosterCraft/) | [**🎯 Demo**](https://github.com/Ephemeral182/PosterCraft) | [**📄 Paper**](https://arxiv.org/abs/2506.10741) | [**🤗 Models**](https://huggingface.co/PosterCraft) | [**📚 Datasets**](https://huggingface.co/PosterCraft) | [**🎥 Video**](https://www.youtube.com/watch?v=92wMU4D7qx0) | [**🤗 HF Demo**](https://huggingface.co/spaces/Ephemeral182/PosterCraft)

--- ## News & Updates - 🔥 **[2025.06]** PosterCraft has been accepted by ICLR 2026! - 📦 **[2025.09]** We have released our [Poster100K dataset](https://huggingface.co/datasets/PosterCraft/Poster100K) on HuggingFace! - 🖥️ **[2025.06]** We have pushed our work on [MeiGen-AI](https://github.com/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](https://github.com/AIFSH) has successfully integrated **PosterCraft into ComfyUI**! You can check out the full workflow here: [PosterCraft-ComfyUI Example](https://www.xiangongyun.com/image/detail/68b711eb-a31e-47db-82eb-47438359f4bf?r=XLVYLW) Big thanks to the contributor — this will be helpful for many users! See [Issue #6](https://github.com/Ephemeral182/PosterCraft/issues/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](https://mp.weixin.qq.com/s/gq6DwohKP0z333OSDRe7Xw) - 🔥 **[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 Chen**](https://ephemeral182.github.io/)^1,2\*, [**Jianyu Lai**](https://openreview.net/profile?id=~Jianyu_Lai1)¹\*, [**Jialin Gao**](https://scholar.google.com/citations?user=sj4FqEgAAAAJ&hl=zh-CN)²\*, [**Tian Ye**](https://owen718.github.io/)¹, [**Haoyu Chen**](https://haoyuchen.com/)¹, [**Hengyu Shi**](https://openreview.net/profile?id=%7EHengyu_Shi1)², [**Shitong Shao**](https://shaoshitong.github.io/)¹, [**Yunlong Lin**](https://scholar.google.com.hk/citations?user=5F3tICwAAAAJ&hl=zh-CN)³, [**Song Fei**](https://openreview.net/profile?id=~Song_Fei1)¹, [**Zhaohu Xing**](https://ge-xing.github.io/)¹, [**Yeying Jin**](https://jinyeying.github.io/)⁴, **Junfeng Luo**², [**Xiaoming Wei**](https://scholar.google.com/citations?user=JXV5yrZxj5MC&hl=zh-CN)², [**Lei Zhu**](https://sites.google.com/site/indexlzhu/home)^1,5† > > 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 ```bash # 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: ```bash 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: ```bash 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. ```bash 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.	🤗 HF
🔄 PosterCraft-v1_Reflect	Stage 4: Vision-Language Feedback	Iteratively refined using vision-language feedback for further harmony and content accuracy.	🤗 HF

--- ## 📚 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	🤗 HF
🎨 HQ-Poster-100K	100K samples	Curated high-quality posters with aesthetic evaluation	🤗 HF
👍 Poster-Preference-100K	100K images	Preference learning poster pairs for RL training	🤗 HF
🔄 Poster-Reflect-120K	120K images	Vision-language feedback pairs for iterative refinement	🤗 HF

--- ## 📝 Citation If you find PosterCraft useful for your research, please cite our paper: ```bibtex @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`

🎨 PosterCraft:Rethinking High-Quality Aesthetic Poster Generation in a Unified Framework

🎨 PosterCraft:
Rethinking High-Quality Aesthetic Poster Generation in a Unified Framework