Data

Tools

Indexes

Applications

Experiments

Awesome

An open API service indexing awesome lists of open source software.

https://github.com/Ephemeral182/PosterCraft

Rethinking High-Quality Aesthetic Poster Generation in a Unified Framework
https://github.com/Ephemeral182/PosterCraft

Last synced: 4 months ago
JSON representation

Rethinking High-Quality Aesthetic Poster Generation in a Unified Framework

Awesome Lists containing this project

README 

          


🎨 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/πŸ€—-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/πŸŽ₯-Live_Demo-purple)](https://www.youtube.com/watch?v=92wMU4D7qx0)

[![HF Demo](https://img.shields.io/badge/πŸ€—-HF_Demo-orange)](https://huggingface.co/spaces/Ephemeral182/PosterCraft)



PosterCraft Logo



### [**🌐 Website**](https://ephemeral182.github.io/PosterCraft/) | [**🎯 Demo**](https://github.com/Ephemeral182/PosterCraft) | [**πŸ“„ Paper**](https://arxiv.org/abs/2506.10741) | [**πŸ€— Models**](https://huggingface.co/PosterCraft) | [**πŸ“š Datasets**](https://huggingface.co/PosterCraft) | [**πŸŽ₯ Video**](https://www.youtube.com/watch?v=92wMU4D7qx0) | [**πŸ€— HF Demo**](https://huggingface.co/spaces/Ephemeral182/PosterCraft)






---



## News & Updates



- πŸ–₯️ **[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 β€” this will be helpful for many users! See [Issue #6](https://github.com/Ephemeral182/PosterCraft/issues/6) for details.

- πŸ“– **[2025.06]** Our **Chinese article** providing a detailed introduction and technical walkthrough of PosterCraft is now available!  

Read it here: [δΈ­ζ–‡θ§£θ―»ο½œι«˜θ΄¨ι‡ηΎŽε­¦ζ΅·ζŠ₯η”Ÿζˆζ‘†ζžΆ PosterCraft](https://mp.weixin.qq.com/s/gq6DwohKP0z333OSDRe7Xw)

- πŸ”₯ **[2025.06]** We have deployed a demo on Hugging Face Space, feel free to give it a try!

- πŸš€ **[2025.06]** Our gradio demo and inference code are now available!

- πŸ“Š **[2025.06]** We have released partial datasets and model weights on HuggingFace.



---



Let me know if this works!



## πŸ‘₯ 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?





What is PosterCraft - Quick Prompt Demo







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**.



## πŸš€ Quick Start



### πŸ”§ 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



```



### πŸš€ 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"

```



### πŸ’» Gradio Web UI



We provide a Gradio web UI for PosterCraft. 



```bash

python demo_gradio.py

```



## πŸ“Š Performance Benchmarks






### πŸ“ˆ 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

  



User Study Results






---



## 🎭 Gallery & Examples






### 🎨 PosterCraft Gallery




Adventure Travel


Post-Apocalyptic


Sci-Fi Drama




Space Thriller


Cultural Event


Luxury Product




Concert Show


Children's Book


Movie Poster






---



## πŸ—οΈ Model Architecture





PosterCraft Framework Overview




A unified framework for high-quality aesthetic poster generation




Our unified framework consists of **four critical optimization stages in the training workflow**:



### πŸ”€ 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.



### πŸ”„ 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.



---



## πŸ’Ύ 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.

πŸ€— HF



πŸ”„ PosterCraft-v1_Reflect

Stage 4: Vision-Language Feedback

Iteratively refined using vision-language feedback for further harmony and content accuracy.

πŸ€— HF






---



## πŸ“š Datasets



We provide **four specialized datasets** for training PosterCraft workflow:



### πŸ”€ Text-Render-2M



Text-Render-2M Dataset




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 Dataset




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.



### πŸ‘ Poster-Preference-100K



Poster-Preference-100K Dataset




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.



### πŸ”„ Poster-Reflect-120K



Poster-Reflect-120K Dataset




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



πŸ”€ Text-Render-2M

2M samples

High-quality text rendering examples with multi-instance support

πŸ€— HF



🎨 HQ-Poster-100K

100K samples

Curated high-quality posters with aesthetic evaluation

πŸ€— HF



πŸ‘ Poster-Preference-100K

100K images

Preference learning poster pairs for RL training

πŸ€— HF



πŸ”„ Poster-Reflect-120K

120K images

Vision-language feedback pairs for iterative refinement

πŸ€— HF






---



## πŸ“ 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}

}

```



---



## πŸ™ Acknowledgments



- πŸ›οΈ Thanks to our affiliated institutions for their support.

- 🀝 Special thanks to the open-source community for inspiration.



---



## πŸ“¬ 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`