Text-to-Image
Diffusers
Safetensors
English
Chinese
BooguImagePipeline
Boogu-AI commited on
Commit
4f86891
Β·
verified Β·
1 Parent(s): e9fd24c

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +9 -6
README.md CHANGED
@@ -27,6 +27,7 @@ library_name: diffusers
27
  [![Hugging Face](https://img.shields.io/badge/πŸ€—-Hugging%20Face-yellow)](https://huggingface.co/Boogu)
28
  [![GitHub](https://img.shields.io/badge/GitHub-Repo-181717?logo=github&logoColor=white)](https://github.com/boogu-project/Boogu-Image)
29
  [![ModelScope](https://img.shields.io/badge/πŸ€–-ModelScope-624aff)](https://modelscope.cn/organization/Boogu)
 
30
 
31
  [![Demo-Base](https://img.shields.io/badge/🎨-Demo%20Base-ff69b4)](http://demo-base.boogu.org/)
32
  [![Demo-Edit](https://img.shields.io/badge/πŸ–ŒοΈ-Demo%20Edit-ff8c00)](http://demo-edit.boogu.org/)
@@ -52,28 +53,30 @@ This repository provides checkpoints and inference code for **Boogu-Image-0.1**.
52
 
53
  Since we could not evaluate on LM Arena directly, we built **Boogu Arena**, an LM Arena-style preference evaluation. We use an LLM to generate diverse user personas, then ask each persona to produce image generation prompts, resulting in **1K+ test prompts** that we will release publicly for community reproduction. The ELO leaderboard below spans leading closed- and open-source systems. **We welcome teams with questions about the results to contact us so that we can work toward a more objective, fair, and reproducible evaluation.**
54
 
55
- <!-- <p align="center">
56
- <img src="assets/ci_chart.svg" alt="Boogu Arena ELO Leaderboard" width="100%" />
57
- </p> -->
58
  <p align="center">
59
- <img src="assets/arena_elo_chart.svg" alt="Boogu Arena ELO Leaderboard" width="100%" />
60
  </p>
61
 
62
  ## ✨ Highlights
63
 
64
  - πŸ“Έ **Beautiful and Precise Photography** β€” Accurately understands photography prompts and generates high-quality images with natural lighting, coherent composition, and faithful details, preserving coherent subject, background, and spatial relationships even in complex real-world scenes
 
65
  - πŸ“ **Diverse and Stable Text Rendering** β€” Supports a wide range of text-heavy designs β€” posters, stamps, documents, interfaces, brand guides, and handwritten boards β€” with readable structure, stable typography, and robust bilingual (Chinese/English) rendering across diverse layouts
 
66
  - 🎨 **Diverse and Beautiful Stylization** β€” Handles stylized generation across miniature 3D scenes, Chinese-inspired gilded aesthetics, shining fantasy visuals, anime portraits, and mythic character art β€” not just style transfer, but stable, attractive, and prompt-aware creative generation
 
67
  - πŸ“Š **Competitive General Performance** β€” Demonstrates competitive performance across many scenarios and benchmarks, with the Boogu-Image-0.1 family ranking among the very top of evaluated open- and closed-source systems in Boogu Arena
68
 
69
  > πŸ“– For the full set of practical lessons and an honest account of current limitations, see [Responsible AI & Limitations](#-responsible-ai--limitations) below.
70
 
71
  ## πŸ“£ News
72
- - **2026-06-XX** 🧊 **Boogu-Image-0.1-Edit-Turbo (Image-to-Image) is coming!**
 
73
  - **2026-06-17** πŸ”₯ [**ComfyUI-Boogu**](https://huggingface.co/Comfy-Org/Boogu-Image) powered by ComfyUI is released! Thank you, ComfyUI!
74
  - **2026-06-17** πŸ”₯ [**ComfyUI-Boogu**](https://github.com/boogu-project/ComfyUI-Boogu) is released!
75
  - **2026-06-16** πŸ”₯ **Boogu-Image-0.1-Base (Text-to-Image) is released!** The core text-to-image foundation model. Try the [online demo](http://demo-base.boogu.org/).
76
- - **2026-06-16** 🎨 **Boogu-Image-0.1-Edit (Image-to-Image) is released!** Image editing and transformation capabilities now available. Try the [online demo](http://demo-edit.boogu.org/).
77
  - **2026-06-16** πŸš€ **Boogu-Image-0.1-Turbo is released!** Four-step distilled variant for fast inference and photorealistic generation. Try the [online demo](http://demo-turbo.boogu.org/).
78
  <!-- - **[{{ 2026-06-DD }}]** πŸ“„ **Technical report is released!** Read our findings on [arXiv](https://arxiv.org/abs/{{ paper_id }}). -->
79
 
 
27
  [![Hugging Face](https://img.shields.io/badge/πŸ€—-Hugging%20Face-yellow)](https://huggingface.co/Boogu)
28
  [![GitHub](https://img.shields.io/badge/GitHub-Repo-181717?logo=github&logoColor=white)](https://github.com/boogu-project/Boogu-Image)
29
  [![ModelScope](https://img.shields.io/badge/πŸ€–-ModelScope-624aff)](https://modelscope.cn/organization/Boogu)
30
+ [![ModelScope](https://img.shields.io/badge/⛰️-Gallery-green)](https://boogu-gallery.netlify.app/)
31
 
32
  [![Demo-Base](https://img.shields.io/badge/🎨-Demo%20Base-ff69b4)](http://demo-base.boogu.org/)
33
  [![Demo-Edit](https://img.shields.io/badge/πŸ–ŒοΈ-Demo%20Edit-ff8c00)](http://demo-edit.boogu.org/)
 
53
 
54
  Since we could not evaluate on LM Arena directly, we built **Boogu Arena**, an LM Arena-style preference evaluation. We use an LLM to generate diverse user personas, then ask each persona to produce image generation prompts, resulting in **1K+ test prompts** that we will release publicly for community reproduction. The ELO leaderboard below spans leading closed- and open-source systems. **We welcome teams with questions about the results to contact us so that we can work toward a more objective, fair, and reproducible evaluation.**
55
 
56
+
 
 
57
  <p align="center">
58
+ <img src="assets/boogu_elo_arena.svg" alt="Boogu Arena ELO Leaderboard" width="100%" />
59
  </p>
60
 
61
  ## ✨ Highlights
62
 
63
  - πŸ“Έ **Beautiful and Precise Photography** β€” Accurately understands photography prompts and generates high-quality images with natural lighting, coherent composition, and faithful details, preserving coherent subject, background, and spatial relationships even in complex real-world scenes
64
+ ![Showcase for Photography](assets/photography_triptych.png)
65
  - πŸ“ **Diverse and Stable Text Rendering** β€” Supports a wide range of text-heavy designs β€” posters, stamps, documents, interfaces, brand guides, and handwritten boards β€” with readable structure, stable typography, and robust bilingual (Chinese/English) rendering across diverse layouts
66
+ ![Showcase for Photography](assets/text_rendering_triptych.png)
67
  - 🎨 **Diverse and Beautiful Stylization** β€” Handles stylized generation across miniature 3D scenes, Chinese-inspired gilded aesthetics, shining fantasy visuals, anime portraits, and mythic character art β€” not just style transfer, but stable, attractive, and prompt-aware creative generation
68
+ ![Showcase for Photography](assets/stylization_triptych.png)
69
  - πŸ“Š **Competitive General Performance** β€” Demonstrates competitive performance across many scenarios and benchmarks, with the Boogu-Image-0.1 family ranking among the very top of evaluated open- and closed-source systems in Boogu Arena
70
 
71
  > πŸ“– For the full set of practical lessons and an honest account of current limitations, see [Responsible AI & Limitations](#-responsible-ai--limitations) below.
72
 
73
  ## πŸ“£ News
74
+ - **2026-06-XX** 🧊 **Boogu-Image-0.1-Edit-Turbo (Image-to-Image) is coming!**
75
+ - **2026-06-XX** 🧊 **Boogu-Image-0.1-Turbo-2K (Text-to-Image) is coming!**
76
  - **2026-06-17** πŸ”₯ [**ComfyUI-Boogu**](https://huggingface.co/Comfy-Org/Boogu-Image) powered by ComfyUI is released! Thank you, ComfyUI!
77
  - **2026-06-17** πŸ”₯ [**ComfyUI-Boogu**](https://github.com/boogu-project/ComfyUI-Boogu) is released!
78
  - **2026-06-16** πŸ”₯ **Boogu-Image-0.1-Base (Text-to-Image) is released!** The core text-to-image foundation model. Try the [online demo](http://demo-base.boogu.org/).
79
+ - **2026-06-16** 🎨 **Boogu-Image-0.1-Edit (Image-to-Image) is released!** Image editing and transformation capabilities now available. Try the [online demo](http://demo-edit.boogu.org/). **Only support 1 reference image for now. Will try our best to support more reference images. Stay tuned!**
80
  - **2026-06-16** πŸš€ **Boogu-Image-0.1-Turbo is released!** Four-step distilled variant for fast inference and photorealistic generation. Try the [online demo](http://demo-turbo.boogu.org/).
81
  <!-- - **[{{ 2026-06-DD }}]** πŸ“„ **Technical report is released!** Read our findings on [arXiv](https://arxiv.org/abs/{{ paper_id }}). -->
82