Instructions to use Boogu/Boogu-Image-0.1-Base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use Boogu/Boogu-Image-0.1-Base with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("Boogu/Boogu-Image-0.1-Base", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
- DiffusionBee
Upload README.md with huggingface_hub
Browse files
README.md
CHANGED
|
@@ -27,6 +27,7 @@ library_name: diffusers
|
|
| 27 |
[](https://huggingface.co/Boogu)
|
| 28 |
[](https://github.com/boogu-project/Boogu-Image)
|
| 29 |
[](https://modelscope.cn/organization/Boogu)
|
|
|
|
| 30 |
|
| 31 |
[](http://demo-base.boogu.org/)
|
| 32 |
[](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 |
-
|
| 56 |
-
<img src="assets/ci_chart.svg" alt="Boogu Arena ELO Leaderboard" width="100%" />
|
| 57 |
-
</p> -->
|
| 58 |
<p align="center">
|
| 59 |
-
<img src="assets/
|
| 60 |
</p>
|
| 61 |
|
| 62 |
## β¨ Highlights
|
| 63 |
|
| 64 |
- πΈ **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 |
- π **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 |
- π¨ **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 |
- π **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 |
> π For the full set of practical lessons and an honest account of current limitations, see [Responsible AI & Limitations](#-responsible-ai--limitations) below.
|
| 70 |
|
| 71 |
## π£ News
|
| 72 |
-
- **2026-06-XX** π§ **Boogu-Image-0.1-Edit-Turbo (Image-to-Image) is coming!**
|
|
|
|
| 73 |
- **2026-06-17** π₯ [**ComfyUI-Boogu**](https://huggingface.co/Comfy-Org/Boogu-Image) powered by ComfyUI is released! Thank you, ComfyUI!
|
| 74 |
- **2026-06-17** π₯ [**ComfyUI-Boogu**](https://github.com/boogu-project/ComfyUI-Boogu) is released!
|
| 75 |
- **2026-06-16** π₯ **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** π¨ **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** π **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 }}]** π **Technical report is released!** Read our findings on [arXiv](https://arxiv.org/abs/{{ paper_id }}). -->
|
| 79 |
|
|
|
|
| 27 |
[](https://huggingface.co/Boogu)
|
| 28 |
[](https://github.com/boogu-project/Boogu-Image)
|
| 29 |
[](https://modelscope.cn/organization/Boogu)
|
| 30 |
+
[](https://boogu-gallery.netlify.app/)
|
| 31 |
|
| 32 |
[](http://demo-base.boogu.org/)
|
| 33 |
[](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 |
## β¨ Highlights
|
| 62 |
|
| 63 |
- πΈ **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 |
+

|
| 65 |
- π **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 |
+

|
| 67 |
- π¨ **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 |
+

|
| 69 |
- π **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 |
> π For the full set of practical lessons and an honest account of current limitations, see [Responsible AI & Limitations](#-responsible-ai--limitations) below.
|
| 72 |
|
| 73 |
## π£ News
|
| 74 |
+
- **2026-06-XX** π§ **Boogu-Image-0.1-Edit-Turbo (Image-to-Image) is coming!**
|
| 75 |
+
- **2026-06-XX** π§ **Boogu-Image-0.1-Turbo-2K (Text-to-Image) is coming!**
|
| 76 |
- **2026-06-17** π₯ [**ComfyUI-Boogu**](https://huggingface.co/Comfy-Org/Boogu-Image) powered by ComfyUI is released! Thank you, ComfyUI!
|
| 77 |
- **2026-06-17** π₯ [**ComfyUI-Boogu**](https://github.com/boogu-project/ComfyUI-Boogu) is released!
|
| 78 |
- **2026-06-16** π₯ **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** π¨ **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** π **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 }}]** π **Technical report is released!** Read our findings on [arXiv](https://arxiv.org/abs/{{ paper_id }}). -->
|
| 82 |
|