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
|
@@ -26,13 +26,13 @@ library_name: diffusers
|
|
| 26 |
[](https://boogu.org)
|
| 27 |
[](https://huggingface.co/Boogu)
|
| 28 |
[](https://github.com/boogu-project/Boogu-Image)
|
| 29 |
-
[](http://demo-base.boogu.org/)
|
| 32 |
[](http://demo-edit.boogu.org/)
|
| 33 |
[](http://demo-turbo.boogu.org/)
|
| 34 |
[](LICENSE)
|
| 35 |
-
|
| 36 |
|
| 37 |
Welcome to the official repository for **Boogu-Image-0.1** !
|
| 38 |
|
|
@@ -70,6 +70,8 @@ Since we could not evaluate on LM Arena directly, we built **Boogu Arena**, an L
|
|
| 70 |
|
| 71 |
## π£ News
|
| 72 |
|
|
|
|
|
|
|
| 73 |
- **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/).
|
| 74 |
- **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/).
|
| 75 |
- **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/).
|
|
@@ -77,16 +79,21 @@ Since we could not evaluate on LM Arena directly, we built **Boogu Arena**, an L
|
|
| 77 |
|
| 78 |
## π₯ Model Zoo
|
| 79 |
|
| 80 |
-
|
| 81 |
-
|
|
| 82 |
-
|
|
| 83 |
-
| **Boogu-Image-0.1-
|
| 84 |
-
| **Boogu-Image-0.1-
|
|
|
|
|
|
|
|
|
|
|
|
|
| 85 |
|
| 86 |
- **Boogu-Image-0.1-Base**: Foundation model with strong **diversity** and **controllability** β ideal for **fine-tuning** and downstream development. Mainly intended for **ultra-dense text rendering**; for photorealism, Turbo is usually the better default.
|
| 87 |
- **Boogu-Image-0.1-Edit**: Image editing and transformation variant.
|
| 88 |
- **Boogu-Image-0.1-Turbo**: Distilled variant with the **same parameter count**, typically requiring only **3~4 steps**. Focuses on **high-quality generation** and photorealism while preserving bilingual text rendering and prompt adherence.
|
| 89 |
|
|
|
|
| 90 |
## π οΈ Installation
|
| 91 |
|
| 92 |
> **Tested environment:** Python 3.10 Β· CUDA 12.6 Β· PyTorch 2.7.1
|
|
|
|
| 26 |
[](https://boogu.org)
|
| 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/)
|
| 33 |
[](http://demo-turbo.boogu.org/)
|
| 34 |
[](LICENSE)
|
| 35 |
+
[-lightgrey)]()
|
| 36 |
|
| 37 |
Welcome to the official repository for **Boogu-Image-0.1** !
|
| 38 |
|
|
|
|
| 70 |
|
| 71 |
## π£ News
|
| 72 |
|
| 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/).
|
|
|
|
| 79 |
|
| 80 |
## π₯ Model Zoo
|
| 81 |
|
| 82 |
+
|
| 83 |
+
| Model | Params | Training | Steps | CFG | Task | Hugging Face | ModelScope | Demo |
|
| 84 |
+
| :--- | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: |
|
| 85 |
+
| **Boogu-Image-0.1-Base** | 10B | Joint Training | 25~50 | 2.0ο½5.0<br>οΌe.g., 4.0οΌ | T2I | [](https://huggingface.co/Boogu/Boogu-Image-0.1-Base) | [](https://modelscope.cn/models/Boogu/Boogu-Image-0.1-Base) | [](http://demo-base.boogu.org/) |
|
| 86 |
+
| **Boogu-Image-0.1-Base-fp8** | 10B | Joint Training | 25~50 | 2.0ο½5.0<br>οΌe.g., 4.0οΌ | T2I | [](https://huggingface.co/Boogu/Boogu-Image-0.1-Base-fp8) | [](https://modelscope.cn/models/Boogu/Boogu-Image-0.1-Base-fp8) | β |
|
| 87 |
+
| **Boogu-Image-0.1-Edit** | 10B | Joint Training | 25~50 | 2.0ο½5.0<br>οΌe.g., 5.0οΌ | TI2I | [](https://huggingface.co/Boogu/Boogu-Image-0.1-Edit) | [](https://modelscope.cn/models/Boogu/Boogu-Image-0.1-Edit) | [](http://demo-edit.boogu.org/) |
|
| 88 |
+
| **Boogu-Image-0.1-Edit-fp8** | 10B | Joint Training | 25~50 | 2.0ο½5.0<br>οΌe.g., 5.0οΌ | TI2I | [](https://huggingface.co/Boogu/Boogu-Image-0.1-Edit-fp8) | [](https://modelscope.cn/models/Boogu/Boogu-Image-0.1-Edit-fp8) | β |
|
| 89 |
+
| **Boogu-Image-0.1-Turbo** | 10B | + Decoupled DMD | 4 | 0.0 | T2I | [](https://huggingface.co/Boogu/Boogu-Image-0.1-Turbo) | [](https://modelscope.cn/models/Boogu/Boogu-Image-0.1-Turbo) | [](http://demo-turbo.boogu.org/) |
|
| 90 |
+
| **Boogu-Image-0.1-Turbo-fp8** | 10B | + Decoupled DMD | 4 | 0.0 | T2I | [](https://huggingface.co/Boogu/Boogu-Image-0.1-Turbo-fp8) | [](https://modelscope.cn/models/Boogu/Boogu-Image-0.1-Turbo-fp8) | β |
|
| 91 |
|
| 92 |
- **Boogu-Image-0.1-Base**: Foundation model with strong **diversity** and **controllability** β ideal for **fine-tuning** and downstream development. Mainly intended for **ultra-dense text rendering**; for photorealism, Turbo is usually the better default.
|
| 93 |
- **Boogu-Image-0.1-Edit**: Image editing and transformation variant.
|
| 94 |
- **Boogu-Image-0.1-Turbo**: Distilled variant with the **same parameter count**, typically requiring only **3~4 steps**. Focuses on **high-quality generation** and photorealism while preserving bilingual text rendering and prompt adherence.
|
| 95 |
|
| 96 |
+
|
| 97 |
## π οΈ Installation
|
| 98 |
|
| 99 |
> **Tested environment:** Python 3.10 Β· CUDA 12.6 Β· PyTorch 2.7.1
|