Create README.md
Browse files
README.md
ADDED
@@ -0,0 +1,90 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: diffusers
|
3 |
+
license: apache-2.0
|
4 |
+
language:
|
5 |
+
- ja
|
6 |
+
pipeline_tag: text-to-image
|
7 |
+
tags:
|
8 |
+
- stable-diffusion
|
9 |
+
---
|
10 |
+
# π Evo-Ukiyoe-v1
|
11 |
+
|
12 |
+
π€ [Models](https://huggingface.co/SakanaAI) | π [Blog](TODO) | π¦ [Twitter](https://twitter.com/SakanaAILabs)
|
13 |
+
|
14 |
+
|
15 |
+
**EvoSDXL-JP-v1** is an experimental education-purpose Japanese SDXL Lightning.
|
16 |
+
This model was created using the Evolutionary Model Merge method.
|
17 |
+
Please refer to our [report](https://arxiv.org/abs/2403.13187) and [blog](https://sakana.ai/evosdxl-jp/) for more details.
|
18 |
+
This model was produced by merging the following models.
|
19 |
+
We are grateful to the developers of the source models.
|
20 |
+
|
21 |
+
- [SDXL](https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0)
|
22 |
+
- [Juggernaut-XL-v9](https://huggingface.co/RunDiffusion/Juggernaut-XL-v9)
|
23 |
+
- [SDXL-DPO](https://huggingface.co/mhdang/dpo-sdxl-text2image-v1)
|
24 |
+
- [JSDXL](https://huggingface.co/stabilityai/japanese-stable-diffusion-xl)
|
25 |
+
- [SDXL-Lightning](https://huggingface.co/ByteDance/SDXL-Lightning)
|
26 |
+
|
27 |
+
|
28 |
+
## Usage
|
29 |
+
|
30 |
+
Use the code below to get started with the model.
|
31 |
+
|
32 |
+
|
33 |
+
<details>
|
34 |
+
<summary> Click to expand </summary>
|
35 |
+
|
36 |
+
1. Git clone this model card
|
37 |
+
```
|
38 |
+
git clone https://huggingface.co/SakanaAI/EvoSDXL-JP-v1
|
39 |
+
```
|
40 |
+
2. Install packages
|
41 |
+
```
|
42 |
+
cd EvoSDXL-JP-v1
|
43 |
+
pip install -r requirements.txt
|
44 |
+
```
|
45 |
+
3. Run
|
46 |
+
```python
|
47 |
+
from evosdxl_jp_v1 import load_evosdxl_jp
|
48 |
+
|
49 |
+
prompt = "ζ΄η¬"
|
50 |
+
pipe = load_evosdxl_jp(device="cuda")
|
51 |
+
images = pipe(prompt, num_inference_steps=4, guidance_scale=0).images
|
52 |
+
images[0].save("image.png")
|
53 |
+
```
|
54 |
+
|
55 |
+
</details>
|
56 |
+
|
57 |
+
|
58 |
+
|
59 |
+
## Model Details
|
60 |
+
|
61 |
+
<!-- Provide a longer summary of what this model is. -->
|
62 |
+
|
63 |
+
- **Developed by:** [Sakana AI](https://sakana.ai/)
|
64 |
+
- **Model type:** Diffusion-based text-to-image generative model
|
65 |
+
- **Language(s):** Japanese
|
66 |
+
- **Blog:** https://sakana.ai/TODO
|
67 |
+
|
68 |
+
|
69 |
+
## License
|
70 |
+
The Python script included in this repository is licensed under the [Apache License 2.0](https://www.apache.org/licenses/LICENSE-2.0).
|
71 |
+
Please note that the license for the model/pipeline generated by this script is inherited from the source models.
|
72 |
+
|
73 |
+
## Uses
|
74 |
+
This model is provided for research and development purposes only and should be considered as an experimental prototype.
|
75 |
+
It is not intended for commercial use or deployment in mission-critical environments.
|
76 |
+
Use of this model is at the user's own risk, and its performance and outcomes are not guaranteed.
|
77 |
+
Sakana AI shall not be liable for any direct, indirect, special, incidental, or consequential damages, or any loss arising from the use of this model, regardless of the results obtained.
|
78 |
+
Users must fully understand the risks associated with the use of this model and use it at their own discretion.
|
79 |
+
|
80 |
+
|
81 |
+
## Acknowledgement
|
82 |
+
|
83 |
+
We would like to thank the developers of the source models for their contributions and for making their work available.
|
84 |
+
|
85 |
+
|
86 |
+
## Citation
|
87 |
+
|
88 |
+
```bibtex
|
89 |
+
TODO
|
90 |
+
```
|