|
--- |
|
license: mit |
|
tags: |
|
- pytorch |
|
- diffusers |
|
- unconditional-image-generation |
|
- diffusion-models-class |
|
datasets: |
|
- Norod78/Vintage-Faces-FFHQAligned |
|
--- |
|
|
|
# English Version |
|
|
|
## Example Fine-Tuned Model for learning diffusion model |
|
|
|
My first fintuning model through python script |
|
|
|
base model: google/ddpm-celebahq-256 |
|
|
|
fine-tuning dataset: vintageface |
|
|
|
> The loss is not very stable, and the output is not very satisfactory. |
|
> But since it's a study case, you can't ask for too much. |
|
|
|
|
|
 |
|
|
|
 |
|
|
|
### Usage |
|
|
|
```python |
|
from diffusers import DDPMPipeline |
|
|
|
pipeline = DDPMPipeline.from_pretrained('Chilli-b/my-finetuned-model-celebahq-on-VintageFaces-4epochs') |
|
image = pipeline().images[0] |
|
image |
|
``` |
|
|
|
# 中文版 |
|
|
|
## 学习扩散模型时训练的微调模型 |
|
|
|
这是我第一个微调模型，也是第一个通过 Python 脚本进行训练的微调模型。 |
|
|
|
基底模型：google/ddpm-celebahq-256 |
|
|
|
微调数据集：Norod78/Vintage-Faces-FFHQAligned |
|
|
|
> loss 不是很稳定，输出结果也不太令人满意。 |
|
> 不过既然是学习案例，那也不能要求太多。 |
|
|
|
 |
|
|
|
 |
|
|
|
### 模型使用 |
|
|
|
```python |
|
from diffusers import DDPMPipeline |
|
|
|
pipeline = DDPMPipeline.from_pretrained('Chilli-b/my-finetuned-model-celebahq-on-VintageFaces-4epochs') |
|
image = pipeline().images[0] |
|
image |
|
``` |
