|
--- |
|
language: en |
|
license: apache-2.0 |
|
library_name: diffusers |
|
tags: [] |
|
datasets: Norod78/EmojiFFHQAlignedFaces |
|
metrics: [] |
|
--- |
|
|
|
# ddpm-EmojiAlignedFaces-64 |
|
|
|
## Model description |
|
|
|
This diffusion model is trained with the [π€ Diffusers](https://github.com/huggingface/diffusers) library |
|
on the [Norod78/EmojiFFHQAlignedFaces](https://huggingface.co/datasets/Norod78/EmojiFFHQAlignedFaces) dataset. |
|
|
|
#### How to use |
|
|
|
```python |
|
from diffusers import DDPMPipeline, DDIMPipeline, PNDMPipeline |
|
|
|
|
|
def main(): |
|
model_id = "Norod78/ddpm-EmojiAlignedFaces-64" |
|
|
|
# load model and scheduler |
|
ddpm = DDPMPipeline.from_pretrained(model_id) # you can replace DDPMPipeline with DDIMPipeline or PNDMPipeline for faster inference |
|
|
|
# run pipeline in inference (sample random noise and denoise) |
|
image = ddpm()["sample"] |
|
|
|
# save image |
|
image[0].save("ddpm_generated_image.jpg") |
|
image[0].show() |
|
|
|
if __name__ == '__main__': |
|
main() |
|
``` |
|
|
|
|
|
### Training data |
|
|
|
[Norod78/EmojiFFHQAlignedFaces](https://huggingface.co/datasets/Norod78/EmojiFFHQAlignedFaces) |
|
|
|
### Training results |
|
|
|
π [TensorBoard logs](https://huggingface.co/Norod78/ddpm-EmojiAlignedFaces-64/tensorboard?#scalars) |
|
|
|
|