|
--- |
|
language: en |
|
license: apache-2.0 |
|
library_name: diffusers |
|
tags: [] |
|
datasets: imagefolder |
|
metrics: [] |
|
--- |
|
|
|
|
|
|
|
# ddpm-apes-128 |
|
|
|
 |
|
|
|
## Model description |
|
|
|
This diffusion model is trained with the [🤗 Diffusers](https://github.com/huggingface/diffusers) library |
|
on the `imagefolder` dataset. |
|
|
|
## Intended uses & limitations |
|
|
|
#### How to use |
|
|
|
```python |
|
from diffusers import DDPMPipeline |
|
import torch |
|
|
|
model_id = "dn-gh/ddpm-apes-128" |
|
device = torch.device("cuda" if torch.cuda.is_available() else "cpu") |
|
|
|
# load model and scheduler |
|
ddpm = DDPMPipeline.from_pretrained(model_id).to(device) |
|
|
|
# run pipeline in inference |
|
image = ddpm().images[0] |
|
|
|
# save image |
|
image.save("generated_image.png") |
|
``` |
|
|
|
#### Limitations and bias |
|
|
|
[TODO: provide examples of latent issues and potential remediations] |
|
|
|
## Training data |
|
|
|
This model is trained on 4866 images generated with [ykilcher/apes](https://huggingface.co/ykilcher/apes) for 30 epochs. |
|
|
|
### Training hyperparameters |
|
|
|
The following hyperparameters were used during training: |
|
- learning_rate: 0.0001 |
|
- train_batch_size: 16 |
|
- eval_batch_size: 16 |
|
- gradient_accumulation_steps: 1 |
|
- optimizer: AdamW with betas=(None, None), weight_decay=None and epsilon=None |
|
- lr_scheduler: None |
|
- lr_warmup_steps: 500 |
|
- ema_inv_gamma: None |
|
- ema_inv_gamma: None |
|
- ema_inv_gamma: None |
|
- mixed_precision: fp16 |
|
|
|
### Training results |
|
|
|
📈 [TensorBoard logs](https://huggingface.co/dn-gh/ddpm-apes-128/tensorboard?#scalars) |
|
|
|
|
