|
--- |
|
language: en |
|
license: apache-2.0 |
|
library_name: diffusers |
|
tags: [] |
|
datasets: huggan/selfie2anime |
|
metrics: [] |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information the training script had access to. You |
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
# ddpm-ema-anime-128 |
|
|
|
## Model description |
|
|
|
This diffusion model is trained with the [🤗 Diffusers](https://github.com/huggingface/diffusers) library |
|
on the `huggan/selfie2anime` dataset. |
|
|
|
## Intended uses & limitations |
|
|
|
#### How to use |
|
|
|
```python |
|
from diffusers import DDPMPipeline |
|
|
|
model_id = "mrm8488/ddpm-ema-anime-128" |
|
|
|
# load model and scheduler |
|
pipeline = DDPMPipeline.from_pretrained(model_id) |
|
|
|
# run pipeline in inference |
|
image = pipeline()["sample"] |
|
|
|
# save image |
|
image[0].save("anime_face.png") |
|
``` |
|
|
|
#### Limitations and bias |
|
|
|
[TODO: provide examples of latent issues and potential remediations] |
|
|
|
## Training data |
|
|
|
[TODO: describe the data used to train the model] |
|
|
|
### Training hyperparameters |
|
|
|
The following hyperparameters were used during training: |
|
- learning_rate: 0.0001 |
|
- train_batch_size: 32 |
|
- eval_batch_size: 32 |
|
- gradient_accumulation_steps: 1 |
|
- optimizer: AdamW with betas=(0.95, 0.999), weight_decay=1e-06 and epsilon=1e-08 |
|
- lr_scheduler: cosine |
|
- lr_warmup_steps: 500 |
|
- ema_inv_gamma: 1.0 |
|
- ema_inv_gamma: 0.75 |
|
- ema_inv_gamma: 0.9999 |
|
- mixed_precision: fp16 |
|
|
|
### Training results |
|
|
|
📈 [TensorBoard logs](https://huggingface.co/mrm8488/ddpm-ema-anime-64/tensorboard?#scalars) |
|
|
|
> Created by [Manuel Romero/@mrm8488](https://twitter.com/mrm8488) with the support of [Q Blocks](https://www.qblocks.cloud/) |
|
|
