---
license: mit
metrics:
- mse
library_name: diffusers
tags:
- diffusion
pipeline_tag: unconditional-image-generation
---
## Cu~~rsed~~te kitty cats Model Card

DDPMCats is a latent noise-to-image diffusion model capable of generating images of cats. For more information about how Stable Diffusion functions, please have a look at 🤗's [Stable Diffusion blog](https://huggingface.co/blog/stable_diffusion).

You can use this with the 🧨Diffusers library from [Hugging Face](https://huggingface.co).

![So cute, right?](pipe.png)

### Diffusers
```py
from diffusers import DiffusionPipeline

pipeline = DiffusionPipeline.from_pretrained("nroggendorff/cats")
pipe = pipeline.to("cuda")

image = pipe().images[0]  

image.save("cat.png")
```


### Model Details
- `train_batch_size`: 16
- `eval_batch_size`: 16
- `num_epochs`: 50
- `gradient_accumulation_steps`: 1
- `learning_rate`: 1e-4
- `lr_warmup_steps`: 500
- `mixed_precision`: "fp16"
- `eval_metric`: "mean_squared_error"

### Bias
- This model may exhibit biases due to its training data. It will not display images of abused or sick cats, as it prioritizes the well-being of animals.

### Limitations

- The model does not achieve perfect photorealism
- The model cannot render legible text
- The model was trained on a medium-to-large-scale dataset: [huggan/few-shot-cat](https://huggingface.co/datasets/huggan/few-shot-cat)
  
### Developed by
- Noa Linden Roggendorff

*This model card was written by Noa Roggendorff and is based on the [Stable Diffusion v1-5 Model Card](https://huggingface.co/runwayml/stable-diffusion-v1-5).*