Downloads · 30 days
94
11% of all-time downloads
ddpm-anime-faces-64
LittleNyima/ddpm-anime-faces-64
ddpm-anime-faces-64 is a unconditional image generation model from LittleNyima. Use it for the unconditional image generation task on the model card, and read the license before you ship it in a product. It is set up for diffusers. The card lists the license as mit.
ddpm-anime-faces-64 is an educational project for introducing the training and sampling processes of DDPM and DDIM models. The model is trained on huggan/anime-faces dataset.
All-time downloads
818
Public
Parameters
114M
455 MB on disk
Likes
4
Public
Repo makeup
Click a slice to open those files.
.safetensors455 MB · 100%
At a glance
- Task
- Unconditional Image Generation
- Library
- diffusers
- License
- mit
- Access
- Public
- Created
- Jun 11, 2024
- Updated
- Jun 6, 2025
- SHA
- c950b469
Datasets
Model card
From the Hugging Face model README
ddpm-anime-faces-64
ddpm-anime-faces-64 is an educational project for introducing the training and sampling processes of DDPM and DDIM models. The model is trained on huggan/anime-faces dataset.
Training Arguments
| Argument | Value |
|---|---|
| image_size | 64 |
| 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" |
For training code, please refer to this link.
Inference
This project aims to implement DDPM from scratch, so DDPMScheduler is not used. Instead, I use only UNet2DModel and implement a simple scheduler myself.
Please refer to sampling_ddpm.py and sampling_ddim.py for detailed usages.
References
- Task
- Unconditional Image Generation
- Library
- diffusers
- License
- mit
- Created
- Jun 11, 2024
- Updated
- Jun 6, 2025