---
license: mit
library_name: diffusers
pipeline_tag: unconditional-image-generation
tags:
- ddpm
- diffusers
- sprited
datasets:
- sprited/dancing-chibi-figures
---

# dancing-chibi-figures-ddpm-64

**Why this model exists:** it is the *answer sheet* for learning image generation on
[sprited/dancing-chibi-figures](https://huggingface.co/datasets/sprited/dancing-chibi-figures). The dataset is meant
to be the first dataset you ever train a diffusion model on — and this checkpoint is what you get when you follow the
**standard 🤗 diffusers recipe** on it, with nothing clever added: the official unconditional-training tutorial
architecture (`UNet2DModel` + `DDPMScheduler`, squaredcos, EMA), 30k steps, ~71M params. If your run looks like the
grid below, you did it right. It doubles as proof that the dataset trains cleanly with textbook code, and as the
unconditional floor that the conditional models (text-to-image, video) are measured against.

One small twist worth knowing: it diffuses **4-channel premultiplied RGBA** directly (no VAE) — the model learns the
transparent background as part of the image.

<p align="center"><img src="sample_030000.png" width="512"></p>

```python
from diffusers import DDPMPipeline
pipe = DDPMPipeline.from_pretrained("sprited/dancing-chibi-figures-ddpm-64").to("cuda")
img = pipe(batch_size=16, num_inference_steps=50).images   # PIL images (RGBA — transparent background included)
```

Training script (deliberately mirrors the official diffusers unconditional-training tutorial):
[`train_diffusers/train_ddpm.py`](https://github.com/sprited-ai/dancing-chibi-figures/blob/main/train_diffusers/train_ddpm.py).
Want text control? See [sprited/dancing-chibi-figures-t2i-64](https://huggingface.co/sprited/dancing-chibi-figures-t2i-64).
Made by [Sprited](https://sprited.ai).