---
license: mit
tags:
- video-diffusion
- diffusion
- pytorch
- sprited
datasets:
- sprited/dancing-chibi-figures
---

# Dancing Chibi Figures — baseline checkpoints

Reference checkpoints for the [sprited/dancing-chibi-figures](https://huggingface.co/datasets/sprited/dancing-chibi-figures)
dataset, trained with the **pure-PyTorch** trainer in the [dataset's GitHub repo](https://github.com/sprited-ai/dancing-chibi-figures)
(`train/video_ddpm.py` — factorised 3D UNet, v-prediction, cosine schedule, EMA).

**Why this repo exists:** the dataset ships two learning tracks. The diffusers track (links at the bottom) teaches the
standard tooling everyone uses; this track is the ~600-line from-scratch version where you can read every line of the
model, the schedule and the sampler — and it is where the **video** models live (diffusers has no tiny video pipeline).
These checkpoints are the "fully-trained" reference the [Colab tutorial](https://github.com/sprited-ai/dancing-chibi-figures/blob/main/notebooks/dancing_chibi_figures_colab.ipynb)
compares your short training runs against.

| file | what | steps |
|---|---|---|
| `unet_img64.pt` | unconditional 64px image model (`--frames 1`) — [samples](unet_img64_samples.png) | 30k |
| `unet_img64_cond.pt` | group-conditional image model (`--cond group`, classifier-free guidance) — [samples](unet_img64_cond_samples.png) | 30k |
| `unet_t2v64.pt` | **text-conditioned autoregressive video** (`--cond text --ar_ctx 8 --frames 8 --stride 2`, CLIP prompt embeddings, warm-started from `unet_img64`) — landing soon | 60k |
| `unet_t2v64_scratch.pt` | same recipe from scratch (how much does the image warm-start buy?) — landing soon | 30k |
| `dit_img64_p2.pt` | the other architecture: DiT (transformer) + flow matching, patch 2 — landing soon | 30k |

Used by the [Colab tutorial](https://github.com/sprited-ai/dancing-chibi-figures/blob/main/notebooks/dancing_chibi_figures_colab.ipynb)
as the warm-start image model and the "fully-trained" reference. Generate a prompt-controlled dance:

```bash
python scripts/rollout.py --ckpt unet_t2v64.pt --prompt "A person jumps in place." --seconds 5 --n 8 --out dance.gif
```

Prefer standard 🤗 diffusers? See [sprited/dancing-chibi-figures-ddpm-64](https://huggingface.co/sprited/dancing-chibi-figures-ddpm-64)
(unconditional `DDPMPipeline`) and [sprited/dancing-chibi-figures-t2i-64](https://huggingface.co/sprited/dancing-chibi-figures-t2i-64)
(text-to-image, mini-Stable-Diffusion style). Made by [Sprited](https://sprited.ai).