Upload README.md with huggingface_hub

README.md

@@ -0,0 +1,32 @@
+---
+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).
+
+| file | what | steps |
+|---|---|---|
+| `unet_img64.pt` | unconditional 64px image model (`--frames 1`) | 30k |
+| `unet_t2v64.pt` | text-conditioned autoregressive video model (`--cond text --ar_ctx 8 --frames 8 --stride 2`, CLIP prompt embeddings) | 60k |
+
+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).