README / README.md
yycc's picture
org card
8125714 verified
|
Raw History Blame Contribute Delete
2.86 kB
---
title: Viggle AI
emoji: 🕺
colorFrom: indigo
colorTo: purple
sdk: static
pinned: false
---
**Viggle AI builds Spatial GenAI.** Our models generate character, motion
and scene together in one shared 4D space — the foundation under Meme Maker, PINOC, Viggle Games
and the Viggle API, used by 50M+ people.
**This organization is where we open-release models.** Weights, inference code and a runnable demo
Space for each one.
## Open releases
<table>
<tr>
<td width="50%" valign="top">
<a href="https://huggingface.co/Viggle/Viggle-Animate"><img src="https://huggingface.co/spaces/Viggle/README/resolve/main/thumb-animate.jpg" width="100%" style="border-radius:10px" alt="Three panels: a painted reference frame, the driving video, and Viggle-Animate's output — a corgi performing the same dance in the same kitchen."></a>
### Viggle-Animate
**Character replacement in video.** Repaint one frame of a clip in any image editor; the model
propagates that edit across the shot with motion, camera and timing untouched. No pose skeleton,
no segmentation mask, no text prompt. A 33 B finetune of MiniMax-H3, DMD-distilled to four
sampling steps — 124 frames in 26 s on one B200.
[Weights](https://huggingface.co/Viggle/Viggle-Animate) ·
[Demo](https://huggingface.co/spaces/Viggle/viggle-animate) ·
[Write-up](https://viggle.ai/research/viggle-animate-character-replacement-from-a-repainted-frame?utm_source=huggingface&utm_medium=social&utm_campaign=org-card)
</td>
<td width="50%" valign="top">
<a href="https://huggingface.co/Viggle/Meridian"><img src="https://huggingface.co/spaces/Viggle/README/resolve/main/thumb-meridian.jpg" width="100%" style="border-radius:10px" alt="A generated view of strawberries mid-splash, with the aligned input frame inset in the corner."></a>
### Meridian
**A new perspective on space and time.** Revisit footage you already have from a camera path you
author: orbit the action, hold one moment still, or follow a retimed sequence — and from a single
photograph too. Geometry comes from the video itself, so you can preview the framing before you
generate. Takes of 3–10 s at 24 fps.
[Weights](https://huggingface.co/Viggle/Meridian) ·
[Demo](https://huggingface.co/spaces/Viggle/Meridian) ·
[Write-up](https://viggle.ai/research/meridian-a-new-perspective-on-space-and-time?utm_source=huggingface&utm_medium=social&utm_campaign=org-card)
</td>
</tr>
</table>
## Elsewhere
[viggle.ai](https://viggle.ai/?utm_source=huggingface&utm_medium=social&utm_campaign=org-card) ·
[Research](https://viggle.ai/research?utm_source=huggingface&utm_medium=social&utm_campaign=org-card) ·
[API docs](https://docs.viggle.ai/v1/introduction) ·
[API portal](https://portal.viggle.ai/) ·
[Discord](https://discord.com/invite/viggle) ·
[X](https://x.com/ViggleAI) ·
[YouTube](https://www.youtube.com/@ViggleAI)