ViggleAI

“Why would I deceive you?” 😭 We turned yesterday’s viral Viggle Animate clip into a free template on Viggle. You can now make your own version online! Simply upload two character photos - no local setup needed. Try it: https://viggle.ai/meme/app/animate

🚀 Viggle Turbo v0.2 is out! Text-to-image and image editing in 6 steps: about 5× faster than the 40-step Qwen-Image-2.1. Run it for free: https://huggingface.co/spaces/Viggle/Qwen-Image-2.1-viggle-turbo

Meet Meridian by Viggle AI: a video model that lets you change the camera angle and timing of an existing video. Follow the action from a new angle. Slow it down. Or freeze the moment and keep the camera moving. Open weights: https://huggingface.co/Viggle/Meridian

We launched the first Qwen-Image-2.1 turbo for the open community. Try Viggle-Turbo, a DMD-distilled Qwen-Image-2.1 that generates and edits in 4 sampling steps, with no classifier-free guidance. Weights: https://huggingface.co/Viggle/Qwen-Image-2.1-viggle-turbo

bet you haven't seen this: GPT-6 Astra for scene & preps modeling+ PINOC mcp for animated gaussian splat characters

Another cool demo using viggle-animate! We have open-sourced this model for you to swap anyone in any videos. We also have a quick version for you to try it online. Access it here:https://viggle.ai/meme/app/animate

Claude Opus 5.5 build Minecraft in browser, in one shot... the result is INSANE! Another example of Claude Opus 5.5 x @Viggle_PINOC MCP for Game Development.

Google is sending TPUs to orbit next week, so we had to. Swap anyone to the Hotel Lobby trend on Viggle Animate.

Our world foundation model JST-2 launched 3 days ago. Text, image, or video in, 3D characters, motion and scenes out. Here’s what people have built with it since. A thread 🧵

One model that generates 3D characters, motion, and scenes. JST-2 is now live in our API. Start building today: https://viggle.ai/developers

✨ Viggle Turbo v0.3 is here! Cleaner surfaces, finer details, and better small-text rendering with the new 9-step mode. Now easier to use in ComfyUI - available as a LoRA or single-file int8/fp8/GGUF model.

Today we are releasing JST-2, the world's first full-stack physics-native world foundation model. Many world models learn in pixel/video space. We went back to first principles and built the entire model stack in 3D. Generate a 3D scene in seconds and expand it in real time. Create characters with motion built in, all through one general architecture.