Viggle Video Creation: viggle.ai/app PINOC: viggle.ai/pinoc Games: viggle.ai/games API: viggle.ai/developers
- Tweets 1,751
- Following 163
- Followers 23,327
- Likes 2,548
Introducing the Viggle API.
Give any character any motion, one API call - alive in seconds.
Wire it into Claude, Codex, or any agent you're building. Starting from $0.01/sec.
Get 100 free credits on signup.
RT + follow + comment, 10 winners get 100 more!
Learn more below👇
27
17
79
13,675
🚀 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: huggingface.co/spaces/Viggle…
7
10
134
14,204
ViggleAI retweeted
Qwen Image 2.1 viggle turbo. This generates images in only 4 steps instead of 40, making it way faster
huggingface.co/Viggle/Qwen-I…
19
24
424
22,088
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.
Claude Opus 5.5 with PINOC MCP one shotted this:
A playable Minecraft recreation
Link, prompt and more examples below 🧵
4
2
12
1,686
🚀 Viggle Turbo v0.2 is out
• diversity improved, drift gone
• better prompt/reference following, less ghosting
Still preview, training continues.
huggingface.co/Viggle/Qwen-I…
Qwen-Image-2.1 in 4 steps is here ⚡
@ViggleAI distilled Qwen-Image-2.1 into a 4-step turbo model, 6× faster, and holds up side by side with the full model
▶️ on Spaces hf.co/spaces/Viggle/Qwen-Ima…
1
7
651
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: huggingface.co/Viggle/Qwen-I…
Qwen-Image-2.1 in 4 steps is here ⚡
@ViggleAI distilled Qwen-Image-2.1 into a 4-step turbo model, 6× faster, and holds up side by side with the full model
▶️ on Spaces hf.co/spaces/Viggle/Qwen-Ima…
6
17
92
9,808
ViggleAI retweeted
Qwen-Image-2.1 in 4 steps is here ⚡
@ViggleAI distilled Qwen-Image-2.1 into a 4-step turbo model, 6× faster, and holds up side by side with the full model
▶️ on Spaces hf.co/spaces/Viggle/Qwen-Ima…
11
114
1,357
92,329
GPT-6 Astra and Opus 5.5 can build entire game worlds.
When it comes to characters, you’re still cleaning up your meshes, figuring out rigging, and trying to make animations work.
So we built PINOC MCP—with a simpler path from character idea to animation.
Start with text or an image and get a fully rigged 3D Gaussian splat character. Your AI agent can animate it with a text prompt, video mocap, or our free motion library. No manual character rigging.
Already have a mesh? If Mixamo doesn’t have the move you have in mind, use PINOC MCP.
We made this whole video with Astra + PINOC MCP btw. Comment & repost to get 300 free credits in your DM!
5
2
19
1,611
ViggleAI retweeted
Viggle dropped another great finetune for H3: Meridian ✨
Camera angle & perspective control from video or image 🎥
> estimates depth and camera poses using VGGT-Omega
> supports: orbit, move in / out, slide sideways, up / down
> runs w/ a 4 step fast inference LoRA
huggingface.co/Viggle/Meridi…
3
8
83
4,509
ViggleAI retweeted
tested H3 Animate on my favorite Wednesday examples
> it's not the first model to finetune on propagating a change from an edited first frame (+ the driving video) - but its the best one I tried
> it's impressive it works this well on complex motion w/o an additional pose estimation - makes me extra curious about the task specific teacher they used
> H3 ref2va already shows impressive pose fidelity & identity transfer w/ inpainting (w/o additional finetuning/lora) - so likely contributed to the results regardless of the specific task teacher
5
7
96
6,780
ViggleAI retweeted
I added an interactive component so you can manually adjust the camera angles with Viggle's H3 Meridian (works both for image and video)
huggingface.co/spaces/linoyt…
2
19
183
9,728
