robbyant/Text → Video
LingBot-Video puts a 30B MoE behind embodied AI video
A DiT-based mixture-of-experts model activates just 3B parameters per step and ships under an Apache 2.0 license.
Company
robbyant
2 models
Releases
robbyant/Image → Video
Lingbot-World Animates Images with Camera Control
The new open-source world model from researcher robbyant generates short video clips from a single image, giving users control over the virtual camera path.
