LingBot Video MoE
LingBot-Video-MoE is an open source Mixture-of-Experts video generation model with 30B total and 3B active parameters, built for embodied intelligence. It supports text-to-image, text-to-video, and image-to-video generation, plus a refiner stage for higher quality output, and is trained on web video combined with over 70,000 hours of embodied data.
- Type
- Video
- Weights
- Open
- Downloads
- 15k
- Likes
- 132
- License
- apache-2.0
- Library
- diffusers
Model hub
robbyant/lingbot-video-moe-30b-a3b
- Repo
- robbyant/lingbot-video-moe-30b-a3b
- Access
- Public
Technical tags and languages
More from Robbyant
11
-
LingBot Depth
3D
LingBot-Depth is a depth completion model that refines noisy or incomplete depth sensor data into high qualit…
-
237 DL
LingBot Video Dense 1.3B
Video
LingBot-Video-Dense is a 1.3 billion parameter dense video generation model from the open source LingBot-Vide…
-
LingBot Vision Giant
Image
LingBot-Vision-Giant is a ViT-g/16 self-supervised Vision Transformer backbone for dense visual perception. P…
-
LingBot Vision Small
Image
LingBot-Vision-Small is a lightweight Vision Transformer (ViT-S/16) backbone pretrained with self-supervised…
-
133 DL
LingBot VLA 2.0
Multimodal
LingBot VLA 2.0 is a 6B parameter Vision Language Action foundation model that converts camera images and lan…
-
111 DL
LingBot VLA 4B Depth
Multimodal
LingBot VLA 4B Depth is a vision language action foundation model for robot manipulation. Pretrained on 20,00…
-
LingBot World 2.0
Video
LingBot-World 2.0 is an interactive world model that generates real-time, controllable video worlds from a si…
-
LingBot World Base Cam
Video
LingBot World Base Cam is an open source image to video world model that generates long, real time interactiv…
About Robbyant
1
Robbyant is an Ant Group embodied-AI company developing foundation models, robot hardware, and end-to-end robotic intelligence systems.