Mini toolsLingBot models
Browse all models from this model family.
to
-
By RobbyantLingBot-Video-Dense is a 1.3 billion parameter dense video generation model from the open source LingBot-Video family, built for embodied intelligence research. It supports text to image, text to video, and text and image to video generation, and is designed to connect video synthesis with physical world understanding rather than general entertainment use.NewVideoReleased 8h ago
-
By RobbyantLingBot-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.NewVideoReleased 8h ago
-
By RobbyantLingBot VLA 2.0 is a 6B parameter Vision Language Action foundation model that converts camera images and language instructions into robot actions across arms, grippers, dexterous hands, waist, head, and mobile base signals for real world manipulation and mobile robot tasks.NewMultimodalReleased 1d ago
-
By RobbyantLingBot-Vision-Giant is a ViT-g/16 self-supervised Vision Transformer backbone for dense visual perception. Pretrained with masked boundary modeling, a boundary-centric objective that produces spatially structured patch features while retaining strong semantic representations, intended for feature extraction and dense prediction research.NewImageReleased 3d ago
-
By RobbyantLingBot-Vision-Small is a lightweight Vision Transformer (ViT-S/16) backbone pretrained with self-supervised masked boundary modeling for dense spatial perception. It produces boundary-aware patch token embeddings for feature extraction, PCA visualization, and downstream dense prediction tasks such as depth estimation and semantic segmentation.NewImageReleased 3d ago
-
By RobbyantLingBot World Base Cam is an open source image to video world model that generates long, real time interactive video from a starting image, text prompt, and camera pose controls. It maintains consistency across diverse environments including realistic, scientific, and cartoon styles over a minute long horizon.VideoReleased 5mo ago
-
By RobbyantLingBot World Fast is an open source image to video world model that generates long, temporally consistent video from a starting image, text prompt, and camera pose signals. It supports 480P and 720P resolution and real time, low latency generation.VideoReleased 5mo ago
-
By RobbyantLingBot-World-Base (Act) is an open source world model that generates interactive videos from an image, text prompt, and action control signals. It maintains high fidelity across realistic, scientific, and cartoon environments, supports minute-level long term memory and consistency, and enables real time interactivity with under 1 second latency at 16 frames per second.VideoReleased 5mo ago
-
By AntGroupLingBot-World is an open-source 28B-parameter real-time world model that turns a single image plus camera poses or actions into an interactive 720p environment, sustaining about 16 FPS, sub-second latency and 10-minute stable, physics-consistent exploration.VideoReleased 5mo ago
-
By RobbyantLingBot-Depth is a depth completion model that refines noisy or incomplete depth sensor data into high quality, metric accurate 3D measurements. It uses masked depth modeling to jointly align RGB appearance and depth geometry in a unified latent space, producing dense depth maps and point clouds for robot learning and 3D vision applications.3dReleased 5mo ago
-
By RobbyantLingBot VLA 4B Depth is a vision language action foundation model for robot manipulation. Pretrained on 20,000 hours of real world data from 9 dual arm robot configurations, it adds a depth distilled module for improved spatial perception, mapping camera images and language instructions directly to robot action sequences.MultimodalReleased 5mo ago
