LTX-2.5 BBox Control
Animate bounding boxes into video, one prompt per box
None defined yet.
Animate bounding boxes into video, one prompt per box
4-step text-to-video+audio with MiniMax-H3 FlashGen LoRA
Edit human-object interactions in images with OneHOI.
Generate extensible underwater 3D scenes with flow matching
Few-shot seismic facies segmentation via GP regression
Fast English ASR with IBM Granite Speech TurboCTC
Seamless looping video generation with Wan2.2 + Loopy
Canter 2B text-to-image flow model
Zero-shot entities, classes, relations & JSON records
Zero-shot entity, classification, relation extraction
Unified text-to-image and image editing model
Schema-driven NER, classification & relation extraction
Unified text-to-image generation and instruction editing
Control-video + prompt to video with sound, MiniMax-H3
Causal world model for robot video generation
Omni-modal image, audio and video understanding
4-step MiniMax-H3 β video with a matching soundtrack
Anime text-to-image with a Qwen3.5 4B cross-adapter
Japanese streaming ASR fine-tuned on 35k hours of speech
TinyCast zero-shot probabilistic time-series forecasting
Generate human motion sequences from text prompts
Monocular portrait video to multi-view videos
Action-conditioned robot manipulation video generation
Track fish in sonar video, fix it with plain English