MoPET Medical Classification
MoPET mixture-of-experts medical image classification
None defined yet.
MoPET mixture-of-experts medical image classification
155M-parameter MMDiT text-to-image model
Structured JSON extraction from text with a 0.6B LLM
Turkish TTS via 183M flow-matching DiT (48 kHz)
Text-prompted 4D reconstruction from a casual video
Few-step image generation with PFM on SD3-Medium
Open-vocabulary grounded detection with VLX-Seek 1.5 10B
Generate 3D-printable ArUco/AprilTag fiducial targets
Japanese TTS with INT8-quantized Irodori-TTS-v4-Small
Tool-augmented geospatial agent for satellite imagery
Unified text-to-image and image editing model
Streaming zero-shot voice conversion with MeanVC2
Residual Flow Matching for 4x image super-resolution
Generate radiology reports from chest X-ray images
VLM with learned retrieval token for visual retrieval
Predict next GUI action from screenshot and instruction
2x image super-resolution with Swin2SR lightweight
Roam a 360Β° panorama with a video world model
Kroma style LoRA for Krea 2 Turbo text-to-image
Robot world model for action-conditioned rollout video
Fast 4-step anime image generation with Anima turbo LoRA
Spatial-reasoning VLM (image+text -> text answer)
4-step distilled video LoRA for LingBot-Video MoE 30B
AoTI-compile the MoVerse Pano DiT blocks