MiniMax-H3-Image
Text-to-image and multi-image editing in 6 steps
Text-to-image and multi-image editing in 6 steps
Human-1M: 100K hours of sensorized human demonstrations
Multilingual TTS with voice cloning and steering controls
Generate images from text prompts using SplatAnything
Text-to-pixel-art diffusion LLM with live unmasking
Generative visual perception โ segment, depth, normals
3D objects, each with the Python program that builds it
Minimax H3 Video in 2โ4 Steps Without a VAE Decoder
State-of-the-art Zero-shot Object Detection
State-of-the-art Zero-shot Object Detection
State-of-the-art Zero-shot Object Detection
State-of-the-art Zero-shot Object Detection
State-of-the-art Zero-shot Object Detection
State-of-the-art Zero-shot Object Detection
State-of-the-art Zero-shot Object Detection
State-of-the-art Zero-shot Object Detection
State-of-the-art Zero-shot Object Detection
State-of-the-art Zero-shot Object Detection
State-of-the-art Zero-shot Object Detection
State-of-the-art Zero-shot Object Detection
State-of-the-art Zero-shot Object Detection
State-of-the-art Zero-shot Object Detection
State-of-the-art Zero-shot Object Detection
One ordinary camera, a 3D mental map. Open research engine.
Detect, segment, track and caption images and videos