Self Forcing Wan 2.1
Real-time video generation
Real-time video generation
image2mesh
Generate custom audio clips from text prompts
Convert text to natural-sounding speech audio
Generate large-scale 3D models with spatial sparse attention
Audio-Driven Multi-Person Conversational Video Generation
A Unified Framework for Image Customization
Try out Mistral's latest OCR with pdfs and images
Chat with an AI assistant that thinks before answering
Demo for Nanonets-OCR
Chat with MedGemma 4B, a medical variant of Gemma 3
Generate medically-informed responses using prompts
Transcribe audio files with timestamps and downloadable subtitles
Conversational speech generation
Transcribe English audio files into text
Clarity AI Upscaler Reproduction
Upscale lowβresolution images to highβresolution with AI
Transcribe song lyrics with timestamps
OmniGen2: Unified Image Understanding and Generation.