Generate images by combining styles and subjects
Generate video from audio and image
Generate talking heads from audio
MegaTTS 3 but with voice cloning!
Higgs Audio Demo
Unified MLLM with Text-Aligned Representations
Demo for multimodal understanding and generation
OmniGen2: Unified Image Understanding and Generation.
Demo of Normalized Attention Guidance for FLUX.1-dev
Next-Gen High-Resolution 3D Model Generation
Expressive Zeroshot TTS