Bernini-R Wan 2.2 R2V Lightning
Generate videos from reference images and text prompts
Demo of the Collection of Qwen Image Edit LoRAs
Kolors Portrait to keep face identity developed with Flux
In-browser background removal
PixelSmile Demo [π¨Developing]
Generate speech from text with voice design, cloning, or presets
Pocket TTS optimized for Hugging Face Spaces on CPU
Audio Conditioned LipSync with Latent Diffusion Models