Upgraded to v1.0!
generate a video from an image with a text prompt
F5-TTS & E2-TTS: Zero-Shot Voice Cloning (Unofficial Demo)
Generate talking-face video from a photo and audio
Fast high quality video with audio generation with FA3
Clarity AI Upscaler Reproduction
Fast high quality video with audio generation
Reference based video generation
Audio Conditioned LipSync with Latent Diffusion Models
Chatterbox TTS supporting 23 languages
Infinite-Length Film Generation
Generate images from text prompts with customizable aspect ratio
Wan: Open and Advanced Large-Scale Video Generative Models