Wan: Open and Advanced Large-Scale Video Generative Models
An anime style Text To Video space powered by HunyuanVideo
Generate Podcast using Kokoro-TTS!
Generate high-quality audio from text using various controls
Consistency generation of portrait and subject
Launch a demo app for showcasing features
Generate video use Hunyuan with or without lora
Video deep fake (uncensored)
ML-powered speech synthesis directly in your browser
Music Generation - text to music, music continuation.
High-quality speech synthesis powered by Kokoro TTS
Transform images based on text instructions
Transform video frames using text instructions
Zero Shot voice cloning with llasa 3b (Unofficial Demo)
Generate images with Lumina Image 2.0
Chat with an AI language model
Create images based on your description and face
✨[With v1.0.0] Accelerated TTS on Kokoro-82M