Wan: Open and Advanced Large-Scale Video Generative Models

Generate code applications using text prompts

Enhance your photos with AI-driven adjustments

Generate icons with a unique style

Diffusion-based multi-modal virtual try-on pipeline demo.

Generate logos using a pre-trained model

Search documents using text queries

Fast image relighting using Latent Bridge Matching

Generate a video from a prompt and an image

Generate a 2-speaker podcast from text input or documents!

Flask API for fetching YouTube video subtitles and transcrip

Clean up noisy audio

Identify NSFW content in images

Transform data into visual insights

Transcribe audio to text

Wan: Open and Advanced Large-Scale Video Generative Models

Process documents and answer queries

Analyze your data and get insights

Load and activate a pre-trained model

Convert sketches to colored images