Id Card Recognition
Identify and verify ID documents
Analyze sentiment of articles related to a trading asset
Generate summaries from YouTube videos or uploaded videos
Recognize faces in a live video stream
Generate images by inpainting with a prompt
Create a video by syncing spoken audio to an image
F5-TTS & E2-TTS: Zero-Shot Voice Cloning (Unofficial Demo)
Generate Vietnamese speech from text and reference audio
Audio Conditioned LipSync with Latent Diffusion Models
Optical illusions and style transfer with FLUX
Create videos with FFMPEG + Qwen2.5-Coder