F5-TTS & E2-TTS: Zero-Shot Voice Cloning (Unofficial Demo)
Transform images into artistic styles like Studio Ghibli
Separate music and vocals from audio
Try Orpheus TTS here
Generate images with texts and reference images
Generate 3D motion videos from text prompts
Convert images to sketches easily
Detect and annotate poses in images and videos
Generate a 3D scene from a single image
Style-Preserving Text-to-Image Generation
Generate consistent character images from prompts
Remove/Change background of video.
Transcribe audio files into text