Whisper Large V3
Transcribe audio or YouTube videos to text
Generate realistic dialogue from a script, using Dia!
Enhance and upscale images with tile‑based AI control
Generate realistic talking video from an image and audio
Universal Image Editing is worth a single LoRA
Upgraded to v1.0!
Large Animatable Human Model
Generate customized images from text and reference photos
Generate an expanded image from a prompt and input image
Edit images with sketches, colors, and text prompts
Generate audio from text with customizable emotions
Generate images from text prompts and optional ID images