hotdogs/omnivoice-thai
Text-to-Speech β’ 0.6B β’ Updated β’ 79 β’ 14
Generate high-quality images from text prompts
Generate videos from text prompts and optional images
ultra-fast video model, LTX 0.9.8 13B distilled
Animate a still image into a short video using a prompt
Generate images from text prompts
Swap faces in images or videos
270+ Impressive LoRAs for Flux.1
Generate animated video from two images and a prompt
Apply the motion of a video on a portrait
Audio to Talking Face
Ghibli Studio LoRA based Text to Image Generation
Source-code Include
F5-TTS & E2-TTS: Zero-Shot Voice Cloning (Unofficial Demo)
Remove backgrounds from images instantly