IAHispano/Applio
Audio-to-Audio β’ Updated β’ 239 β’ 217
Generate videos from text prompts or images
Video deep fake
generate a video from an image with a text prompt
Give you the best results.
CPU = UNLIMIT (DUPLICATE this Space)!
Launch a web UI for interacting with the model
generate a video from an image with a text prompt
Convert and separate audio using models and TTS
Copied from https://github.com/microsoft/VibeVoice
Pocket TTS optimized for Hugging Face Spaces on CPU