BitDance-14B-64x
Open-source autoregressive model with binary visual tokens.
Open-source autoregressive model with binary visual tokens.
Generate singing voice from your lyrics
FireRed-Image-Edit-1.0
FireRed-Image-Edit Γ Qwen-Image-Edit-Rapid (Transformers)
Generate detailed images from your text prompts
MegaTTS 3 but with voice cloning!
Generate detailed captions or tags for any uploaded image
Generate a text prompt from an image
Generate speech from text with selectable voices
Convert text to natural-sounding speech audio
F5-TTS & E2-TTS: Zero-Shot Voice Cloning (Unofficial Demo)
Try Orpheus TTS here
Generate speech from text using a reference audio