MOSS-Image Workflow
MOSS-Image text-to-image as a gr.Workflow node canvas.
Audio-driven talking-head video generation (Meituan LongCat)
Text-to-audio with SA3 Medium / Small Music / Small SFX.
High-fidelity pixel-aligned image-to-3D generation.
Vocal and background audio separator
Generate custom songs from text prompts and lyrics
Zero-shot expressive voice cloning and speech generation
Expressive TTS with voice cloning — DramaBox demo
Upscale images using various models
generate a video from an image with a text prompt
generate a video from an image with a text prompt
Generate audio from video and text prompts
High-quality voice cloning TTS for 600+ languages
VoxCPM2 Nano-vLLM Demo