PROMETHEUS v1.0 — World Model Interactive Demo
World-first embodied AI world model
World-first embodied AI world model
generate a video from an image with a text prompt
Portrait animation & lipsync with LTX 2.3
Generate speech audio from text with custom or cloned voices
FireRed-Image-Edit × Qwen-Image-Edit-Rapid (Transformers)
Track objects in your video and get an annotated result
Generate lip-synced videos from images and audio
Fast high quality video with audio generation with FA3
Relight and change backgrounds of photos with AI brushes
Generate short videos from text or images
High-fidelity 3D Generation from images
Music Generation Foundation Model v1.5
Official demo of DA^2: Depth Anything in Any Direction
Translate text to emojis with Gemma 3 270M running on-device
Blazingly Fast and Embarrassingly Simple Song Generation
Generate text using the GLM-4.6 model