Models
One workbench, every model
Each model page pairs the model's documented capabilities with our workbench. The badges are honest: Live means it runs here today, Demo means stock sample outputs, Coming soon means documented but not yet connected.
DemoGLM Image
Text-guided image-to-image editing: reshape your photos with words and up to 4 reference images
DemoGPT Image 1.5
Turn prompts and sketches into high-fidelity, production-ready visuals with precise localized editing
DemoGPT Image 2
Publication-ready assets with flawless text rendering and structural consistency
Coming soonGrok Imagine
Turn any static image into a 15-second cinematic video with smooth, natural motion
Coming soonHappyHorse 1.0
The mystery model that topped the Video Arena — unified video and audio generation in a single pass
Coming soonKling 3.0
15-second cinematic video with native audio, lip-sync, and multi-character consistency
Coming soonKling 3.0 Motion Control
Transfer real motion onto any image — body movement, expressions, and camera dynamics
PixVerse C1
Production-grade AI video: 15-second 1080p sequences with native audio and storyboard-to-video
PixVerse V6
Multi-shot cinematic video with 20+ lens controls and multi-image character consistency
Seedance 2.0
ByteDance's director-level AI video: text, image, and audio inputs with cinematic stability
DemoSeedream 5.0 Pro
Precision image editing with local control, multilingual text, and 2K output