Introducing Wan3.0 — now in Public Beta.
Simple Input. Smart Creation. Where Imagination Meets Reality.
• Native 30-Second Video Generation
• Reality-Grade Rendering
• Omni-Reference: Beyond text, images, audio, and video—now with documents, spreadsheets, slides, webpages, and more.
Public Beta is now live. Apply now and start creating ↓
Introducing FLUX 3.
One multi-modal model for Image, Video, Audio and Action-Prediction. Creations are truer to life in every kind of style.
FLUX 3 Video is now available in early access (link below).
Jointly trained in one unified architecture, our model can be extended to predict actions for robotics. See our work with mimic and Audi in the thread.
@lonewolf_3d@SD_Tutorial It looks exactly the same on APIs. It’s a matter of promoting and promot enhancers. Also Krea‘s VAE is arguably worse than Ideogram‘s. Swapping it for WAN‘s VAE helps a little in terms of realism.
I made a training adapter for @krea_ai Krea2 Turbo that will allow you to train a LoRA on the turbo model directly without breaking down the distillation. This works the same way as my Z-Image turbo adapter.