Dongyang Liu

Z-Image Turbo++ achieves high-quality 2-step image generation that rivals 8-step models, transforming the landscape of diffusion distillation.

Denoising-based training unlocks smoother, more reliable real-time robot control by better modeling asynchronous execution during chunked action planning.

Fine-tuning efficient few-step diffusion models no longer requires sacrificing their speed, thanks to a self-distillation approach that preserves inference capabilities.

You don't need 80B parameters to rival top-tier commercial image generators: Z-Image proves that a carefully optimized 6B model can deliver comparable performance with dramatically lower computational cost.