Kolors

Kolors is a large-scale text-to-image generation model based on latent diffusion，Developed by the Kolors team at Kuaishou。
Trained on tens of billions of text-image pairs，Kolors in visual quality、Demonstrates significant advantages over open-source and closed-source models in terms of accurate semantic understanding and text rendering of Chinese and English characters。also，Kolors supports Chinese and English input，Performs exceptionally well in understanding and generating China-specific content。