HF | VAE |

Basic workflow in the zip file. Turbo CFG: 1 Steps: 8

ERNIE-Image is an 8B parameter text-to-image model from Baidu.

It excels at complex prompt understanding, clear text rendering inside images, and structured layouts like posters, comics, and multi-panel designs.

Includes a built-in Prompt Enhancer that turns short inputs into detailed descriptions. Works great in English and Chinese.

Apache 2.0 license

The model is mirrored here for convenience.