ERNIE-Image: Baidu Open Source Image Generation for ComfyUI

ERNIE-Image is Baidu's 8B parameter open text-to-image model series with a light Prompt Enhancer, excelling at text rendering and structured generation.

E

ERNIE-Image by Baidu

Text-to-Image8B DiTText RenderingOpen Source

Open text-to-image generation model series from Baidu's ERNIE team. The 8B single-stream DiT model paired with a Prompt Enhancer delivers SOTA open-weight performance on complex instruction following, text rendering, and structured image generation.

Models

ModelDescriptionLicenseReleased
ERNIE-Image8B DiT SFT (50-step) + Turbo (8-step)Apache 2.02025-11

Select a model above for curated weight downloads, tutorials, and related information.