ERNIE Image is an open-source text-to-image AI model developed by Baidu, designed for generating images with precise text rendering and structured layouts. It supports local deployment, API, and CLI usage, and is suitable for researchers and developers needing advanced image generation capabilities.
In the Image generation space, ERNIE Image takes a focused approach. It focuses on generating images with accurate in-image text and structured layouts from text prompts, locally or via API. It is built as an open-source project for AI researchers and developers. ERNIE Image is open source under the Apache-2.0 license. ERNIE Image is available on the web, the command line, iOS, and API, and it can be self-hosted.
聪 吕 builds and maintains ERNIE Image, and it first shipped in 2026. The project is developed in the open on GitHub with 490 stars. Key capabilities include text-to-image generation, text rendering, and structured layouts. It exposes integrations via a public API.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Closest matches by what these projects do