Baidu Releases 8B Text-to-Image Model ERNIE-Image
The large diffusion model from the Chinese tech giant is available under the commercially permissive Apache 2.0 license, a notable release for the community.

Baidu has released ERNIE-Image, a powerful new text-to-image model, making it freely available to the open-source community. Part of the company's broader "ERNIE" family of foundational models, this release adds another significant player to the landscape of open generative AI.
What makes this release particularly notable is its scale and its license. At 8 billion parameters, ERNIE-Image is a substantial diffusion model. More importantly, it is available under the Apache 2.0 license, a fully permissive license that allows for commercial use, modification, and distribution. This stands in contrast to many other popular image models that carry more restrictive terms.
The model's weights and usage instructions are accessible on its Hugging Face repository. The release provides researchers and developers with a powerful, unrestricted foundation for building new applications, from creative tools to synthetic data generation.
Baidu's contribution marks a significant open-source release from a major Chinese technology firm. By providing a large-scale, commercially viable model, ERNIE-Image could help diversify the tooling available to the global AI community and foster new kinds of innovation outside the ecosystem of dominant Western tech companies.
Sources
- Visit
baidu/ERNIE-Image
Hugging Face
0 comments
No comments yet. Be the first to weigh in.
More in Text → Image

Ideogram 4.0: A 9.3B Open-Weight Text-to-Image Model
The new 9.3 billion parameter model uses a Diffusion Transformer architecture and excels at rendering coherent text within generated images.

ByteDance Releases Lance, a Unified Generative AI Model
The 3-billion-parameter model handles image and video generation, editing, and understanding from a single set of weights under a permissive license.

SenseTime Releases 8B 'Any-to-Any' Infographic Model
The new 8B-parameter SenseNova U1 model from SenseTime is designed for complex multimodal tasks, including the in-conversation generation and editing of infographics.