In Brief
Both Dalle-2 and Stable Diffusion were significantly outperformed by ERNIE-ViLG 2.0
The Trust Project is a worldwide group of news organizations working to establish transparency standards.
ERNIE-ViLG 2.0 is a text-to-image model that offers better performance than Dalle-2 and Stable Diffusion, two of the most popular text-to-image models currently available. The new model was designed and trained by a team of researchers from Baidu, and the outcomes are breathtaking.

The outcomes demonstrated that ERNIE-ViLG 2.0 significantly outperformed Dalle-2 and Stable Diffusion. This is a significant achievement and demonstrates the power of the ERNIE framework. The Metaverse Post team compared ERNIE-ViLG 2.0 with Stable Diffusion below:










These results provide strong support for the hypothesis that ERNIE-ViLG 2.0 is a more effective text-to-image system than both Dalle-2 and Stable Diffusion.
The Unet architecture from Stable Diffusion is taken as a basis, but with changes:
- A Mixture of Denoising Experts: There are 10 neural networks instead of just one, with each being responsible only for certain diffusion steps.
- Textual knowledge: Automatically reweighted the words in the query so that keywords get more weight.
- Visual knowledge: During training, objects were detected on intermediate generation results, and the weight of the loss function on regions with objects was increased.
As a result, the world’s largest text-to-image model came out with 24 billion parameters (10 times bigger than SD) to train the model.
In comparison to earlier models, ERNIE-ViLG 2.0 greatly exceeds them in terms of image quality and image-to-text matching when tested simultaneously on the ViLG-300 bilingual prompt set by a person.
Prompts are simply translated from Chinese to English automatically in the HuggingFace public demo before being sent into the AI. A lot of features flow from this.
- ERNIE does not know international public figures. For instance, ERNIE doesn’t know Arnold Schwarzenegger. It certainly has local favorites in China.
- As a result, the method of using celebrity names in prompts to dramatically boost the quality of faces fails.
- You can expect some distortion because of the translation from Chinese, so there might be some surprises in store for you if you don’t speak Chinese.
- It doesn’t even know anything about Greg Rutkowski.
Read related articles:
Disclaimer
Any data, text, or other content on this page is provided as general market information and not as investment advice. Past performance is not necessarily an indicator of future results.