ERNIE-ViLG 2.0: The new text-to-image model from Baidu outperforms Dalle-2 and Stable Diffusion
To improve your local-language experience, sometimes we employ an auto-translation plugin. Please note auto-translation may not be accurate, so read original article for precise information.
Both Dalle-2 and Stable Diffusion were significantly outperformed by ERNIE-ViLG 2.0
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.
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:
In line with the Trust Project guidelines, please note that the information provided on this page is not intended to be and should not be interpreted as legal, tax, investment, financial, or any other form of advice. It is important to only invest what you can afford to lose and to seek independent financial advice if you have any doubts. For further information, we suggest referring to the terms and conditions as well as the help and support pages provided by the issuer or advertiser. MetaversePost is committed to accurate, unbiased reporting, but market conditions are subject to change without notice.