MiniMax (00100) H3-image tops the AA double list: Wensheng Figure and Image Editing Open Weight Model No. 1

The Zhitong Finance App learned that on November 12, the global independent AI evaluation platform Artificial Analysis (AA) list showed that MiniMax (00100)'s newly released image generation model H3-Image ranked first in both Text to Image (Text to Image) and Image Editing (Image Editing) lists.

The results of the list were based on users' pairwise voting on image-generated content, and the model's performance in generating images based on text and editing images in accordance with instructions was examined separately. H3-Image can generate a 4096 x 4096 pixel, about 16MP (4K) high-resolution image in 10s, and the speed can reach 5 times the mainstream level in the market. In terms of picture quality, the model provides rich picture details and a strong sense of realism, and the distance between the AI-generated image and the real visual world is further reduced. Additionally, H3-Image has top command compliance capabilities in the open source model and supports up to 16 reference images, providing developers and creators with more options for image generation, editing, and workflow development.