Meitu launches “self-developed AI visual model” 3.0, which it claims will be used in imaging and design products

IT House stated in a news release on October 10 that Meitu held an event called the “15th Anniversary Birthday Party” yesterday. At the event, Meitu CEO Wu Xinhong released version 3.0 of MiracleVision, a large-scale AI vision model they developed themselves

The content that needs to be rewritten is: ▲ Picture source Meitu Company

Meitu Company announced that Meitu AI visual model MiracleVision3.0 will be fully used in Meitu’s imaging and design products 100 days after its launch, and will be used in the five major industries of e-commerce, advertising, games, animation and film and television. provide support

Wu Xinhong said that three months ago, MiracleVision's painting level was still at the initial stage, but now the 3.0 version is able to depict real and delicate picture details. Currently, users can visit the official website of the AI ​​visual creation tool "WHEE" to experience it

The content that needs to be rewritten is: ▲ Picture source Meitu Company

IT House discovered that Meitu has broken down the core capabilities of its self-developed AI visual model MiracleVision into two major features: "whimsical ideas" and "intelligent creation":

"Wonderful Ideas" Level

MiracleVision claims to be able to lower the threshold of use for the public through the "intelligent association of word prompts" function. When users enter keywords, MiracleVision can automatically add relevant expressions, such as light and shadow effects, texture, style, picture quality, etc.

This function has "precise control of prompt words" and can meet "more professional design requirements", such as using descriptions such as "close shot", "distant view", "forward light", "backlight" to control the final generated effect

The content that needs to be rewritten is: "Intelligent Creation" level

MiracleVision claims to be able to further enrich the details of the work and enhance the expressiveness through the "Deepening Creation" function. The "AI screen expansion" function can make the work larger in size and richer in details; the "partial modification" function can also be used to accurately modify and adjust part of the screen, and the "resolution improvement" function can generate high-definition large images.

Wu Xinhong said that MiracleVision will give full play to its capabilities of whimsy and intelligent creation, delve into the above five industries, and continue to provide support for more design scenarios. It is expected that related visual large model applications will gradually mature and become popular from 2026 to 2030

The content that needs to be rewritten is: ▲ Picture source Meitu Company

The above is the detailed content of Meitu launches “self-developed AI visual model” 3.0, which it claims will be used in imaging and design products. For more information, please follow other related articles on the PHP Chinese website!