Meitu AI Visual Large Model MiracleVision to Be Opened to the Public

Recently, Meitu Image Research Institute (MT Lab) and Beijing Jiaotong University jointly proposed a technique called MEMatte (Memory Efficient Matting), which is a super high-resolution matting technology successfully selected for the top-tier conference in the field of artificial intelligence, AAAI 2025. The main highlight of the MEMatte technology is that it is a memory-friendly natural image matting framework that effectively reduces the computational overhead of the model. This innovation allows for operations in memory-constrained environments, such as commercial graphics cards and edge devices.
Recently, Meitu announced that its WHEE application will soon launch a brand new 'AI Poster' feature, designed to simplify the poster creation process through artificial intelligence technology, providing users with an efficient and convenient design experience. In traditional poster creation, users often spend a lot of time and effort searching for inspiration, gathering materials, and repeatedly adjusting layouts. However, the 'AI Poster' feature of Meitu WHEE will completely change this situation. Users will only need to input a simple sentence to easily generate posters in various styles.
Recently, Meitu Inc. launched a new feature for its image generation tool WHEE, which now supports the creation of Chinese posters. WHEE is renowned for its high-quality material generation, and this upgrade further enhances user experience and functional diversity. The AI poster generation feature of WHEE allows users to flexibly handle text layout. Due to the randomness and uncontrollable font styles present in traditional AI text layout, Meitu has innovatively made the text an editable independent layer. Users can not only drag freely