As reported by AIBASE, on September 5th, Jimeng AI, a subsidiary under ByteDance, rolled out Jimeng Pictures Version 4.0. This new release represents a significant milestone as it introduces, for the first time, support for multimodal image generation. This innovative system seamlessly combines text-to-image conversion, image editing, and batch image generation functions within a unified model framework. Notably, the text-to-image feature stands out for its ability to generate images with a resolution of 2K in just 1.8 seconds, with the capability to produce images up to a maximum resolution of 4K.