Midjourney has recently announced a series of exciting updates and upcoming new features, indicating the company's rapid development and innovation in the field of AI image generation.
Firstly, Midjourney is set to launch a new online editor, which will allow users to import images and utilize built-in depth maps and image restoration features for editing. The team is actively discussing which features will be included in the initial release and is optimizing the user interface to distinguish new features from existing image functionalities. Additionally, the content moderation function is operating well, ensuring compliance of platform content.
In terms of personalization features, Midjourney is developing new tools that will make it easier for users to manage and switch between multiple personalization configurations. These tools will support the activation of multiple personalization configurations and introduce a more refined style personalization system, further enhancing the user's creative experience.
Regarding the V7 model, Midjourney has resumed training the model after fixing previously identified bugs. The training and testing are expected to take several weeks, and the team anticipates improvements in several areas, including better understanding of prompts and enhanced multilingual processing capabilities. Before the official release, Midjourney will invest sufficient time in testing to ensure the model's performance meets expected standards.
Although the development of the video model is still ongoing, the team is discussing the types of video models to be developed, considering factors such as speed, resolution, and cost. They are also monitoring the increasing development costs of video models.
In the area of 3D models, Midjourney has collected the first large-scale 3D datasets and is ready to begin training 3D models. The team is evaluating whether 3D models should be an extension of 2D models or video models.
Furthermore, Midjourney is preparing articles on demographic and psychometric research, with preliminary results being satisfactory. They plan to integrate a new feature that allows users to exaggerate demographic characteristics to explore effects in extreme scenarios.
In terms of software development and hardware, Midjourney is recruiting experts in hardware and software development and discussing the possibility of developing desktop and mobile applications.
Finally, Midjourney is contemplating how to balance the development of multiple projects while maintaining rapid iteration. They are discussing whether to focus on a single project or to advance multiple projects simultaneously. Currently, the team's focus is on improving quality and developing core features, rather than rushing to release new products.