Midjourney has released the alpha version of Midjourney V6, introducing enhancements in AI-generated imagery. The company, known for its AI models, has taken a major leap forward with features that include the generation of legible text within images and more realistic, detailed renderings.
Groundbreaking Features and Prompts
According to Midjourney CEO David Holz, V6 is the third model developed from scratch on the collective's AI superclusters and has evolved through nine months of dedicated development. With the promise of greater precision in prompt adherence and overall coherence, users are also greeted with new prompting methods. Midjourney has moved away from the technical prompting styles of prior versions, requiring users to learn a new, more sensitive approach to generate desired outputs. Holz emphasizes the removal of ‘junk' text and urges users to be explicit in their requests for most accurate results.
User Adaptation and Developmental Insights
As is typical with new technology iterations, it may take some time for users to adapt to the updated model. While a subset of users has praised V6 for its advancements, initial individual tests reveal the updates might not be immediately noticeable to all, but the potential for refinement and creativity is palpable. Although some features from V5.2 are currently absent, there are plans to include them in V6's future versions, indicating that Midjourney V6 is not the final stage but a step towards deeper integration with users' creative processes.
The release of Midjourney V6 has stirred excitement within the AI art community, demonstrating the collective's commitment to pushing the boundaries of AI-powered creativity. While the tool faces the usual challenges inherent to AI art technologies, including ongoing legal discussions concerning the training of such models, Midjourney continues to assert its leading position in the competitive landscape of AI artwork generation.
Other Notable AI Image Generators
- OpenAI has also introduced ShapE, a generative model that can create 3D models from text, opening up new possibilities for AI in image creation. The company also recently launched its DALL-E 3 image generating art model.
- Microsoft partners with OpenAI to bring Bing Image Creator, which has recently been integrated with DALL-E 3.
- Stability AI, a startup that focuses on generative AI, has released StableStudio, an open-source web app that uses its Stable Diffusion model to generate images from text prompts. Users can also use DreamStudio features to make multiple variations of an image with different styles and attributes.
- Meta, the company formerly known as Facebook, is already in this field and has unveiled I-JEPA, its own AI image generator based on its generative transformer model. I-JEPA can learn the associations between words and images, and generate realistic images from text descriptions.
- Alibaba, the Chinese e-commerce giant, has launched Tongyi Wanxiang, a generative AI image generator that can handle both Chinese and English languages. Users can customize the image output parameters using Composer, a large model developed by Alibaba Cloud.
- Chip giant Nvidia debuted its Perfusion AI art creation tool in August.
