USA: A photo of Pope Francis sauntering in a Balenciaga puffer jacket went viral earlier this year. Many people were surprised to learn that the image was a hoax. It was generated by AI. It was created specifically with the AI art generator Midjourney. Midjourney 5.1, the most recent version of the AI service, has been released. It promises improved images, but what about the concerns?
With the introduction of ChatGPT and its subsequent popularity, text-to-text AI has become the poster child of the AI revolution. We must not, however, forget that AI is capable of dressing the Holy Father in designer attire. Text-to-image AIs such as Midjourney, Stable Diffusion, and DALL-E are capable of outperforming real-world photographs. As these tools improve, we must consider how they will impact social discourse.
Midjounrey 5.1 is more opinionated than previous versions, so even short prompts can produce images. There is a 'RAW' mode for those who enjoy the Midjourney 5's unpredictability. Other enhancements include increased coherence, better response to prompts, fewer borders or text artefacts, and sharper image quality, according to the company.
Also Read: You can see Eta Aquarids meteor shower on May 4-5
Version 4 is currently the default version of Midjourney. Version 5.1 will be released to replace it. Midjourney has also added a feature called 'AI moderation.' In contrast to previous versions and older models, AI moderation can understand words in context and detect violations. A user may object if there is a violation. Another powerful AI system will evaluate the objection.
The company is ushering in the next generation of AI art with the latest version of Midjourney. Midjourney 5.1 can produce more natural-looking images. It also has better dynamic compositions and uses colours better than Midjourney 5. Midjourney 5.1 images can appear to be taken by a professional photographer.
Also Read: S.Korea, Indonesia to seek stronger economic ties, Details Inside
We began by discussing an AI-generated image of Pope Francis. Although we know it's a hoax, many people believed it was genuine. That wasn't even the most perplexing aspect of an AI-generated image. Many people believed that photos of Donald Trump being arrested were genuine. The consistently improving quality of AI-generated images has made it difficult to distinguish between real and fake.
We live in an age when information spreads like wildfire. The interconnected web of social media accounts has made information sharing extremely simple. This has also led to an increase in misinformation. The veracity of information is now way down the priority list. Likes, shares, and retweets, among other things, are becoming increasingly important.
The hyper-realistic nature of AI-generated images makes disinformation easy to spread. The plausibility of an image is sufficient to persuade the general public.
Also Read: Water vapour is found around an alien planet by the James Webb Space Telescope
The lack of context makes it even more difficult to distinguish AI images. The ability of Midjourney 5.1 to create better images than its predecessors or competitors will be tested against these issues.
It should be noted that we have yet to develop a robust solution to deal with fake AI art designed to deceive people. Some cues and properties aid in the differentiation of an AI-generated image from a real one. The hands of people in AI images are one of the most obvious telltale signs. Midjourney has been working on that. Other flaws would vanish in the same way.