Stability AI, the startup behind Stable Diffusion, the tool that uses generative AI to create images from text prompts, revealed Stable Diffusion 3, a new generation model, Thursday. Stability AI claimed that the new model, which is not yet widely available, improves image quality, works better with prompts containing multiple topics, and can display more accurate text as part of the generated image, what previous stable diffusion models were not great at. has.
Emad Mosque, CEO of Stability AI, published some examples on X.
This announcement comes days after Stability AI's biggest rival, OpenAI, revealed Sora, a brand new AI model capable of generating near-realistic high-definition videos from simple text prompts. Sora, which is not yet available to the general public, has sparked concerns about its potential to create fake realistic images. OpenAI said it was working with experts in misinformation and hateful content to test the tool before making it widely available. Stability AI said it does the same. “(We) have taken and continue to take reasonable steps to prevent the misuse of Stable Diffusion 3 by bad actors,” the company wrote in a blog post on its website. “By continually collaborating with researchers, experts, and our community, we hope to further innovate with integrity as the model approaches public release.” »
It's unclear when Stable Diffusion 3 will be released to the public, but until then, anyone interested can join. a waiting list.