Stability AI, the startup behind Stable Diffusion, a tool that uses generative artificial intelligence to create images from text prompts, revealed Stable Diffusion 3, the new generation model, on Thursday. Stability AI claimed that the new model, which is not yet widely used, improves image quality, works better with cues containing multiple subjects, and can generate more accurate text as part of the generated image, where previous Stable Diffusion models were not as good. hour.
Stability AI CEO Emad Mosque posted some examples of this on X.
The announcement comes just days after Stability AI’s biggest competitor, OpenAI. Sora presented, a new AI model capable of creating near-realistic, high-definition videos from simple text instructions. Sora, which has yet to be released to the general public, has raised concerns about its potential to create fake images that look real. OpenAI said it is working with experts on disinformation and hateful content to test the tool before making it widely available. Stability AI said it does the same. “[We] Stable Diffusion 3 has taken and continues to take reasonable steps to prevent misuse by bad actors,” the company wrote in a blog post on its website. “In continued collaboration with researchers, experts, and our community, we honestly look forward to further innovation as we move closer to the model’s public release.”
It’s unclear when Stable Diffusion 3 will be released to the public, but until then anyone interested can join. waiting list.
