Stable Diffusion 3 is officially released, taking AI mapping technology a step further!
Stable Diffusion 3 is here!
Just as the public was cooling off a bit from the shock of Sora, Stability AI dropped a bomb: Stable Diffusion 3. Stability AI says this is their most powerful grammatical model yet, with greatly improved performance for multi-topic prompts, image quality, and spelling capabilities. The current parameter range for the Stable Diffusion 3 model suite is 800M to 8B. Details: https://stability.ai/news/stable-diffusion-3
In addition, Stable Diffusion 3 seems to have an understanding of the physical world. Stability AI also revealed that, like Sora, they have adopted the diffusion transformer architecture in the new model, but the access rights have not yet been officially opened. Friends can go to the link below Apply.
Stability AI CEO Emad Mostaque posted on X that the model will be open sourced after everything is debugged.
The prompt in the picture posted is Epic anime artwork of a wizard atop a mountain at night casting a cosmic spell into the dark sky that says “Stable Diffusion 3” made out of colorful energy Chinese translation: Prompt: At night, a wizard stands Mountain top casting a cosmic spell into the dark sky, the spell reads “Steady Diffusion 3”, made of colorful energy
