Stable Diffusion 3 was released last night. As a more powerful text-to-image model, it has significantly improved in handling multi-subject prompts, image quality, and spelling ability.
Prompt: 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
Apply for access at https://stability.ai/stablediffusion3
Technology
The parameter range of the Stable Diffusion 3 model suite currently varies from 800M to 8B, offering users multiple scalability and quality options to best meet various creative needs. Stable Diffusion 3 combines the diffusion transformer architecture with flow matching technology.
). The paper can be found at https://arxiv.org/abs/2212.09748.
The flow matching paper can be found at https://arxiv.org/abs/2210.02747.
Effectiveness
Prompt: studio photograph closeup of a chameleon over a black background
Prompt: Resting on the kitchen table is an embroidered cloth with the text 'good night' and an embroidered baby tiger. Next to the cloth there is a lit candle. The lighting is dim and dramatic.
Comparison
Prompt: cinematic photo of a red apple on a table in a classroom, on the blackboard are the words "go big or go home" written in chalk
Stable Diffusion 3
Midjourney v 6.0
Gemini Advanced / Ultra
Prompt: a painting of an astronaut riding a pig wearing a tutu holding a pink umbrella, on the ground next to the pig is a robin bird wearing a top hat, in the corner are the words "stable diffusion"
Stable Diffusion 3
Bing
Midjourney v 6.0
DALLE-3
Gemini Advanced