Stability AI's 8.1-billion parameter Multimodal Diffusion Transformer (MMDiT) text-to-image model featuring improved image quality, typography, complex prompt understanding, and resource-efficiency
Gallery
14 itemsThis gallery features 14 images generated by Stable Diffusion 3.5 Large, including 3 curated high-fidelity examples and 11 results from head-to-head arena competitions. These samples demonstrate the model's ability to handle complex typography and resource-efficient image synthesis.
Cinematic wide shot of a high-end, minimalist flagship store in a bustling me...
A portrait of an elderly artisan in a sun-drenched Mediterranean workshop, me...
A cozy street-side bakery with a chalkboard sign out front that reads "FRESH ...
Create a clean, modern vector infographic poster about the Apollo 11 mission....
Close portrait of a battle-worn paladin in ornate engraved plate armor, hair ...
Hyper-photorealistic interior of a lush Victorian glass greenhouse filled wit...
Modern minimalist restaurant menu design, white background with colorful food...
Create a clear, 45° top-down isometric miniature 3D cartoon scene of Japan's ...
A glass cube on a wooden table. Inside the cube is a small blue sphere. On to...
Vintage minimalist restaurant logo for "Caffè Florian", retro cloche dome wit...
Perfectly symmetrical mandala made entirely of real flowers, petals, leaves, ...
Hyper-photorealistic scene of fluffy baby animals—a golden retriever puppy, t...
A candid street photo of an elderly Japanese man repairing a red bicycle in l...
Hyper-photorealistic full-body portrait of a female superhero standing triump...