Stability AI

Stable Diffusion 3.5 Large

AI Image Generation Model

Image

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

How Stable Diffusion 3.5 Large performs

Rankings based on human votes in the Lumenfall Arena, where real users pick their favorite without knowing which model made which image.

All categories

Stable Diffusion 3.5 Large competes across 4 categories in the arena

Text Rendering

Text-to-Image

Ranked #13 of 23 models · 42.4% win rate Leaderboard

Stable Diffusion 3.5 Large

Same prompt, other models

Ranked using Apollo 11: Journey to Tranq... Modern Clean Menu Vintage Cafe Logo

Portrait

Text-to-Image

Ranked #16 of 21 models · 31.7% win rate Leaderboard

Stable Diffusion 3.5 Large

Same prompt, other models

Ranked using Fantasy Warrior

Photorealism

Text-to-Image

Ranked #18 of 23 models · 25.0% win rate Leaderboard

Stable Diffusion 3.5 Large

Same prompt, other models

Ranked using Candid Street Photography

Product, Branding & Commercial

Text-to-Image

Ranked #19 of 21 models · 21.6% win rate Leaderboard

Stable Diffusion 3.5 Large

Same prompt, other models

Ranked using Vintage Cafe Logo