Stability AI

Stable Diffusion 3.5 Large

AI Image Generation Model

Mode:

All Text to Image Image Edit

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

What Stable Diffusion 3.5 Large is good at

Rankings based on human votes in the Lumenfall Arena, where real users pick their favorite without knowing which model made which image. Excels at #15 Text Rendering (Text-to-Image) , placing in the top 39% of all competing models.

Stable Diffusion 3.5 Large Strengths

Stable Diffusion 3.5 Large outperforms most competing models here

Text Rendering

Text-to-Image

Ranked #15 of 37 models · 43.3% win rate Leaderboard

Stable Diffusion 3.5 Large

Same prompt, other models

Ranked using Apollo 11: Journey to Tranq... Chalkboard Menu Magic Burger Explosion: Fie... Modern Clean Menu The Halloween Invitation Vintage Cafe Logo

Other categories

Stable Diffusion 3.5 Large competes but doesn't rank as highly

Photorealism

Text-to-Image

Ranked #27 of 38 models · 25.0% win rate Leaderboard

Stable Diffusion 3.5 Large

Same prompt, other models

Ranked using Candid Street Photography Chalkboard Menu Magic Burger Explosion: Fie... The Capybara Taxi Driver The Reversed Rodeo

Portrait

Text-to-Image

Ranked #17 of 23 models · 30.4% win rate Leaderboard

Stable Diffusion 3.5 Large

Same prompt, other models

Ranked using Fantasy Warrior

Product, Branding & Commercial

Text-to-Image

Ranked #22 of 29 models · 24.5% win rate Leaderboard

Stable Diffusion 3.5 Large

Same prompt, other models

Ranked using Magic Burger Explosion: Fie... Vintage Cafe Logo