Stable Diffusion 3.5 Medium

AI Image Generation Model

Image $$ · 2¢

Stability AI's 2.5-billion parameter Multimodal Diffusion Transformer with improvements (MMDiT-X) text-to-image model optimized for consumer hardware, featuring improved image quality, typography, and complex prompt understanding

How Stable Diffusion 3.5 Medium 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 Medium competes across 1 category in the arena

Art

Text-to-Image
Ranked #2 of 3 models · 25.0% win rate Leaderboard
Stable Diffusion 3.5 Medium
Same prompt, other models