Stability AI
3 AI Image Generation Models
Models
3 models
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
Distilled version of SD 3.5 Large that generates high-quality images in just 4 steps, offering faster inference and reduced costs
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
Examples
9 imagesArena Rankings
Text to Image
View full leaderboard| # | Model | Elo |
|---|---|---|
| 23 | Stable Diffusion 3.5 Large | 1233 |
|
18 more models
|
||
| 42 | Stable Diffusion 3.5 Medium | 1129 |
| 43 | Stable Diffusion 3.5 Large Turbo | 1062 |
43 models ranked
Top Matchups
Head-to-head results between Stability AI models and competitors, based on community votes in blind comparisons.
Stable Diffusion 3.5 Large vs Seedream 4.5
Challenge: Isometric Miniature Diorama Scenes
20% W · 80% L
Stable Diffusion 3.5 Large vs ImagineArt 1.5 (Preview)
Challenge: Geometric Composition
0% W · 100% L
Stable Diffusion 3.5 Large Turbo vs GPT Image 2
Challenge: Magic Burger Explosion: Fiery Photorealism Challenge
0% W · 100% L
Stable Diffusion 3.5 Medium vs GPT Image 2
Challenge: The Reversed Rodeo
0% W · 100% L