Excels at photorealism, typography, and prompt following. Works best in 1024x1024.
Approx. Price
$0.018 per image
Model Type
image
Settings
Generation controls available for this model.
Images Per Run
Up to 4
Output images
Input Images
N/A
No reference/edit image input
Output Sizes
Negative Prompt
Default
N/A
Num Steps
Default
28
Number of Images
Default
1
Resolution
Default
1024x1024
Options (3)
512x512 (0.25x price), 1024x1024, 2048x2048 (4x price)
Sampler Name
Default
FlowMatchEuler
Scale
Default
4
Benchmarks
Benchmarks
Human preference benchmarks sourced from Artificial Analysis.
Text to Image
#135 / 148
ELO
910.0
Appearances
11,943
95% CI
-9/9
Release Date 2024-06 · Matched as Stable Diffusion 3 Medium
Artificial Analysis APIExamples
Loading examples…
Related image models
Compare Stable Diffusion 3 Medium with similar models from the same provider or model family.
Stable Diffusion XL
fast-sdxlCheap and powerful text-to-image model that generates pictures rapidly.
SD 3.5 Large
stable-diffusion-v35-largeStable Diffusion's newest model. Generates a wide variety of images reflecting different styles without complex prompting.
SD 3.5 Large Turbo
stable-diffusion-v35-large/turboTurbo version of Stable Diffusion's newest model. Faster and cheaper performance while still maintaining great prompt adherence and quality.
Fluently XL V3 Lightning
stable-diffusion-xl-turboFluently XL V3 Lightning - Fast, high-quality image generation. CivitAI model 324891@408626.
Krea 2 Medium Turbo
wavespeed-ai/krea-v2-medium-turbo/text-to-imageKrea 2 Medium Turbo generates high-fidelity images extremely fast with aspect ratio, creativity, seed controls, and optional style references.
Krea 2 Medium
wavespeed-ai/krea-v2-medium/text-to-imageKrea 2 Medium generates high-quality images from text prompts with aspect ratio, creativity, and optional style reference controls.