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
Settled by community votes across 1 shared challenge, with an AI judge weighing in on each.
Stable Diffusion 3.5 Medium
17.0
arena score
#41 of 44 in Text-to-Image
Skill signature
Not enough comparable category data
The chart appears once both models have ratings across at least three shared arena categories.
Wan 2.7 Pro
21.4
arena score
#29 of 44 in Text-to-Image
Vote tally
Where the votes landed
Stable Diffusion 3.5 Medium
0.0%
win rate
Ties
0.0%
Wan 2.7 Pro
100.0%
win rate
0.0%
0.0% ties
100.0%
Shared challenges
1
Challenge by challenge
The strongest take from each model on every shared challenge, with the AI judge's read.
The Halloween Invitation
Text-to-Image“Vintage gothic Halloween party invitation. Dark parchment poster, spooky border with webs and thorns, central glowing jack-o-lantern, bats, twisted trees, moody night sky. Add elegant gothic title text saying "Halloween Party Invitation", a small scroll banner saying "You are invited to a night of frights", and event details at the bottom: Date: 30.10.2026 Time: 7pm Location: The Arches, NYC Spooky but polished, cinematic lighting, square format.”
Stable Diffusion 3.5 Medium
Wan 2.7 Pro
0% wins
0% ties
100% wins
AI Judge Analysis
Stable Diffusion 3.5 Medium
- + Successfully incorporates twisted trees and bats into the background
- + The layout resembles a classic aged parchment poster
- − Numerous spelling errors including 'Halloweeen' and 'Inviloween'
- − Poor text rendering for the small details and location
- − Illogical placement of pumpkins in trees
Wan 2.7 Pro
- + Flawless text rendering for both titles and specific details
- + Exquisite artistic composition with cinematic lighting and a clear scroll banner
- + Perfect adherence to all prompt elements including the specific date and location
- − The jack-o-lantern is central but sits in a landscape rather than on a single parchment sheet
- − Slightly less 'gritty' gothic aesthetic in favor of a polished digital art look
Verdict: Wan 2.7 Pro followed the instructions perfectly, delivering an image with immaculate text rendering and a beautiful, balanced composition. Stable Diffusion 3.5 Medium struggled significantly with the text requirements, producing multiple spelling errors and garbled details that make the invitation unusable.
Next steps
Explore each model
Alibaba's Wan 2.7 Pro image generation and editing model with higher-quality outputs and support for 4K image generation