Distilled version of SD 3.5 Large that generates high-quality images in just 4 steps, offering faster inference and reduced costs
Settled by community votes across 2 shared challenges, with an AI judge weighing in on each.
Stable Diffusion 3.5 Large Turbo
6.0
arena score
#44 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.
Z-Image Turbo
24.7
arena score
#15 of 44 in Text-to-Image
Vote tally
Where the votes landed
Stable Diffusion 3.5 Large Turbo
0.0%
win rate
Ties
0.0%
Z-Image Turbo
100.0%
win rate
0.0%
0.0% ties
100.0%
Shared challenges
2
Challenge by challenge
The strongest take from each model on every shared challenge, with the AI judge's read.
Magic Burger Explosion: Fiery Photorealism Challenge
Text-to-Image“Ad for 'Magic Burger'. Dynamic, exploded burger with all components (bun, patty, cheese, lettuce, tomato, sauce) suspended in mid-air. Emphasize photorealistic detail and a sense of motion. Dark, fiery background with glowing embers. Integrate text: 'MAGIC BURGER' as a prominent title, 'LIMITED TIME ONLY' as a secondary message, and '€6.99' in a starburst, all rendered with a fiery, glowing effect.”
Stable Diffusion 3.5 Large Turbo
Z-Image Turbo
0% wins
0% ties
100% wins
AI Judge Analysis
Stable Diffusion 3.5 Large Turbo
- + Strong artistic interpretation of the fiery background
- + Vibrant colors and glowing embers create a high-energy feel
- − Completely failed to include any of the requested text
- − The burger is stacked normally rather than having 'exploded' suspended components
- − The bottom bun looks distorted and melting rather than photorealistic
Z-Image Turbo
- + Perfect text rendering for all three requested phrases
- + Excellent photorealistic detail on the burger patties and vegetables
- + Incorporates the starburst and fiery glowing effects as requested
- − The burger is tilted but not truly 'exploded' with suspended components
- − Slightly less 'dynamic' in terms of motion compared to the prompt's potential
Verdict: Stable Diffusion 3.5 Large Turbo failed all text-based instructions and produced more of a digital painting than a photorealistic ad. Z-Image Turbo followed almost every instruction, including complex text and specific UI elements like the starburst, resulting in a much more professional and accurate output.
Chalkboard Menu
Text-to-Image“Handwritten-style chalkboard menu in a cozy café, all text rendered in the exact same realistic chalk handwriting style with natural variations in letter size, slight slant, and chalk texture — no printed or digital fonts anywhere on the board. Title at the top in elegant cursive chalk handwriting: ‘TODAY’S SPECIALS – APRIL 30, 2026’. Below it, three menu items also in the same handwritten chalk style: ‘Truffle Mushroom Risotto – $24’, ‘Grilled Octopus with Lemon & Herbs – $28’, ‘Brown Butter Chocolate Chip Cookies – $9’. At the very bottom, smaller text in the identical handwritten chalk style (slightly smaller but still clearly legible with the same handwriting characteristics): ‘All items made fresh daily • Ask about our gluten-free options’. Warm ambient café lighting, visible chalk dust and smudges, realistic handwriting imperfections, no clean printed text anywhere.”
Stable Diffusion 3.5 Large Turbo
Z-Image Turbo
AI Judge Analysis
Stable Diffusion 3.5 Large Turbo
- + Features a pleasant café environment with realistic lighting and decor.
- + Good visual composition with a balanced layout.
- − Failed significantly on text rendering with multiple spelling errors and gibberish ('trulale', 'ocopus', 'apri 3L').
- − Text appears as a digital font overlay rather than realistic chalk texture.
- − Did not follow the specific menu item list requested in the prompt.
Z-Image Turbo
- + Excellent text rendering with near-perfect spelling and realistic chalk smudge textures.
- + Followed the prompt instructions precisely, including specific dates, items, and prices.
- + Handwriting style looks authentic with natural variations as requested.
- − Simple composition focusing only on the board rather than the 'cozy café' atmosphere.
- − Small typo in 'Mustroom' (Mushroom).
Verdict: Z-Image Turbo is the clear winner as it successfully rendered the complex text requirements and followed the prompt's specific menu items and date with high accuracy. Stable Diffusion 3.5 Large Turbo failed to produce legible or accurate text, resulting in a board full of spelling errors and font-like characters that lacked the requested chalk texture.
Next steps
Explore each model
Tongyi-MAI's 6-billion parameter distilled text-to-image model optimized for speed, achieving high-quality generation in 8 steps or fewer with support for bilingual text rendering