FP8 quantized variant of Black Forest Labs' FLUX.1 [schnell] model, offering ~2x faster inference with reduced precision while maintaining high-quality image generation in 4 steps
Settled by community votes across 2 shared challenges, with an AI judge weighing in on each.
FLUX.1 [schnell] FP8
17.8
arena score
#36 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
FLUX.1 [schnell] FP8
100.0%
win rate
Ties
0.0%
Z-Image Turbo
0.0%
win rate
100.0%
0.0% ties
0.0%
Shared challenges
2
Challenge by challenge
The strongest take from each model on every shared challenge, with the AI judge's read.
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.”
FLUX.1 [schnell] FP8
Z-Image Turbo
100% wins
0% ties
0% wins
AI Judge Analysis
FLUX.1 [schnell] FP8
- + Excellent chalk texture on the board surface
- + Correct date and title formatting
- + Realistic lighting and shadows within the café environment
- − Significant spelling errors and repetitive text hallucinations
- − The handwriting is all block letters instead of the requested cursive title
- − The prices and item names are scrambled and incoherent
Z-Image Turbo
- + Very high spelling accuracy across all menu items
- + Clean and legible layout
- + Correctly interpreted the incomplete prompt for 'Brown Butter Cookies'
- − The handwriting style is not cursive as specifically requested in the prompt
- − Text looks a bit too clinical despite the chalk texture
- − Minor spelling error in 'Mustroom'
Verdict: Z-Image Turbo is the clear winner as it successfully rendered almost all the requested text with high legibility and correct pricing, whereas FLUX.1 [schnell] FP8 suffered from significant text hallucinations and repetition. While neither model successfully produced 'elegant cursive' for the title, Z-Image Turbo's overall adherence to the menu content was far superior.
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.”
FLUX.1 [schnell] FP8
Z-Image Turbo
AI Judge Analysis
FLUX.1 [schnell] FP8
- + Strong cinematic lighting on the jack-o-lantern
- + Clean graphic design layout
- + Good centered jack-o-lantern illustration
- − Numerous spelling errors in the lower portion of the invitation
- − Fails to include the parchment texture requested
- − Text rendering is inconsistent across different lines
Z-Image Turbo
- + Excellent adherence to aesthetic details like parchment, thorns, and webs
- + Mostly accurate text rendering with clear gothic fonts
- + Dynamic composition with twisted trees and tombstones in the background
- − Minor typo in 'The Archves' (should be Arches)
- − The small scroll banner at the top is very tiny compared to the main text
Verdict: Z-Image Turbo is the clear winner as it successfully captured the requested 'dark parchment' and 'thorns and webs' aesthetic, whereas FLUX.1 [schnell] FP8 produced a dark gradient background instead. Furthermore, Z-Image Turbo rendered the event details with near-perfect accuracy and appropriate fonts, while FLUX.1 [schnell] FP8 suffered from significant spelling malfunctions in the bottom half of the image.
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