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.
Stable Diffusion 3.5 Medium
15.7
arena score
#41 of 44 in Text-to-Image
Vote tally
Where the votes landed
FLUX.1 [schnell] FP8
0.0%
win rate
Ties
50.0%
Stable Diffusion 3.5 Medium
50.0%
win rate
0.0%
50.0% ties
50.0%
Shared challenges
2
Challenge by challenge
The strongest take from each model on every shared challenge, with the AI judge's read.
The Reversed Rodeo
Text-to-Image“Horse riding astronaut in space — horse on top, not vice versa. Surreal, highly detailed, cinematic.”
FLUX.1 [schnell] FP8
Stable Diffusion 3.5 Medium
0% wins
100% ties
0% wins
AI Judge Analysis
FLUX.1 [schnell] FP8
- + Excellent adherence to the complex spatial instruction of putting the horse on top.
- + High cinematic quality with dramatic lighting and a beautiful planetary background.
- + Creatively interprets the 'astronaut' part as a literal piece of hardware or a mechanical construct being ridden.
- − Anatomy of the horse in the background is a bit distorted and strange.
- − The 'astronaut' is depicted as a machine rather than a person in a suit, which might deviate from some expectations.
Stable Diffusion 3.5 Medium
- + Very clear and sharp stars and planet rendering.
- + Classic, clean rendering of an astronaut suit and a white horse.
- − Completely failed the primary prompt instruction of having the horse on top.
- − Anatomical issues with the horse's legs appearing elongated and deformed.
- − The composition is generic and lacks the requested 'surreal' quality.
Verdict: FLUX.1 [schnell] FP8 successfully followed the difficult prompt constraint of placing the horse on top of the astronaut/equipment, resulting in a much more surreal and interesting image. Stable Diffusion 3.5 Medium ignored the specific positioning instruction and produced a standard astronaut-on-horse image with significant anatomical errors in the horse's legs.
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
Stable Diffusion 3.5 Medium
0% wins
0% ties
100% wins
AI Judge Analysis
FLUX.1 [schnell] FP8
- + Strong cinematic lighting with a vibrant glowing jack-o-lantern.
- + The composition feels cohesive and professionally balanced.
- + Features the twisted trees and bats as requested in a moody atmosphere.
- − Significant text errors including 'Tine' and 'Theaches'.
- − The scroll banner text is split awkwardly and misspelled.
Stable Diffusion 3.5 Medium
- + Better execution of the 'dark parchment' and spider web border elements.
- + Includes multiple jack-o-lanterns and clear twisted tree silhouettes.
- + Large, legible gothic-style font.
- − Major text typos such as 'Halloweeen Inviloween' and 'Loccation'.
- − The date and time are missing or heavily mangled (Year '226').
Verdict: Both models struggled significantly with the specific text requirements, but FLUX.1 [schnell] FP8 produced a much more 'polished' and 'cinematic' image as requested by the prompt. While Stable Diffusion 3.5 Medium captured the vintage parchment aesthetic well, its text errors were more distracting and the overall composition felt less premium than FLUX.1's atmospheric lighting.
Next steps
Explore each model
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