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 13 shared challenges, with an AI judge weighing in on each.
FLUX.1 [schnell] FP8
#47 of 62 in Text-to-Image
Stable Diffusion 3.5 Medium
#58 of 62 in Text-to-Image
Where the votes landed
FLUX.1 [schnell] FP8
0.0%
win rate
Ties
50.0%
Stable Diffusion 3.5 Medium
50.0%
win rate
Challenge by challenge
The strongest take from each model on every shared challenge, with the AI judge's read.
Geometric Composition
Text-to-Image“A glass cube on a wooden table. Inside the cube is a small blue sphere. On top of the cube sits a red book. A green plant is behind the cube, partially visible through the glass. Soft window light from the left.”
AI Judge Analysis
FLUX.1 [schnell] FP8
- + Excellent photorealism and high visual quality.
- + Realistic handling of light and reflections within the glass.
- + Accurately places the green plant behind the cube as requested.
- − The cube is elongated, appearing more like a rectangular prism than a perfect cube.
- − The blue sphere is resting on a shelf inside the cube rather than appearing as a simple sphere inside.
Stable Diffusion 3.5 Medium
- + Correctly adheres to the 'cube' geometry.
- + Captures the levitating or centered placement of the blue sphere well.
- − Lower overall image quality with visible grain and less realistic lighting.
- − The sphere has strange artifacts and lacks a coherent light source reflection.
- − The plant is visible behind the cube but the glass refraction is less convincing.
Verdict: FLUX.1 [schnell] FP8 produces a much more polished and aesthetically pleasing image with professional-grade lighting and textures, though it interpreted the cube as a taller prism. Stable Diffusion 3.5 Medium followed the geometric prompt of a 'cube' more accurately but failed significantly in terms of visual fidelity, resulting in a flat and noisy image. FLUX.1 [schnell] FP8 is the preferred choice for its superior realism and composition.
Candid Street Photography
Text-to-Image“A candid street photo of an elderly Japanese man repairing a red bicycle in light rain, reflections on wet pavement, shallow depth of field, 50mm lens, natural skin texture, imperfect framing, motion blur from passing cars, cinematic but realistic, no stylization.”
AI Judge Analysis
FLUX.1 [schnell] FP8
- + Excellent anatomical details on the man's hands and face
- + Superior technical realism for the red bicycle's construction
- + Very realistic reflections and high-quality background bokeh
- − Fails to include visible rain or motion blur requested in the prompt
- − Composition feels a bit too clean and centered for 'imperfect framing'
Stable Diffusion 3.5 Medium
- + Successfully captures the light rain and motion blur for passing cars
- + Effective use of 'imperfect framing' and cinematic composition
- + Strong adherence to the wet, moody atmosphere requested
- − Anatomical errors in the hands and facial features
- − The bicycle design is inconsistent and lacks structural logic in several places
Verdict: FLUX.1 [schnell] creates a much more technically polished image with realistic human features and a believable bicycle, but it completely ignores the request for rain and motion blur. Stable Diffusion 3.5 Medium adheres much better to the specific atmosphere and environmental requirements of the prompt, though it fails significantly on the details of the man and the bike.
Fantasy Warrior
Text-to-Image“Close portrait of a battle-worn paladin in ornate engraved plate armor, hair braided with small beads, faint scars and dirt on the skin, warm torchlight reflecting off metal, shallow depth of field, bokeh sparks, lifelike eyes, highly detailed texture on leather straps and cloth underlayer.”
AI Judge Analysis
FLUX.1 [schnell] FP8
- + Exceptional sharpness and clarity in the facial features and skin texture
- + Strong emotional intensity in the eyes and expression
- + Highly detailed engraving on the leather and armor trim
- − Missed the request for braided hair
- − The 'armor' looks more like leather and fabric than plate metal
- − Bokeh sparks from the prompt are mostly missing or generic
Stable Diffusion 3.5 Medium
- + Excellent adherence to all prompt elements including braids, scars, and bokeh sparks
- + Realistic metallic sheen on the plate armor with reflecting light
- + Strong gritty atmosphere that feels 'battle-worn'
- − Slightly lower facial clarity compared to the competitor
- − Some muddy textures on the forehead skin
Verdict: While FLUX.1 [schnell] FP8 produces a higher-resolution face with more striking eyes, it fails to include the requested braids and plate armor. Stable Diffusion 3.5 Medium followed the prompt much more accurately, successfully incorporating the braided hair, bokeh sparks, and distinct metallic plate armor surface.
Modern Clean Menu
Text-to-Image“Modern minimalist restaurant menu design, white background with colorful food photos in grid, sections for appetizers/pizza/mains, bold sans-serif fonts, vibrant accents, clean professional layout for casual dining.”
AI Judge Analysis
FLUX.1 [schnell] FP8
- + Excellent typography and layout structure that mimics a real menu
- + Clean, high-resolution food photography that fits the grid perfectly
- + Contains specific sections as requested in the prompt
- − Typos in section headings like APPTIZERS and PIZZAL
- − The SECCER heading is nonsensical
Stable Diffusion 3.5 Medium
- + Good variety of food images with professional-looking lighting
- + Successful grid layout with consistent image sizing
- − Text is largely unintelligible and poorly rendered
- − Poor alignment of text elements compared to the grid
- − Fails to clearly label the specific sections requested, like pizza or mains
Verdict: FLUX.1 [schnell] FP8 is the clear winner for its superior layout design and typography, which much more closely resembles a professional restaurant menu. While both models struggle with spelling, FLUX.1 [schnell] FP8 provides a cleaner aesthetic and more logical organization of information compared to the cluttered text in Stable Diffusion 3.5 Medium.
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.”
AI Judge Analysis
FLUX.1 [schnell] FP8
- + Excellent photographic texture on the meat patty and bun.
- + Vibrant color palette with high contrast.
- + Good implementation of the scattered ingredients/motion effect.
- − Significant text errors including 'LIIMITED' and 'NEEY'.
- − Incorrect price rendering at €69 and €.99 instead of €6.99.
- − The burger is mostly assembled rather than 'exploded' into major layers.
Stable Diffusion 3.5 Medium
- + Perfect text rendering for all requested strings including the price.
- + Strong fiery aesthetic with glowing embers that matches the prompt well.
- + The starburst design for the price is creative and clear.
- − Fails the 'exploded' instruction as the burger is almost entirely intact.
- − The main title text lacks the requested 'fiery, glowing effect'.
- − The burger bun texture looks slightly plastic or overly smoothed.
Verdict: Stable Diffusion 3.5 Medium is the winner primarily due to its superior handling of the complex text requirements, correctly rendering every word and the specific price. While FLUX.1 [schnell] FP8 produced a more appetizing meat texture and better ingredient suspension, its significant spelling errors and price inaccuracies make it less viable for an actual advertisement.
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.”
AI Judge Analysis
FLUX.1 [schnell] FP8
- + Excellent adherence to the specific date requested
- + Natural-looking chalk texture on the lettering
- + Balanced composition with realistic frame lighting
- − Repeated words and inconsistent pricing in the menu body
- − Spelling errors in secondary menu items
- − White marker-style look rather than soft cursive chalk requested for the header
Stable Diffusion 3.5 Medium
- + Stylized artistic chalk flourishes
- + Great visual texture of a used chalkboard with smudges
- + Composition feels like a designer menu board
- − Severe failures in spelling and word rendering
- − Failed to include the specific date of April 30, 2026 accurately
- − Text is largely illegible gibberish
Verdict: FLUX.1 [schnell] is the clear winner as it successfully rendered the specific date and most of the requested menu items with decent legibility, despite some repetition and minor spelling errors. Stable Diffusion 3.5 Medium produced a more artistic chalkboard aesthetic but failed significantly on prompt adherence, resulting in nonsensical text and an incorrect date.
The Reversed Rodeo
Text-to-Image“Horse riding astronaut in space — horse on top, not vice versa. Surreal, highly detailed, cinematic.”
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 Capybara Taxi Driver
Text-to-Image“Photorealistic scene inside a yellow New York taxi at night. A capybara is driving, wearing a yellow taxi driver cap and a dark jacket. It has a calm, professional expression and both front paws on the steering wheel. In the back seat sits a human businesswoman in a coat, looking at her phone with a completely normal, bored expression (as if this is just another normal ride). Through the windows you can see the streets of Manhattan at night with blurred lights. Realistic taxi interior, photorealistic, detailed fur and fabric, 35mm lens, night lighting with reflections, shallow depth of field.”
AI Judge Analysis
FLUX.1 [schnell] FP8
- + Excellent text rendering on the driver's cap.
- + Very clear and detailed taxi interior with accurate lighting.
- + Captures the businesswoman and her phone as requested in the background.
- − The woman is holding two phones, which is a logic error.
- − The capybara's head looks a bit pasted onto the jacket.
Stable Diffusion 3.5 Medium
- + The capybara driver has a very professional and cute expression.
- + The paws are positioned well on the steering wheel.
- + The hat design looks very authentic to a professional driver's uniform.
- − Missed the detail about the passenger looking at her phone.
- − The perspective makes the taxi look extremely small relative to the capybara.
- − Low background detail for the passenger.
Verdict: FLUX.1 [schnell] FP8 wins because it accurately includes all elements of the prompt, including the passenger and the phone, whereas Stable Diffusion 3.5 Medium completely ignored the instruction for the passenger to be looking at her phone. While FLUX.1 had an artifact issue with the woman holding two phones, its overall composition and adherence to the 'taxi interior' feel were much stronger.
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.”
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.
Isometric Miniature Diorama Scenes
Text-to-Image“Create a clear, 45° top-down isometric miniature 3D cartoon scene of Japan's signature dish: sushi, with soft refined textures, realistic PBR materials, gentle lighting, on a small raised diorama base with minimal garnish and plate. Solid light blue background. At top-center: 'JAPAN' in large bold text, 'SUSHI' below it, small flag icon. Perfectly centered, ultra-clean, high-clarity, square format.”
AI Judge Analysis
FLUX.1 [schnell] FP8
- + Excellent 3D miniature/cartoon aesthetic that matches the 'soft refined textures' prompt.
- + High clean visual quality with professional lighting and shadows.
- − Failed to render the word 'SUSHI' correctly.
- − The text 'JAPAN' is repetitive and includes a nonsensical flag integration.
Stable Diffusion 3.5 Medium
- + Successfully rendered both words 'JAPAN' and 'SUSHI' with high clarity.
- + Good realistic PBR-style textures on the nori and roe.
- − Missed the 'small raised diorama base' instruction, placing it on a simple plate.
- − The light blue background feels flat rather than a 3D isometric environment.
Verdict: Each model succeeded where the other failed: Stable Diffusion 3.5 Medium followed the text instructions perfectly but failed on the 3D diorama composition, while FLUX.1 [schnell] FP8 nailed the aesthetic and composition but completely failed the specific text requirements. FLUX is slightly preferred for the overall visual appeal and adherence to the 'isometric miniature' theme.
Adorable Baby Animals in Sunny Meadow
Text-to-Image“Hyper-photorealistic scene of fluffy baby animals—a golden retriever puppy, tabby kitten, baby bunny, and red fox kit—with big expressive eyes and ultra-detailed soft fur, playfully chasing butterflies and tumbling together in a lush wildflower meadow, warm golden sunrise light with god rays and dew sparkles, joyful wholesome vibe, 8K masterpiece.”
AI Judge Analysis
FLUX.1 [schnell] FP8
- + Excellent depiction of soft, ultra-detailed fur textures.
- + High animal count creates a dense, joyful composition.
- + Superior lighting effects with hazy golden hour glow and god rays.
- − Missed the baby bunny prompt requirement.
- − Anatomical issues with overlapping limbs and an extra ambiguous animal head at the bottom right.
- − The kitten's mouth and some butterfly wings appear slightly distorted.
Stable Diffusion 3.5 Medium
- + Features a clearer golden retriever and fox kit with good distinction.
- + Vibrant colors and high contrast in the wildflower meadow.
- + Follows the general composition requested with animals in a lush setting.
- − Failed to include a rabbit or a distinct tabby kitten.
- − The blue butterfly is rendered with strange artifacts and floating legs.
- − Less 'hyper-photorealistic' and more illustrative/saturated compared to the other model.
Verdict: Both models failed to include all four requested animals, specifically omitting the baby bunny. FLUX.1 [schnell] FP8 offers much better fur detail and cinematic lighting that fits the '8K masterpiece' requirement, whereas Stable Diffusion 3.5 Medium has a more generic, oversaturated look with noticeable artifacts on the butterflies. FLUX.1 is the winner for its superior texture and atmosphere, despite the anatomical clipping in the huddle.
Vintage Cafe Logo
Text-to-Image“Vintage minimalist restaurant logo for "Caffè Florian", retro cloche dome with steam and "Est. 1720" banner, classic typography, warm brown and cream tones, subtle texture on light background, vector emblem style.”
AI Judge Analysis
FLUX.1 [schnell] FP8
- + Strong minimalist vector aesthetic
- + Clean, balanced emblem composition
- + Accurate date 'Est. 1720' rendering
- − Major spelling errors in the primary name ('AFE FLAMILAN')
- − The 'cloche' looks more like a building dome
Stable Diffusion 3.5 Medium
- + Captures the 'retro cloche' shape more effectively
- + Spelling of 'Florrian' is closer to the prompt than model a
- + Beautiful hand-drawn engraving style
- − Incorrect date text ('Est 170')
- − Too detailed/busy for a minimalist logo
- − Extra character in the name ('Florrian' instead of 'Florian')
Verdict: Both models struggled with the specific text and minimalism. FLUX.1 [schnell] FP8 produced a much cleaner vector-style logo but failed significantly on the brand name, whereas Stable Diffusion 3.5 Medium captured the requested cloche shape and name better but failed on the date and simplicity. FLUX.1 [schnell] FP8 is the preferred choice as a logo base due to its superior layout and clarity.
Apollo 11: Journey to Tranquility
Text-to-Image“Create a clean, modern vector infographic poster about the Apollo 11 mission. NASA-inspired palette (navy, white, muted red, light gray). Flat-vector style, crisp lines, consistent iconography, subtle gradients only. Steps (stop at landing): 1. Launch (Saturn Vicon) 2. Earth Orbit (Earth + orbit ring icon) 3. Translunar (trajectory arc icon) 4. Lunar Orbit (Moon + orbit ring icon) 5. Descent (lunar module descending icon) 6. Landing (lunar module on the surface icon) Small supporting elements (minimal text): • Crew strip: three silhouette icons with only last names: Armstrong, Aldrin, Collins. • Landing site marker: Moon pin labeled "Tranquility" only. Layout constraints: generous margins, large readable labels, clean background with subtle stars. Vector-only, print-poster look, high resolution.”
AI Judge Analysis
FLUX.1 [schnell] FP8
- + Excellent adherence to the clean, modern vector style.
- + Follows the NASA-inspired color palette perfectly.
- + Includes distinct icons for the requested steps with a logical horizontal layout.
- − Nonsense filler text below the main heading.
- − The lunar module illustration is a bit abstract and fragmented.
Stable Diffusion 3.5 Medium
- + Creative use of orbits and arcs to fill the space.
- + Clean font for the main labels.
- − Failed the vector aesthetic, appearing more like a grainy painting or scan.
- − Icons are inconsistent and do not clearly represent the specific steps requested (e.g., 'Launch' shows a map fragment).
- − Included excessive 'star' noise that clashes with the requested 'clean' look.
Verdict: FLUX.1 [schnell] is the clear winner as it successfully delivered a clean, professional vector infographic that followed the layout and color instructions. In contrast, Stable Diffusion 3.5 Medium produced a cluttered, textured image with poor iconography that did not match the requested flat-vector style.
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