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
#46 of 62 in Text-to-Image
Z-Image Turbo
#12 of 62 in Text-to-Image
Where the votes landed
FLUX.1 [schnell] FP8
100.0%
win rate
Ties
0.0%
Z-Image Turbo
0.0%
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 handling of complex glass reflections and light refraction
- + High aesthetic quality with vibrant colors and sharp details
- + Accurate placement of the plant partially visible through the glass
- − The cube geometry is slightly tall, resembling more of a rectangular prism
- − Includes an internal shelf that was not requested in the prompt
Z-Image Turbo
- + Strict adherence to the basic geometric shape of a cube
- + Realistic textures on the book and wooden table surface
- + Accurate sphere placement resting on the base of the cube
- − Overall image is a bit soft and lacks the crispness of Model A
- − The plant in the background is less distinct through the glass
- − A white artifact or smudge is visible on the right face of the glass cube
Verdict: While both models followed the prompt instructions accurately, FLUX.1 [schnell] FP8 produced a more visually striking image with superior light refraction through the glass. Z-Image Turbo followed the geometric cube shape more strictly but lacked the clarity and polished finish of FLUX.1.
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 handling of wet pavement reflections and bokeh.
- + Strong cinematic composition with beautiful color contrast.
- + High level of detail in skin texture and facial features.
- − Lack of visible rain falling despite the wet surfaces.
- − The man's scale relative to the bike feels slightly off, appearing very large.
Z-Image Turbo
- + Successfully depicts falling rain streaks.
- + The man's anatomical proportions and age markers are very realistic.
- + Good adherence to the 'candid' and 'imperfect framing' request.
- − Lighting is somewhat flat compared to the 'cinematic' request.
- − The background cars lack the requested motion blur.
- − Hand-to-handlebar interaction is slightly unnatural.
Verdict: FLUX.1 [schnell] FP8 delivers a more cinematic and visually striking image with superior lighting and reflections, though it fails to render the falling rain. Z-Image Turbo captures the atmospheric rain better and feels more like a genuine candid snapshot, but it lacks the depth of field and motion blur specified in the prompt. Overall, FLUX.1 [schnell] FP8 is preferred for its high technical quality and adherence to the 50mm lens look.
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
- + Intense, high-contrast lighting that emphasizes skin texture
- + Strong follow-through on the 'close portrait' aspect
- + Extremely sharp facial details and lifelike eye iris rendering
- − Missed the explicit request for braided hair with beads
- − The armor details are obscured by the very tight framing
- − Skin appears overly smooth/digital in some highlights despite scars
Z-Image Turbo
- + Excellent adherence to all specific details including braided hair with beads and ornate armor engravings
- + Clearly depicts the torch and the resulting sparks/bokeh
- + Naturalistic 'battle-worn' appearance with visible dirt and minor wounds
- − The eyes are slightly less detailed compared to Model A
- − Resolution on the chainmail layer appears a bit noisy
- − Framing is a medium-close shot rather than the requested close portrait
Verdict: Z-Image Turbo followed the prompt much more accurately, successfully incorporating the complex hair requirements, the torch, and the ornate armor details. While FLUX.1 [schnell] FP8 produced a striking and sharp facial study, it ignored several key descriptive elements of the character's appearance and equipment.
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
- + Successfully mimics a two-page menu layout
- + Clear white background with well-defined sections for pizza and mains
- + Clean, professional typography that remains legible in headers
- − Typos in section headers like 'ORCETERS', 'PIZZAL', and 'SECCER'
- − The food photos look slightly repetitive and less realistic
Z-Image Turbo
- + Excellent high-quality food photography in a structured grid
- + Strong bold sans-serif fonts with vibrant orange accents
- + Better overall visual appeal for a modern casual dining experience
- − Significant text errors like 'PIZZA MANS' and 'SE TIIION'
- − The layout is a bit cluttered with large images pushing text to tight corners
Verdict: Both models struggled with spelling, but FLUX.1 [schnell] FP8 produced a more logical menu structure that felt like a cohesive document. Z-Image Turbo had superior image quality and more vibrant colors, but the 'PIZZA MANS' header and awkward text placement made it less effective as a functional design.
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
- + Features a dynamic sense of motion with suspended particles
- + High-resolution texture on the burger bun and patty
- − Multiple spelling errors in the text including 'LIIMITED' and 'NEEY'
- − Fails the specific price requirement, showing €69 instead of €6.99
- − The 'starburst' is a dull grey shape that clashes with the fiery theme
Z-Image Turbo
- + Perfect text rendering with the requested fiery, glowing effect
- + Accurate price and starburst integration
- + Excellent lighting coherence between the background and the subject
- − The burger is not truly 'exploded', as the components are still mostly stacked together
- − Lower background resolution compared to the foreground
Verdict: Z-Image Turbo is the clear winner for its superior text rendering and adherence to the specific price and stylistic requirements. While FLUX.1 [schnell] FP8 attempted a more 'exploded' composition, it failed significantly on text accuracy and final price, which are critical for an 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 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 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
- + Successfully followed the difficult logic of the horse being on top of the astronaut equipment/entity
- + High cinematic quality with impressive lighting and a grand sense of scale
- + Creative interpretation of the machinery as the 'astronaut' base
- − Anatomy of the second horse head is somewhat confusing
- − The 'astronaut' is represented as a machine rather than a human in a suit
Z-Image Turbo
- + Standard clean composition for a space-themed image
- + Anatomically correct horse and human proportions
- − Failed the negative constraint; the astronaut is riding the horse instead of the horse riding the astronaut
- − Lacks the 'surreal' quality requested in the prompt
- − Composition is generic compared to Model A
Verdict: FLUX.1 [schnell] FP8 is the clear winner as it successfully interpreted the challenging logical constraint of the horse riding the astronaut. Z-Image Turbo ignored the specific instructional nuance and provided a standard astronaut-on-horse image, which failed the core requirement of the prompt.
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 character expressions, specifically the bored passenger
- + Clear and legible text on the driver's cap
- + Vibrant, high-contrast night lighting that feels professional
- − The passenger is holding two phones unnaturally
- − The capybara's paws look more like human-monkey hybrid hands
Z-Image Turbo
- + Features a more realistic taxi driver hat
- + Capybara's fur texture is exceptionally high quality
- + Better anatomical accuracy of the capybara's paws on the wheel
- − Lighting is a bit flat compared to the requested photorealistic night scene
- − The bored expression of the passenger is less distinct than in Model A
Verdict: FLUX.1 [schnell] FP8 captures the cinematic atmosphere and specific emotions of the prompt more effectively, despite the error of the passenger holding two phones. Z-Image Turbo produces more realistic textures for the animal and accessories, but the overall composition feels less like a New York night scene.
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 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.
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 soft 3D textures and material quality.
- + Clean, minimal composition that feels like a premium diorama.
- + Accurate sushi variety and shape.
- − Text rendering is broken, repeating 'JAPAN' incorrectly.
- − Failed to include the word 'SUSHI' and rendered a distorted flag icon.
Z-Image Turbo
- + Perfect text rendering for both 'JAPAN' and 'SUSHI'.
- + Accurate 45-degree isometric composition.
- + Good material shaders on the salmon and plate.
- − Displays the flag of China instead of Japan.
- − Only shows a single piece of sushi, lacking the 'scene' complexity requested.
Verdict: FLUX.1 [schnell] FP8 produced a much more visually appealing'miniature' style with superior textures, but it failed significantly on the text. Z-Image Turbo followed the text instructions perfectly but made a major factual error by displaying the Chinese flag for a Japanese dish, and the overall scene was less creative. FLUX.1 [schnell] FP8 is the preferred choice for its artistic quality despite the text errors.
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
- + Warm and magical lighting with consistent golden tones
- + Vibrant colors and a very high density of flowers
- + Excellent fur texture and expressive facial features
- − Failed to include a rabbit, replacing it with multiple kittens and fox-like hybrids
- − The animals look more like figurines or digital art than photorealistic animals
Z-Image Turbo
- + Successfully included all four requested species: puppy, kitten, bunny, and fox kit
- + Captures the 'playful tumbling' action described in the prompt
- + More realistic anatomy and natural outdoor lighting
- − The butterfly on the right has a slightly distorted, merged wing structure
- − The background bokeh is a bit more generic compared to the god rays in Model A
Verdict: Z-Image Turbo is the clear winner because it followed the strict prompt requirements, successfully including the golden retriever, kitten, fox, and bunny, whereas FLUX.1 [schnell] FP8 failed to generate a bunny. While FLUX.1 [schnell] FP8 has a more stylized and magical aesthetic, Z-Image Turbo captures the physical interactions and species diversity much more accurately.
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
- + Successfully captures the vector emblem aesthetic with a decorative banner.
- + Correctly renders the 'Est. 1720' text.
- + Includes nice artistic flourish and detail on the dome element.
- − Severely fails the primary text prompt, spelling it as 'AFe FLAMILAN'.
- − The dome looks more like a building or clock tower than a food cloche dome.
Z-Image Turbo
- + Perfectly renders all text requested including 'Caffè Florian' and 'Est. 1720'.
- + Excellent adherence to the 'minimalist' and 'cloche dome' instructions.
- + Very clean vector-style lines and professional composition.
- − Lacks the requested 'banner' for the date.
- − Steam trails are very simple and somewhat basic.
Verdict: While FLUX.1 [schnell] FP8 creates a more complex emblem, it fails significantly on the typography, misspelling the restaurant name. Z-Image Turbo captures the minimalist aesthetic perfectly, produces clean and accurate text, and provides a much better representation of the cloche dome mentioned in the prompt.
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 professional infographic layout and structure.
- + Strict adherence to the requested NASA-inspired color palette.
- + Crisp vector iconography that matches the clean modern style requested.
- − Internal text labels contain significant gibberish/nonsense.
- − The Saturn V icon is represented as a plain white circle rather than a rocket silhouette.
Z-Image Turbo
- + Features a recognizable Saturn V rocket and lunar module illustration.
- + Text is largely legible and correctly spelled (e.g., 'Earth Orbit').
- + Includes various infographic elements like the Earth and Moon with rings.
- − Failed to follow the infographic layout, presenting as a collection of clip-art rather than a structured poster.
- − Spelling errors in prominent headers like 'Apolio E 11' and 'Descenty'.
- − Poor composition with floating text and icons that don't follow the requested step-by-step sequence.
Verdict: FLUX.1 [schnell] FP8 followed the stylistic and structural requirements of the prompt far better, creating a professional-looking infographic layout even though its text labels were largely illegible. Z-Image Turbo produced separate illustrations that felt more like a random collection of assets rather than a coordinated poster, and it struggled with spelling in the large header text.
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