Head to head
Esc

Models · slot A

to navigate to pick

FLUX.1 [schnell] FP8 Black Forest Labs FLUX.2 [dev] Black Forest Labs

Settled by community votes across 13 shared challenges, with an AI judge weighing in on each.

FLUX.1 [schnell] FP8

19.0 arena score

#47 of 62 in Text-to-Image

Skill signature · Text-to-Image

FLUX.2 [dev]

24.3 arena score

#19 of 62 in Text-to-Image

Vote tally

Where the votes landed

FLUX.1 [schnell] FP8

0%

win rate

Ties

0%

FLUX.2 [dev]

0%

win rate

Shared challenges 13

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.”

FLUX.1 [schnell] FP8
FLUX.2 [dev]

AI Judge Analysis

FLUX.1 [schnell] FP8

  • + Excellent surface reflections and lighting on the glass.
  • + High artistic quality with a beautiful, vibrant color palette.
  • + Good interpretation of the plant being visible through the glass.
  • The glass object is a tall rectangular prism rather than a cube.
  • The blue sphere is levitating on an internal shelf that wasn't requested.
  • The glass has an unrealistic internal divider.

FLUX.2 [dev]

  • + Accurately depicts a cube shape as requested.
  • + Realistic placement of the sphere on the bottom surface of the cube.
  • + High level of photorealism in textures, especially the wooden table and book.
  • The sphere is slightly large for the description 'small'.
  • The plant's visibility through the cube is slightly less clear than model a.

Verdict: While FLUX.1 [schnell] FP8 creates a more stylized and vibrant image, it fails on geometric accuracy by generating a tall prism instead of a cube and adding an unprompted internal shelf. FLUX.2 [dev] follows the spatial and geometric instructions perfectly, providing a cube with the sphere correctly resting on the base and superior texture realism.

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.”

FLUX.1 [schnell] FP8
FLUX.2 [dev]

AI Judge Analysis

FLUX.1 [schnell] FP8

  • + Effective shallow depth of field
  • + Good color contrast with red bicycle
  • + Clear pavement reflections
  • Failed to include motion blur on passing cars
  • Missing visible rain particles
  • Man's ethnicity appears less specific to the prompt

FLUX.2 [dev]

  • + Excellent adherence to motion blur requirement
  • + Highly realistic skin texture and facial details
  • + Accurate depiction of rain on clothing and bicycle
  • Composition feels slightly more cluttered
  • Secondary white handlebar in the foreground is a bit distracting

Verdict: FLUX.2 [dev] significantly outperformed the other model by including all specific prompt details, most notably the motion blur of passing cars and the presence of light rain. While FLUX.1 [schnell] FP8 produced a clean image, it ignored the motion and weather elements, resulting in a more static feel. FLUX.2 [dev] also provided more convincing skin textures and a more authentic Japanese character model.

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.”

FLUX.1 [schnell] FP8
FLUX.2 [dev]

AI Judge Analysis

FLUX.1 [schnell] FP8

  • + Intense, high-contrast lighting that creates a dramatic mood
  • + Extremely sharp facial details and textures
  • + Strong cinematic framing for a close portrait
  • Failed to include the requested beads in the hair
  • Armor details are mostly obscured by shadows and tight cropping
  • Missing the requested dirt and scars on the skin

FLUX.2 [dev]

  • + Perfectly adheres to all prompt instructions including beads, sparks, and scars
  • + Beautifully rendered engraved plate armor with visible leather straps
  • + More realistic skin texture and visible battle-worn effects
  • Lighting is slightly flatter compared to the intense highlights of the other model
  • The background torch has some minor flame artifacts/coherence issues

Verdict: FLUX.2 [dev] is the clear winner as it fulfilled every specific detail of the prompt, including the beads, scars, and ornate armor, which FLUX.1 [schnell] FP8 largely ignored. While FLUX.1 [schnell] FP8 produced a striking image, it failed at the specific requirements of the text-to-image challenge.

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.”

FLUX.1 [schnell] FP8
FLUX.2 [dev]

AI Judge Analysis

FLUX.1 [schnell] FP8

  • + Excellent minimalist layout that mimics a real physical menu
  • + Strong grid organization for multiple food photos
  • + Clear section headers for appetizers, pizza, and mains
  • Several spelling errors in headings like APPTIZERS and PIZZAL
  • Food photos are somewhat repetitive and low-detail

FLUX.2 [dev]

  • + Higher visual quality and appetite appeal in food photography
  • + Effective use of vibrant color accents and bold sans-serif fonts
  • + Better interpretation of the casual dining aesthetic
  • Text is largely gibberish
  • The grid layout is slightly less clean than Model A

Verdict: FLUX.1 [schnell] FP8 creates a more structured and professional-looking layout that feels like a real restaurant menu, despite several spelling errors in the headers. FLUX.2 [dev] produces much higher quality food imagery and better color accents, but the text is complete nonsense and the layout is a bit more crowded. FLUX.1 [schnell] FP8 is the preferred choice for a design challenge as its composition is more balanced and functional.

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.”

FLUX.1 [schnell] FP8
FLUX.2 [dev]

AI Judge Analysis

FLUX.1 [schnell] FP8

  • + Features vibrant and appetizing food textures
  • + High contrast lighting makes the burger pop against the dark background
  • Multiple spelling errors in the text like 'LIIMITED' and 'NEEY'
  • Fails the price prompt by displaying '€69' instead of '€6.99'
  • The burger is mostly assembled rather than properly 'exploded' into individual layers

FLUX.2 [dev]

  • + Perfect text rendering for all requested phrases including the correct price
  • + Accurately depicts an 'exploded' burger with vertical separation of every layer
  • + Successful application of the 'fiery, glowing effect' to all textual elements
  • The bun texture is slightly smooth/artificial compared to the high-detail patty
  • The starburst shape is somewhat irregular

Verdict: FLUX.2 [dev] significantly outperforms FLUX.1 [schnell] FP8 by adhering to every complex instruction, specifically the correct spelling of all text and the accurate price formatting. While FLUX.1 [schnell] FP8 has great food textures, its failure to render the price and secondary messages correctly makes it less useful as 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.”

FLUX.1 [schnell] FP8
FLUX.2 [dev]

AI Judge Analysis

FLUX.1 [schnell] FP8

  • + Features a realistic wooden frame for the chalkboard.
  • + Achieves high contrast between the board and the text.
  • Significant spelling errors and word repetitions throughout the menu items.
  • The cursive request for the title was not followed, as it is in block caps.
  • Text layout is messy with overlapping lines and inconsistent pricing formats.
  • The chalk texture looks more like a digital marker than actual chalk.

FLUX.2 [dev]

  • + Excellent adherence to the specific text in the prompt, including the final truncated item completion.
  • + Superb chalk texture with realistic smudges and strokes.
  • + Successfully used elegant cursive for the handwritten headers and items.
  • The 'h' in 'with' on the second line is slightly faded and messy.
  • Background blur is a bit heavy, though it fits the 'cozy café' vibe.

Verdict: FLUX.2 [dev] significantly outperforms FLUX.1 [schnell] FP8 by accurately rendering the complex prompt text without spelling errors or nonsensical repetitions. While FLUX.1 [schnell] produced gibberish like 'Octemon' and 'Risortto', FLUX.2 [dev] delivered a highly aesthetic chalkboard with convincing chalk textures and beautiful cursive handwriting.

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
FLUX.2 [dev]

AI Judge Analysis

FLUX.1 [schnell] FP8

  • + Successfully followed the specific 'horse on top' prompt instruction
  • + Cinematic composition with dramatic lighting and scale
  • The 'astronaut' is depicted as a machine/box rather than a recognizable human astronaut
  • Anatomical oddity with a second horse head emerging from the back

FLUX.2 [dev]

  • + High visual quality and clear details on the astronaut suit
  • + Coherent horse anatomy and beautiful nebula background
  • Failed the negative constraint/specific instruction 'horse on top, not vice versa'
  • Conventional interpretation rather than the requested surreal reversal

Verdict: While FLUX.2 [dev] produced a higher quality, more coherent image, it completely ignored the specific instruction to have the horse riding the astronaut. FLUX.1 [schnell] FP8 correctly interpreted the surreal prompt request, creating a composition where the horse is the rider, despite some anatomical artifacts.

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.”

FLUX.1 [schnell] FP8
FLUX.2 [dev]

AI Judge Analysis

FLUX.1 [schnell] FP8

  • + High resolution and vibrant colors.
  • + Excellent texture on the capybara's fur.
  • + Clear legible text on the driver's hat.
  • The woman is holding two phones, which is awkward and unintended.
  • The perspective makes the capybara look like it is in the back seat with the woman rather than driving from the front.

FLUX.2 [dev]

  • + Perfect adherence to the 'both front paws on the steering wheel' instruction.
  • + More realistic spatial arrangement showing the capybara in the front and the passenger in the back.
  • + Captures the requested bored/normal expression on the human passenger very well.
  • The hat design is slightly less 'NYC taxi' and more generic.
  • The image has a slightly softer focus on the passenger.

Verdict: While FLUX.1 [schnell] FP8 has higher sharpness and clarity, FLUX.2 [dev] followed the prompt instructions much more accurately, specifically regarding the paws on the steering wheel and the spatial relationship between the driver and passenger. FLUX.1 [schnell] FP8 also introduced a logical error by giving the passenger two phones.

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
FLUX.2 [dev]

AI Judge Analysis

FLUX.1 [schnell] FP8

  • + Features a vibrant, glowing jack-o-lantern central focus.
  • + Atmospheric use of bats and silhouetted trees in the background.
  • Text rendering is poor with several typos and jumbled words in the event details.
  • The border lacks the requested thorns and webs, appearing more like burnt paper.

FLUX.2 [dev]

  • + Excellent text rendering, following all specific copy requirements accurately.
  • + Strong adherence to border elements, featuring both thorns and spider webs as requested.
  • + Composition is well-balanced with a polished, professional design.
  • The jack-o-lantern's surface is dark/black, which might be less 'traditional' than a bright orange pumpkin.

Verdict: FLUX.1 [schnell] FP8 struggles significantly with the text at the bottom and fails to include the specific border elements like thorns and webs. In contrast, FLUX.2 [dev] delivers a perfect execution of the text and border requirements while maintaining a high-quality gothic aesthetic that fits the cinematic prompt.

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.”

FLUX.1 [schnell] FP8
FLUX.2 [dev]

AI Judge Analysis

FLUX.1 [schnell] FP8

  • + Excellent soft 3D cartoon shading and lighting
  • + Clean, high-quality rendering of the podium and plate
  • Failed to render the word 'SUSHI'
  • Rendered the word 'JAPAN' twice with spelling errors on the second line
  • The flag icon is integrated into the text incorrectly

FLUX.2 [dev]

  • + Perfect adherence to all text requirements including 'JAPAN', 'SUSHI', and flag icon
  • + Accurate miniature diorama aesthetic with realistic sushi textures
  • + Strict adherence to the 45-degree isometric camera angle
  • The lighting is a bit flatter compared to the more vibrant Model A
  • The shadows on the podium are slightly harsh for a 'gentle lighting' prompt

Verdict: While FLUX.1 [schnell] FP8 has a more appealing 3D cartoon style, it failed significantly on the text and flag requirements. FLUX.2 [dev] followed the prompt instructions perfectly, delivering correct text, the flag icon, and an accurate isometric diorama composition.

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.”

FLUX.1 [schnell] FP8
FLUX.2 [dev]

AI Judge Analysis

FLUX.1 [schnell] FP8

  • + Vibrant, saturated colors that create a magical atmosphere
  • + Excellent backlighting and 'god rays' effects
  • + Cute, expressive facial features on the animals
  • Failed to include the bunny
  • Anatomical oddities include a cat/fox hybrid creature and extra animals not requested
  • Leans way into a digital art/illustration style rather than photorealistic

FLUX.2 [dev]

  • + Successfully included all four requested species: golden retriever, tabby kitten, bunny, and fox kit
  • + Much more realistic fur textures and anatomical proportions
  • + Subtle and professional lighting with realistic dew sparkles
  • The composition is slightly more static compared to the 'tumbling' request
  • The tabby kitten's expression is a bit blank compared to the others

Verdict: FLUX.2 [dev] followed the complex prompt requirements much better, successfully including the golden retriever, tabby, bunny, and fox kit with realistic details. FLUX.1 [schnell] FP8 failed to generate a bunny and instead produced a confusing cluster of five animals with questionable anatomy, looking more like an AI illustration than the requested hyper-photorealistic scene.

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.”

FLUX.1 [schnell] FP8
FLUX.2 [dev]

AI Judge Analysis

FLUX.1 [schnell] FP8

  • + Successfully captures the warm brown and cream color palette.
  • + Includes the requested 'Est. 1720' text and banner.
  • Severely garbled primary text, rendering 'AFe FLAMILAN' instead of 'Caffè Florian'.
  • The cloche dome is over-designed with architectural elements, losing the 'minimalist' aesthetic.

FLUX.2 [dev]

  • + Excellent text rendering with perfect spelling of 'Caffè Florian'.
  • + Accurate interpretation of a 'retro cloche dome' and 'steam' icon.
  • + Clean, vector-style execution with appropriate subtle texture.
  • The placement of 'Est. 1720' is beneath the primary banner rather than being the focus of the banner itself.

Verdict: FLUX.2 [dev] significantly outperforms FLUX.1 [schnell] FP8 by accurately spelling the restaurant name and adhering to the minimalist vector aesthetic. While FLUX.1 [schnell] creates a more complex emblem, the catastrophic failure in text rendering makes it unusable as a logo compared to the clean, professional output of FLUX.2 [dev].

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.”

FLUX.1 [schnell] FP8
FLUX.2 [dev]

AI Judge Analysis

FLUX.1 [schnell] FP8

  • + Strong adherence to the flat-vector aesthetic.
  • + Clean organizational layout with a clear timeline structure.
  • + Excellent use of the specified NASA-inspired color palette.
  • Nonsensical placeholder text throughout the design.
  • Iconography is overly abstract and loses mission-specific details.

FLUX.2 [dev]

  • + High-quality illustrations with good technical detail.
  • + Successfully includes major mission milestones as requested.
  • + Creative addition of astronaut names using the defined color scheme.
  • Grid layout feels less like a cohesive infographic poster and more like a set of icons.
  • Failed to maintain a strictly flat-vector style, introducing complex gradients and shadows.

Verdict: FLUX.1 [schnell] FP8 captures the professional infographic layout and flat-vector style more accurately, but is hampered by gibberish text. FLUX.2 [dev] provides much higher illustrative quality and recognizable symbols at the cost of the requested flat aesthetic. FLUX.1 [schnell] FP8 is the preferred choice for a true minimalist infographic design.

Next steps

Explore each model