Head to head
Esc

Models · slot A

to navigate to pick

FLUX.1 [dev] Black Forest Labs FLUX.2 [dev] Flash fal

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

FLUX.1 [dev]

24.6 arena score

#16 of 62 in Text-to-Image

Skill signature · Text-to-Image

FLUX.2 [dev] Flash

27.0 arena score

#7 of 62 in Text-to-Image

Vote tally

Where the votes landed

FLUX.1 [dev]

0.0%

win rate

Ties

0.0%

FLUX.2 [dev] Flash

100.0%

win rate

0.0% 0.0% ties 100.0%
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 [dev]
FLUX.2 [dev] Flash

AI Judge Analysis

FLUX.1 [dev]

  • + Excellent photorealism in the book texture and lighting.
  • + Artistic interpretation of the glass cube with polished edges.
  • + Correct window lighting interpretation.
  • The glass cube geometry is physically confusing with internal reflections that break the illusion of a hollow cube.
  • The plant is mostly above/behind the cube rather than visible through the glass panes as requested.

FLUX.2 [dev] Flash

  • + Perfect adherence to all spatial instructions, including the plant being visible through the glass.
  • + Realistic glass imperfections and reflections.
  • + Accurate scaling of the sphere relative to the cube.
  • The text on the book spine is gibberish.
  • The composition is slightly tight on the left side.

Verdict: Both models followed the prompt well, but FLUX.2 [dev] Flash captured the specific spatial requirement of seeing the plant through the glass much better than FLUX.1 [dev]. While FLUX.1 [dev] produced a more polished, abstract-looking object, FLUX.2 [dev] Flash felt more grounded and realistic in its depiction of the glass container and the spheres's placement.

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 [dev]
FLUX.2 [dev] Flash

AI Judge Analysis

FLUX.1 [dev]

  • + Excellent bokeh and realistic shallow depth of field
  • + High cinematic quality with clean reflections on the pavement
  • + Stronger overall visual clarity and lighting
  • The man appears to be posing with the bike rather than actively repairing it
  • Missing the specifically requested 'motion blur' on the background car

FLUX.2 [dev] Flash

  • + Strong adherence to the 'repairing' aspect with tools and a broken chain
  • + Successfully captures motion blur on passing cars as requested
  • + Detailed skin texture and authentic-looking older Japanese bicycle type
  • Anatomical errors in the hands with extra/fused fingers
  • Some messy artifacts on the ground around the tools

Verdict: While FLUX.1 [dev] produces a more aesthetically pleasing and high-quality image, FLUX.2 [dev] Flash adhered better to the specific narrative details of the prompt such as 'motion blur' and 'repairing'. However, FLUX.1 [dev] is the likely winner due to the significant mangling of the subject's hands in the high-speed Flash 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 [dev]
FLUX.2 [dev] Flash

AI Judge Analysis

FLUX.1 [dev]

  • + Excellent high-contrast warm lighting reflecting off the metal.
  • + Striking, lifelike eye rendering and skin texture.
  • Missed the request for hair beads.
  • The 'battle-worn' aspect is very subtle, appearing more like clean freckles than scars and dirt.

FLUX.2 [dev] Flash

  • + Highly accurate adherence to specific prompt details like beads in hair and ornate engraving.
  • + Truly conveys a 'battle-worn' look with realistic scars and grime.
  • + Excellent texture on leather straps and cloth underlayers.
  • Background torches look slightly generic compared to the foreground quality.
  • The lighting on the face is a bit flatter than in the other model.

Verdict: While FLUX.1 [dev] produced a visually striking portrait with beautiful lighting, FLUX.2 [dev] Flash followed the prompt much more accurately. FLUX.2 [dev] Flash included all the requested details such as the beads, ornate engravings, and significant battle damage that were largely missing or under-represented in the first image.

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 [dev]
FLUX.2 [dev] Flash

AI Judge Analysis

FLUX.1 [dev]

  • + Very clean, minimalist design with professional white space.
  • + Excellent typesetting that looks like a real graphic design layout.
  • + High-quality food imagery that blends well with the aesthetic.
  • Missed the 'grid' requirement for food photos, using a more organic placement instead.
  • Missing the specific 'pizza' section requested in the prompt.

FLUX.2 [dev] Flash

  • + Successfully implemented the grid layout for food photos.
  • + Included all three requested sections: Appetizers, Pizza, and Mains.
  • + Vibrant colorful accents accurately reflect the prompt.
  • Text rendering is messy with numerous spelling errors like 'CASSLAL5'.
  • The grid layout is repetitive, showing almost exclusively pizza even for the non-pizza sections.
  • Less 'minimalist' than requested, feeling a bit cluttered at the top and bottom.

Verdict: FLUX.1 [dev] produced a much more professional and aesthetically pleasing design that truly captures the 'minimalist' and 'modern' keywords, though it failed to include the pizza section and the photo grid. FLUX.2 [dev] Flash adhered better to the specific structural requirements like the grid and headers, but the low quality of the text and repetitive imagery makes it less usable overall. FLUX.1 [dev] is the preferred choice for a design-led task where visual coherence is paramount.

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 [dev]
FLUX.2 [dev] Flash

AI Judge Analysis

FLUX.1 [dev]

  • + Features a very high level of symmetry in the layout.
  • + Includes a dramatic fire line at the base for atmospheric effect.
  • Completely failed to include the primary title text 'MAGIC BURGER'.
  • Missed the starburst element for the price.
  • The burger layers are repetitive and do not look like a single coherent burger.

FLUX.2 [dev] Flash

  • + Successfully included all requested text elements with excellent fire effects.
  • + Perfectly executed the starburst element for the price.
  • + Better sense of motion with sauce droplets and floating embers.
  • The pricing starburst is a bit large, slightly crowding the composition.

Verdict: FLUX.2 [dev] Flash significantly outperformed FLUX.1 [dev] by adhering to all the prompt's complex text requirements, including the fiery 'MAGIC BURGER' title and the price starburst, which FLUX.1 [dev] failed to generate. While FLUX.1 [dev] created a neat vertical stack, FLUX.2 [dev] Flash captured the 'exploded' and 'dynamic' feel much more effectively with realistic textures and motion.

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 [dev]
FLUX.2 [dev] Flash

AI Judge Analysis

FLUX.1 [dev]

  • + Excellent text rendering with no spelling errors.
  • + Clean composition that is easy to read.
  • + Natural variations in handwriting styles for different sections.
  • The 'chalk' texture looks a bit too clean and digital, lacking dusty artifacts.
  • The title 'TODAY SPECIALS' is missing the possessive 'S' requested in the prompt.

FLUX.2 [dev] Flash

  • + Superb authentic chalk texture with realistic dust and smudging on the board.
  • + Captures the 'handwritten' aesthetic more convincingly with slight slants and pressure variations.
  • + Correctly followed the 'TODAY'S SPECIALS' title prompt.
  • Repeated the price '$9' twice on the cookie entry.
  • Minor text crowding at the bottom of the board.

Verdict: FLUX.2 [dev] Flash is the winner because it captures the requested 'chalk texture' much more realistically than FLUX.1 [dev], which appears a bit too clean and digital. While FLUX.2 [dev] Flash had a minor repetition error with the cookie price, its overall adherence to the 'handwritten' feel and the specific title formatting was superior.

The Reversed Rodeo

Text-to-Image

“Horse riding astronaut in space — horse on top, not vice versa. Surreal, highly detailed, cinematic.”

FLUX.1 [dev]
FLUX.2 [dev] Flash

AI Judge Analysis

FLUX.1 [dev]

  • + Excellent anatomical rendering of the horse and astronaut
  • + Clean, cinematic lighting with a professional digital art finish
  • + Correct adherence to the prompt despite the confusing instruction
  • The rear hooves have some minor structural merging
  • The composition is slightly static compared to the other

FLUX.2 [dev] Flash

  • + Dynamic composition with better depth and environment details
  • + High level of detail on the space suit and celestial bodies
  • + The lighting on the horse's fur feels more realistic
  • The horse's front left hoof is oddly shaped and lacks clear definition
  • The astronaut's feet seem disconnected from the stirrups

Verdict: Both models failed the negative constraint to put the 'horse on top' of the astronaut, instead defaulting to the standard 'astronaut riding a horse' interpretation. FLUX.1 [dev] produced a cleaner, more polished artistic image, while FLUX.2 [dev] Flash offered a more detailed background and dynamic energy at the cost of some anatomical artifacts 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.”

FLUX.1 [dev]
FLUX.2 [dev] Flash

AI Judge Analysis

FLUX.1 [dev]

  • + Excellent photorealism in the capybara's fur and the taxi's lighting.
  • + The framing feels cinematic and intimate.
  • The passenger appears to be in the front passenger seat rather than the back seat.
  • The capybara is slightly too small and its paws on the wheel look a bit unnatural.

FLUX.2 [dev] Flash

  • + Correctly places the woman in the back seat as requested.
  • + The capybara has a more professional, driver-like posture and clothing.
  • + The background streets and taxi exterior are more clearly defined.
  • The capybara's paws look more like claws, which is slightly unsettling though biologically accurate for its size.
  • The woman's expression is more sad than bored.

Verdict: FLUX.2 [dev] Flash followed the spatial instructions much better by placing the businesswoman in the back seat, whereas FLUX.1 [dev] placed her in the front next to the driver. FLUX.2 [dev] Flash also captured the 'professional' driver aesthetic more effectively with the scale of the capybara and the authentic-looking taxi cap.

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 [dev]
FLUX.2 [dev] Flash
0% wins 0% ties 100% wins

AI Judge Analysis

FLUX.1 [dev]

  • + Strong cinematic lighting with high contrast
  • + Intricate thorny border with good visual depth
  • Major text errors including 'Falloween Rancy' and typos in the invitation body
  • Missed the spider web requirement on the border
  • Incorrect punctuation and spacing in the date and time sections

FLUX.2 [dev] Flash

  • + Excellent text rendering, correctly spelling the main title and most details
  • + Perfect adherence to background elements including webs, thorns, and twisted trees
  • + More authentic vintage gothic aesthetic with parchment textures
  • Small artifact in the time section adding gibberish text 'Hurk: 0369'
  • Slightly less 'glowy' than Model A, though still moody

Verdict: While FLUX.1 [dev] has striking lighting, it failed significantly on the text rendering and missed the spider web requirement. FLUX.2 [dev] Flash followed the layout instructions much more accurately, successfully including the webs and parchment texture while rendering the specific gothic title and invitation text almost perfectly.

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 [dev]
FLUX.2 [dev] Flash

AI Judge Analysis

FLUX.1 [dev]

  • + Excellent soft refined textures and gentle lighting.
  • + Creates a cohesive diorama aesthetic with a consistent plastic-like material feel.
  • + Captures the top-down 45-degree isometric perspective perfectly.
  • Text rendering is poor, featuring misspelling ('SUSH CATON') and unnecessary characters.
  • The diorama base is less distinct from the background compared to Model B.

FLUX.2 [dev] Flash

  • + Perfect text rendering for all specified words.
  • + Superior material realism with believable wood grain and sushi textures.
  • + Excellent diorama presentation on a clearly defined raised wooden base.
  • The sushi design is a bit unconventional with the nori wrap placement.
  • Slightly less 'miniature' in terms of scale compared to Model A.

Verdict: FLUX.2 [dev] Flash followed the text requirements perfectly, whereas FLUX.1 [dev] struggled with spelling and letter forms. While FLUX.1 [dev] achieved a very nice soft plastic miniature look, FLUX.2 [dev] Flash delivered a higher-quality result in terms of crispness, layout, and professional-looking typography.

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 [dev]
FLUX.2 [dev] Flash

AI Judge Analysis

FLUX.1 [dev]

  • + Strong vibrant colors with a very cohesive aesthetic.
  • + Excellent bokeh effect and atmospheric lighting.
  • Failed the photorealistic requirement, appearing more like a 3D animated movie style.
  • Missed the tabby kitten entirely, showing duplicate dogs and fox/rabbit hybrids.
  • Anatomical issues such as missing limbs and indistinct animal species.

FLUX.2 [dev] Flash

  • + Captures a much more realistic, photorealistic photographic style.
  • + Successfully included all requested animals: golden retriever, tabby kitten, bunny, and fox.
  • + Excellent attention to detail with dew sparkles on the grass as requested.
  • The composition is a bit crowded with six animals instead of the four implied.
  • Minor anatomical oddities where the kitten's body merges with the fox's tail.

Verdict: FLUX.2 [dev] Flash is the clear winner as it adhered to the 'hyper-photorealistic' instruction and included all four requested species, whereas FLUX.1 [dev] produced a highly stylized, cartoonish image that omitted the kitten. While FLUX.2 [dev] Flash added extra animals not explicitly requested, its lighting, texture, and prompt fidelity are significantly superior for this specific challenge.

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 [dev]
FLUX.2 [dev] Flash

AI Judge Analysis

FLUX.1 [dev]

  • + Elegant script typography layout.
  • + Good use of negative space for a minimalist feel.
  • Significant spelling errors in the main name ('Flariláan') and 'RESEAURANT'.
  • Hallucinated unrelated numbers (11011, 1941) not found in the prompt.

FLUX.2 [dev] Flash

  • + Perfect adherence to text requirements with zero spelling errors.
  • + Excellent application of subtle texture on the background and logo elements.
  • + Stronger interpretation of the vintage vector emblem style.
  • Composition feels slightly top-heavy due to the size of the cloche dome.

Verdict: While FLUX.1 [dev] has a nice aesthetic, it fails significantly on text rendering, misspelling the primary brand name and additional words. FLUX.2 [dev] Flash perfectly executes the prompt, providing accurate text, the requested 'Est. 1720' banner, and a professional vintage texture that makes it much more usable as a logo.

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 [dev]
FLUX.2 [dev] Flash

AI Judge Analysis

FLUX.1 [dev]

  • + Excellent vector art style with professional layout and balance.
  • + Strictly follows the requested 'NASA-inspired' muted palette.
  • + Sophisticated use of lines and arcs to create a cohesive infographic look.
  • Text rendering is mostly gibberish or heavily distorted.
  • Iconography is abstract and doesn't clearly represent the specific mission steps requested.

FLUX.2 [dev] Flash

  • + Highly legible and mostly accurate text for titles and crew names.
  • + Clearer representation of specific technical elements like the Lunar Module and Saturn V.
  • + Directly maps icons to the requested 6-step sequence.
  • Composition is cluttered and lacks the refined 'vector infographic' feel requested.
  • Art style is inconsistent, mixing flat elements with more detailed textures.
  • Visual hierarchy is messy with overlapping lines and repeating labels.

Verdict: FLUX.1 [dev] produces a much more aesthetically pleasing and stylistically accurate 'modern vector' poster, though its text is unreadable. FLUX.2 [dev] Flash follows the instructional content of the prompt much better, providing readable labels and specific mission details, but fails to achieve the clean, professional design language requested. FLUX.2 [dev] Flash is the preferred choice here for its superior prompt adherence and text rendering despite the less refined art style.

Next steps

Explore each model