Head to head
Esc

Models · slot A

to navigate to pick

FLUX.1 Kontext [pro] Black Forest Labs FLUX.2 [dev] Turbo fal

Settled by community votes across 17 shared challenges, with an AI judge weighing in on each.

FLUX.1 Kontext [pro]

20.3 arena score

#41 of 62 in Text-to-Image

Skill signature · Text-to-Image

FLUX.2 [dev] Turbo

27.9 arena score

#3 of 62 in Text-to-Image

Top 3 in Text-to-Image
Vote tally

Where the votes landed

FLUX.1 Kontext [pro]

0.0%

win rate

Ties

0.0%

FLUX.2 [dev] Turbo

100.0%

win rate

0.0% 0.0% ties 100.0%
Shared challenges 17

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 Kontext [pro]
FLUX.2 [dev] Turbo
0% wins 0% ties 100% wins

AI Judge Analysis

FLUX.1 Kontext [pro]

  • + Excellent adherence to lighting and composition instructions.
  • + The glass cube has realistic, thin edges that feel like a high-quality display case.
  • + Very clean, professional-looking textures on the book and table.
  • The blue sphere appears to be floating rather than resting on the bottom of the cube.
  • The blue sphere has a fuzzy/felt texture which might not be the expected material for a sphere in a glass cube.

FLUX.2 [dev] Turbo

  • + The sphere rests naturally on the bottom surface with realistic reflections.
  • + The plant is more clearly visible through the glass as requested.
  • + The wooden table has a rich, realistic weathered texture.
  • The glass cube has very thick, somewhat messy seams at the corners.
  • The lighting is a bit harsher than the requested 'soft window light'.

Verdict: Both models followed the complex spatial instructions perfectly, including the nested objects and plant placement. FLUX.1 Kontext [pro] produced a cleaner, more aesthetic image with better lighting, while FLUX.2 [dev] Turbo succeeded in making the sphere sit naturally on the surface with realistic glass distortions.

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 Kontext [pro]
FLUX.2 [dev] Turbo

AI Judge Analysis

FLUX.1 Kontext [pro]

  • + Excellent shallow depth of field and bokeh
  • + Subtle, realistic skin textures
  • + Strong atmospheric lighting and rain effects
  • The subject is riding/leaning on the bike rather than repairing it
  • Composition feels a bit too posed and centered for a 'candid' prompt

FLUX.2 [dev] Turbo

  • + Perfectly adheres to the 'repairing' action with tools on the ground
  • + Successful motion blur on passing cars
  • + Natural, 'imperfect' street photography framing and composition
  • Slightly over-sharpened digital look in some areas
  • Anatomy of the bicycle on the ground/wheel intersection is slightly messy

Verdict: While FLUX.1 Kontext [pro] captures a beautiful cinematic mood, FLUX.2 [dev] Turbo followed the complex prompt requirements much more accurately. FLUX.2 [dev] Turbo correctly depicted the act of repairing with tools and a kickstand, while also successfully incorporating the motion blur of passing cars which FLUX.1 Kontext [pro] missed.

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 Kontext [pro]
FLUX.2 [dev] Turbo

AI Judge Analysis

FLUX.1 Kontext [pro]

  • + Excellent photographic realism with natural skin textures and lighting.
  • + Sophisticated engraved plate armor with subtle, realistic weathering.
  • + Better focused composition with a clean shallow depth of field.
  • Missed the request for beads in the hair.
  • The 'battle-worn' elements like scars and dirt are very faint.

FLUX.2 [dev] Turbo

  • + Followed all prompt details including the beads in the hair.
  • + Successfully captured a more intense 'battle-worn' look with prominent scars.
  • + Dynamic composition with a visible torch and active bokeh sparks.
  • Lighting is somewhat flat and less realistic than its counterpart.
  • The beard and hair textures look slightly less natural than Model A.

Verdict: FLUX.1 Kontext [pro] produced a high-quality, cinematic portrait with superior lighting and metal textures, but it ignored the specific instruction for beads in the hair. FLUX.2 [dev] Turbo followed the prompt more laterally, including the beads and more aggressive scars, making it a better match for the specific prompt requirements despite a slightly less refined lighting setup.

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 Kontext [pro]
FLUX.2 [dev] Turbo

AI Judge Analysis

FLUX.1 Kontext [pro]

  • + Excellent adherence to the section headers requested
  • + Clean, minimalist aesthetic with good use of white space
  • + Coherent relationship between the section titles and the images beside them
  • Text is mostly gibberish despite looking like words
  • Prices are inconsistent and nonsensical for a casual menu
  • Layout is more of a list than a specific grid of photos

FLUX.2 [dev] Turbo

  • + Successfully creates a grid of food photos as requested
  • + Used color blocking and accents to enhance the modern feel
  • + Text rendering is cleaner and closer to legible English
  • Photos are repetitive, showing mostly pizzas across all categories
  • Layout feels a bit cluttered with overlapping elements
  • The section headers are somewhat disconnected from the images

Verdict: FLUX.1 Kontext [pro] creates a much cleaner, more professional minimalist design that feels like a real boutique menu, whereas FLUX.2 [dev] Turbo better understands the 'grid of photos' instruction but fails to provide variety in the food shown. FLUX.1 Kontext [pro] is the likely winner for its superior composition and professional aesthetic despite the gibberish text.

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 Kontext [pro]
FLUX.2 [dev] Turbo
0% wins 0% ties 100% wins

AI Judge Analysis

FLUX.1 Kontext [pro]

  • + Excellent typography with a glowing neon effect
  • + High-quality textures on the burger bun and melting cheese
  • + Atmospheric use of embers and fire
  • Failed to render a starburst for the price
  • Repeated the price text twice, creating a cluttered bottom section
  • The burger is barely 'exploded', adhering more to a standard stacked look

FLUX.2 [dev] Turbo

  • + Captured the 'exploded' dynamic perfectly with distinct suspended layers
  • + Accurately followed the 'starburst' instruction for the price
  • + Consistent fiery text effect across all copy
  • The meat patty looks slightly dry compared to Model A
  • The sauce droplets have a somewhat stylized, less photorealistic appearance

Verdict: FLUX.2 [dev] Turbo followed the prompt instructions much more closely, successfully executing the 'exploded' layout and the specific 'starburst' requirement for the price. While FLUX.1 Kontext [pro] produced a more appetizing-looking burger and slicker main title, it failed several specific prompt constraints and suffered from redundant text elements.

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 Kontext [pro]
FLUX.2 [dev] Turbo

AI Judge Analysis

FLUX.1 Kontext [pro]

  • + Excellent spelling throughout all mandated text and additional lines.
  • + Very clear, legible chalk texture on the letters.
  • + Clean wooden frame and realistic cafe background depth.
  • The text style for 'TODAY'S SPECIALS' is block caps rather than the requested elegant cursive.
  • The handwriting feels slightly more uniform and less 'hand-drawn' than model b.

FLUX.2 [dev] Turbo

  • + Excellent adherence to the 'elegant cursive' style for the header.
  • + Very authentic chalk smudge textures and natural handwriting variations across the board.
  • + Great environmental context with cafe equipment visible.
  • Contains a minor text repetition error with a floating '- 9' above the cookie price.
  • The background text on the secondary board is slightly garbled.

Verdict: FLUX.1 Kontext [pro] produced a cleaner, perfectly spelled image, but failed to follow the instruction for a cursive header. FLUX.2 [dev] Turbo captured the aesthetic of a hand-written chalkboard much more effectively, including the requested cursive, despite a small layout artifact in the pricing of the cookies. FLUX.2 [dev] Turbo is the preferred choice for its superior artistic interpretation of the 'handwritten' and 'cursive' prompts.

The Reversed Rodeo

Text-to-Image

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

FLUX.1 Kontext [pro]
FLUX.2 [dev] Turbo

AI Judge Analysis

FLUX.1 Kontext [pro]

  • + Excellent adherence to the 'horse on top' spatial instruction.
  • + Highly surreal and creative interpretation of the prompt.
  • + Cinematic lighting and composition with high visual clarity.
  • Anatomical blending error where the astronaut's legs turn into horse hooves.
  • The secondary smaller astronaut on the horse's back is a bit strange and unexplained.

FLUX.2 [dev] Turbo

  • + High level of intricate detail in the space suit and horse's coat.
  • + Strong cinematic atmosphere with vibrant colors and lighting.
  • + Clean rendering without obvious anatomical merging.
  • Completely failed the specific spatial instruction; the astronaut is riding the horse.
  • Clichéd interpretation that ignores the core subversion requested in the prompt.

Verdict: FLUX.1 Kontext [pro] successfully interpreted the difficult 'horse on top' instruction, creating a surreal and memorable image, whereas FLUX.2 [dev] Turbo produced a generic 'astronaut riding a horse' image. Although FLUX.1 Kontext [pro] has some merging errors with the limbs, it is the clear winner for actually following the specific logic 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.”

FLUX.1 Kontext [pro]
FLUX.2 [dev] Turbo

AI Judge Analysis

FLUX.1 Kontext [pro]

  • + Excellent texture on the capybara's fur
  • + Sharp, cinematic lighting within the car interior
  • The passenger is in the front seat instead of the back seat
  • The capybara's paws are not clearly placed 'both' on the wheel as requested
  • Text on the cap is cut off

FLUX.2 [dev] Turbo

  • + Perfect adherence to the prompt regarding both paws on the wheel
  • + Accurately places the passenger in the back seat looking at her phone
  • + Realistic city street background through the windshield
  • The passenger's phone has slight lighting inconsistencies
  • Composition is a bit crowded vertically

Verdict: FLUX.2 [dev] Turbo followed all instructions of the prompt, specifically placing the passenger in the back seat and showing both of the capybara's paws on the steering wheel. FLUX.1 Kontext [pro] produced a high-quality close-up but failed on spatial orientation by placing the passenger in the passenger seat and obscuring the requested pose of the animal.

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 Kontext [pro]
FLUX.2 [dev] Turbo

AI Judge Analysis

FLUX.1 Kontext [pro]

  • + Excellent typography for the main title and sub-banner.
  • + Sophisticated cinematic lighting and a delicate spiderweb border.
  • Includes hallucinations in the event details section, like 'Your: Vorkleat'.
  • Parchment texture is less evident compared to the dark void background.

FLUX.2 [dev] Turbo

  • + Perfect text accuracy with no hallucinations in the event details.
  • + Very clear 'dark parchment' texture and better integration of thorns and webs in the border.
  • + Distinct twisted trees that frame the central jack-o-lantern well.
  • The main title font is slightly less 'elegant gothic' than the first model.
  • The glow from the pumpkin is a bit more localized and less atmospheric.

Verdict: Both models handled the complex text requirements impressively. FLUX.1 Kontext [pro] produced a more stylish, high-contrast atmospheric design, but it hallucinated extra lines of text that weren't in the prompt. FLUX.2 [dev] Turbo followed all instructions perfectly, providing a cleaner layout and significantly better adherence to the 'dark parchment' and 'thorns' descriptions.

Bald man challenge

Image Editing
Edit instruction

“Give the person a full, thick head of natural hair with realistic texture, density, and a natural hairline. Preserve facial features and lighting.”

Before After
FLUX.1 Kontext [pro]
Before After
FLUX.2 [dev] Turbo

AI Judge Analysis

FLUX.1 Kontext [pro]

  • + Excellent color matching with the existing beard
  • + Preserves the original facial structure very well
  • + Natural integration of sideburns and temples
  • The forehead appears slightly wider/distorted compared to the source
  • The glasses frames became much thicker and darker

FLUX.2 [dev] Turbo

  • + Impressive realistic texture and flyaway hairs
  • + Perfectly preserves the original glasses and facial features
  • + Strong source preservation of the background and clothing
  • The hair type is a significant departure from the beard's texture
  • The volume/shape looks slightly unnatural for the subject

Verdict: Both models handled the edit well, but FLUX.2 [dev] Turbo did a superior job of preserving the source image's specific details like the glasses and background. While FLUX.1 Kontext [pro] provided a more stylistically appropriate haircut for the man, it unintentionally altered his facial geometry and the thickness of his eyewear.

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 Kontext [pro]
FLUX.2 [dev] Turbo

AI Judge Analysis

FLUX.1 Kontext [pro]

  • + Excellent adherence to the cartoon aesthetic with soft, rounded textures
  • + Clean typography that matches the 3D playfulness of the scene
  • + Strong 45° isometric perspective
  • The rice grains look more like foam balls than realistic sushi rice
  • The flag icon is stylized/distorted rather than a standard flag icon

FLUX.2 [dev] Turbo

  • + Superior PBR materials with realistic textures on the fish and nori
  • + Clean, professional typography and layout
  • + Higher detail in the food rendering while maintaining the diorama feel
  • Slightly less 'cartoon' than requested, leaning more toward realistic miniature
  • The flag icon placement is slightly off-center compared to the text block

Verdict: FLUX.1 Kontext [pro] captures the '3D cartoon' style more effectively with its soft, bubbly shapes, while FLUX.2 [dev] Turbo provides much better material quality and realism within the diorama. FLUX.2 [dev] Turbo is the overall winner for its superior rendering of the salmon and rice, which makes for a more appetizing and professional-looking graphic.

Over-the-top cartoon caricature

Editing
Edit instruction

“Create a caricature of me and my job. Make it exaggerated and humorous, incorporating my profession as a tv show anchor and my love for dogs and hockey.”

Source
FLUX.1 Kontext [pro]
FLUX.2 [dev] Turbo

AI Judge Analysis

FLUX.1 Kontext [pro]

  • + Successfully converts the person into a stylized illustration.
  • + Maintains the outfit and basic pose of the source image.
  • Completely misses nearly all prompt requirements (no hockey, no dogs, no TV anchor setting).
  • The 'caricature' style is more of a generic cartoon/anime style rather than a comedic exaggeration.

FLUX.2 [dev] Turbo

  • + Excellent adherence to all prompt elements including TV anchor desk, hockey rink setting, and dogs.
  • + Cleverly integrates the dogs into the hockey environment.
  • + Achieves a classic caricature style with an enlarged head and expressive features.
  • Loses the specific denim outfit from the source image in favor of a professional suit.
  • Some minor artifacts in the background text and small details (extra limbs on one dog).

Verdict: FLUX.1 Kontext [pro] failed the editing task by ignoring the specific thematic requests (hockey, dogs, and TV anchor), resulting in a simple cartoon rendition of the original photo. In contrast, FLUX.2 [dev] Turbo followed the prompt perfectly, creating a humorous, detailed caricature that creatively blended all requested elements into a cohesive scene. FLUX.2 [dev] Turbo is the clear winner for its superior prompt adherence and storytelling.

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 Kontext [pro]
FLUX.2 [dev] Turbo

AI Judge Analysis

FLUX.1 Kontext [pro]

  • + Excellent soft lighting and glowing bokeh effect.
  • + High level of fur detail with a consistent 'cutesy' aesthetic.
  • Failed to include a tabby kitten, rendering multiple cat-like figures that look more like a single breed.
  • Anatomy is slightly merged between the central animals, lacking distinct separation.
  • The fox kit lacks characteristic dark markings.

FLUX.2 [dev] Turbo

  • + Correctly included all four distinct species: golden retriever, tabby kitten, bunny, and fox kit.
  • + Dynamic composition captures the 'playfully chasing' and 'tumbling' aspect of the prompt much better.
  • + Beautiful inclusion of dew sparkles and clear god rays as requested.
  • The tabby kitten's anatomy features a slightly strange limb placement while jumping.

Verdict: FLUX.2 [dev] Turbo is the clear winner as it adhered to all elements of the prompt, including the specific species list and the active 'tumbling' movement. While FLUX.1 Kontext [pro] created a beautiful, soft atmosphere, it failed to differentiate the animals, omitting the tabby kitten and making the cat and fox look nearly identical.

Studio Ghibli Anime Style

Editing
Edit instruction

“Transform this photo into a Studio Ghibli–inspired illustration. Use soft pastel colors, hand-painted textures, gentle lighting, dreamy backgrounds, and a warm, nostalgic mood”

Source
FLUX.1 Kontext [pro]
FLUX.2 [dev] Turbo

AI Judge Analysis

FLUX.1 Kontext [pro]

  • + Perfectly captures the Studio Ghibli cel-shaded character design and watercolor texture.
  • + Maintains the original composition and character expressions with high fidelity.
  • + Captures the specific 'hand-painted' paper texture requested in the prompt.
  • The color palette is a bit more saturated than the 'soft pastel' request.

FLUX.2 [dev] Turbo

  • + Excellent application of soft pastel colors and dreamy atmospheric lighting.
  • + Beautifully reimagined background with Ghibli-esque foliage and flowers.
  • + Successful 'hand-painted' texture on the clothing and skin.
  • The male character's face looks slightly more generic/westernized than a Ghibli design.
  • Added some extra hair detail to the male character that deviates from the smooth Ghibli style.

Verdict: FLUX.1 Kontext [pro] creates a more authentic Studio Ghibli aesthetic, particularly in the character line art and the watercolor-on-paper texture. While FLUX.2 [dev] Turbo does a better job with the 'soft pastel' color palette and dreamy background elements, FLUX.1 Kontext [pro] better preserves the iconic expressions of the 'distracted boyfriend' meme within the requested art style.

Golden Hour Stroll

Image Editing
Edit instruction

“Add dynamic motion to this photo: make hair blow in the wind, add leaves flying, energetic and lively feel.”

Before After
FLUX.1 Kontext [pro]
Before After
FLUX.2 [dev] Turbo

AI Judge Analysis

FLUX.1 Kontext [pro]

  • + Excellent preservation of the original face and clothing details.
  • + Natural hair motion that looks realistic.
  • + Subtle and organic placement of flying leaves.

FLUX.2 [dev] Turbo

  • + Strong creative interpretation of 'lively' mood.
  • + High quantity of leaves creates a festive, dynamic atmosphere.
  • Significant distortion of the woman's face compared to the source image.
  • The hair flow looks more like a static 'crown' effect rather than natural wind direction.

Verdict: FLUX.1 Kontext [pro] is the clear winner as it successfully applies the motion edits while maintaining the identity and features of the person in the source image. In contrast, FLUX.2 [dev] Turbo changes the woman's facial structure significantly and creates a less realistic wind effect, despite adding much more debris to the 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 Kontext [pro]
FLUX.2 [dev] Turbo

AI Judge Analysis

FLUX.1 Kontext [pro]

  • + Excellent typography with a clean, authentic slab serif feel
  • + High contrast and legible layout
  • + Correct accent mark on the 'E' in 'Caffè'
  • Typos in the banner text ('EEST.' instead of 'EST.')
  • The cloche handle and steam are slightly off-center

FLUX.2 [dev] Turbo

  • + Sophisticated vintage texture and paper effect
  • + Correct spelling of 'EST.' in the banner
  • + Elegant vector-style shadowing and illustrative detail
  • Incorrect accent mark direction on 'CAFFÈ' (it uses a grave accent in the prompt/brand, but the image uses something resembling a tilde or inconsistent mark)
  • Text is slightly tighter and harder to read at small scales

Verdict: Both models captured the vintage aesthetic well, but FLUX.2 [dev] Turbo produced a more polished and professional-looking emblem with correct spelling. While FLUX.1 Kontext [pro] had cleaner typography, the 'EEST' typo and simpler textures make it feel less like a finished logo compared to the detailed work in FLUX.2 [dev] Turbo.

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 Kontext [pro]
FLUX.2 [dev] Turbo

AI Judge Analysis

FLUX.1 Kontext [pro]

  • + Excellent typography rendering for the main title
  • + Captures an artistic, minimalist vector aesthetic well
  • Confusing scientific accuracy, placing Saturn near a rocket launch
  • Text labels are nonsensical (e.g., '2, far Collins') and poorly placed
  • Fails to follow the requested step-by-step numbering logic

FLUX.2 [dev] Turbo

  • + Successfully follows the requested 6-step logical flow
  • + Includes clear, relevant icons for each phase like the Lunar Module
  • + High accuracy in text rendering and labeling of mission phases
  • The rocket icon includes the literal text 'Saturn Icon' from the prompt
  • Repeats the 'Translunar' phase twice in the layout
  • Layout is a bit cluttered compared to a sleek infographic design

Verdict: FLUX.2 [dev] Turbo followed the prompt's structural instructions significantly better, providing specific icons for the descent and landing phases that FLUX.1 Kontext [pro] ignored. While FLUX.1 Kontext [pro] has a more cohesive artistic style, its content is nonsensical, including an image of Saturn at a rocket launch and garbled text, whereas FLUX.2 [dev] Turbo created a functional, readable infographic.

Next steps

Explore each model