Head to head
Esc

Models · slot A

to navigate to pick

FLUX.1 Krea [dev] Black Forest Labs GPT Image 1 Mini OpenAI

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

FLUX.1 Krea [dev]

18.8 arena score

#48 of 62 in Text-to-Image

Skill signature · Text-to-Image

GPT Image 1 Mini

25.0 arena score

#13 of 62 in Text-to-Image

Vote tally

Where the votes landed

FLUX.1 Krea [dev]

0%

win rate

Ties

0%

GPT Image 1 Mini

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 Krea [dev]
GPT Image 1 Mini

AI Judge Analysis

FLUX.1 Krea [dev]

  • + Excellent photorealistic rendering of glass and reflections.
  • + Accurately represents the blue sphere as deep blue with complex lighting.
  • + Great use of soft window light from the left side.
  • The glass cube is slightly skewed in shape toward the bottom.
  • The plant is very dark and less distinct behind the glass.

GPT Image 1 Mini

  • + Perfect geometric cube with thin, realistic glass edges.
  • + Better visibility of the green plant through the transparent cube.
  • + Very clean composition and high-quality textures on the book.
  • The sphere appears more matte/plastic rather than a high-quality glass or polish like the surrounding materials.
  • The lighting is a bit more flat compared to the dramatic realism of Model A.

Verdict: Both models followed the prompt perfectly, placing all objects in their correct spatial relationships. FLUX.1 Krea [dev] produced a more cinematic and photorealistic image with realistic light play, while GPT Image 1 Mini produced a cleaner, more technically precise geometric assembly. FLUX.1 Krea [dev] is slightly preferred for its superior handling of glass physics and lighting.

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 Krea [dev]
GPT Image 1 Mini

AI Judge Analysis

FLUX.1 Krea [dev]

  • + Excellent depiction of motion blur on passing cars as requested.
  • + Effective use of wide, wet environmental reflections.
  • + Successfully captures the 'imperfect framing' of a candid street photo.
  • The man is just standing with the bike rather than actively 'repairing' it.
  • Skin texture and facial details are a bit soft and lacks the requested 'natural skin texture' detail.

GPT Image 1 Mini

  • + Stronger adherence to the 'repairing' aspect of the prompt.
  • + Superior natural skin texture and fine detail on the face and hands.
  • + Atmospheric lighting on the wet bike surface is very realistic.
  • Misses the 'motion blur from passing cars' almost entirely; cars in background are static or nearly so.
  • Hand anatomy is slightly distorted with several anatomical merging issues on the fingers.

Verdict: GPT Image 1 Mini captures the intimate details and the specific action of repairing much better than FLUX.1 Krea, though it fails to include the requested motion blur. FLUX.1 Krea succeeds in creating the described environmental atmosphere and movement but falls short on the primary action and fine textures of the subject. GPT Image 1 Mini is preferred for its high-quality rendering of skin and more compelling cinematic composition.

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 Krea [dev]
GPT Image 1 Mini

AI Judge Analysis

FLUX.1 Krea [dev]

  • + Excellent adherence to the 'beads in braids' request.
  • + Strong lighting contrast and clear bokeh effect.
  • + High-quality rendering of the ornate engraving on the armor.
  • The blood/dirt on the face looks a bit like paint rather than natural texture.
  • The leather strap appears slightly flat compared to the metalwork.

GPT Image 1 Mini

  • + Superb skin texture with realistic pores, scars, and grittiness.
  • + The torchlight reflection feels more integrated into the atmosphere.
  • + Better representation of 'battle-worn' through rusted and weathered armor finishes.
  • Missed the request for 'small beads' in the braided hair.
  • The focus is very tight on the face, losing some of the 'cloth underlayer' detail requested.

Verdict: Both models performed exceptionally well, but FLUX.1 Krea (dev) followed the specific prompt details more accurately, particularly regarding the hair beads. However, GPT Image 1 Mini achieved a more convincing 'battle-worn' aesthetic with superior skin textures and realistic environmental lighting.

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 Krea [dev]
GPT Image 1 Mini

AI Judge Analysis

FLUX.1 Krea [dev]

  • + Excellent professional layout with dense, realistic menu content
  • + Good use of vibrant orange accents for headers
  • + Food photos are well-integrated and appetizing
  • Text consists of garbled placeholder characters
  • Repeats the 'Appetizers' section header

GPT Image 1 Mini

  • + Perfectly legible English headers
  • + Very clean, minimalist aesthetic
  • + Aligns food categories directly with corresponding images
  • The menu body is completely empty with no items or prices
  • Text is a bit too large, making it look more like a poster than a menu

Verdict: FLUX.1 Krea [dev] produces a much more realistic and professional-looking menu layout that feels ready for a restaurant, despite the garbled text. GPT Image 1 Mini creates a very clean design with legible headers, but it fails to generate any actual menu items, leaving large empty voids in the composition.

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 Krea [dev]
GPT Image 1 Mini

AI Judge Analysis

FLUX.1 Krea [dev]

  • + Excellent photorealistic texture on the burger bun and patty.
  • + Professional layout that resembles a real-world advertisement.
  • + High-quality fire effects and embers at the base.
  • Missed the 'fiery, glowing effect' on the primary text.
  • Failed to place the price inside a starburst as requested.
  • The 'exploded' effect is less dynamic with components overlapping closely.

GPT Image 1 Mini

  • + Perfect adherence to the text styling, featuring the fiery glowing effect on all fonts.
  • + Successfully placed the price inside a glowing starburst as requested.
  • + The 'exploded' burger effect is more clear, with distinct air gaps between all ingredients.
  • The 'LIMITED TIME ONLY' text is slightly off-center and clipped at the bottom.
  • The textures are a bit more illustrative compared to the photorealism of the competitor.

Verdict: GPT Image 1 Mini followed the prompt instructions much more closely, specifically regarding the fiery text effects and the starburst element. While FLUX.1 Krea (dev) has slightly more realistic food textures, it failed to deliver the specific graphic design requirements of the prompt.

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 Krea [dev]
GPT Image 1 Mini

AI Judge Analysis

FLUX.1 Krea [dev]

  • + Features a very realistic wood frame and natural lighting
  • + Captures a fluid, handwritten cursive aesthetic
  • + Includes the specific date and items mentioned
  • Serious spelling errors like 'Gruffle', 'Lcoman', and 'Uvrcuations'
  • Includes printed-style font for the 'Today's Specials' title, which was explicitly forbidden
  • The handwriting style is inconsistent throughout the board

GPT Image 1 Mini

  • + Excellent prompt adherence with near-perfect spelling on all requested items
  • + Has a very convincing chalk texture that looks like it was drawn on a board
  • + Follows the instruction for no printed or digital fonts, maintaining a consistent handwritten feel
  • The layout is a bit tight at the bottom edge
  • The $9 price alignment is slightly off compared to the others

Verdict: GPT Image 1 Mini is the clear winner because it followed all text-based instructions perfectly, including the prohibition of digital fonts and the specific spelling of complex menu items. FLUX.1 Krea produced a more visually artistic photograph, but failed significantly on spelling and text style consistency.

The Reversed Rodeo

Text-to-Image

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

FLUX.1 Krea [dev]
GPT Image 1 Mini

AI Judge Analysis

FLUX.1 Krea [dev]

  • + Excellent high-contrast cinematic lighting
  • + Unique interpretation with the horse having cybernetic or space-faring equipment
  • + Clear and sharp resolution for both foreground and planet background
  • The horse's front legs and belly area have confusing anatomy and merging textures with the suit
  • Fails the negative constraint of 'horse on top'

GPT Image 1 Mini

  • + Natural and coherent composition
  • + Good texture on the astronaut suit and horse's coat
  • + Balanced placement of the moon and stars
  • Fails the specific prompt instruction 'horse on top, not vice versa'
  • Muted colors lack the high-detail cinematic punch requested in the prompt

Verdict: Both models failed the high-difficulty logic test of placing the horse on top of the astronaut (a reversal of the standard 'astronaut riding horse' trope). However, FLUX.1 Krea [dev] is the superior image due to its much higher visual fidelity, cinematic lighting, and more detailed rendering of the space setting compared to the flatter, more generic output of GPT Image 1 Mini.

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 Krea [dev]
GPT Image 1 Mini

AI Judge Analysis

FLUX.1 Krea [dev]

  • + Excellent lighting and high resolution details
  • + Clearer texture on the capybara fur
  • + The taxi sign on top of the car is a nice touch
  • Includes an extra passenger in the front seat
  • The cap looks like a construction helmet with 'Taxi' written on it
  • The passenger's phone handling looks slightly awkward with light artifacts

GPT Image 1 Mini

  • + Perfect adherence to the single passenger request
  • + More authentic NYC taxi driver cap design
  • + Excellent realization of the 'inside the car' perspective
  • The capybara's hand/paw on the steering wheel looks a bit human-like
  • Slightly less crisp than Model A

Verdict: GPT Image 1 Mini followed the prompt instructions more accurately by including only one passenger in the back seat, whereas FLUX.1 Krea [dev] added an extra person in the front. GPT Image 1 Mini also captured a more realistic taxi driver aesthetic with the checkered cap and focused perspective, making it the more successful interpretation of the 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.”

FLUX.1 Krea [dev]
GPT Image 1 Mini

AI Judge Analysis

FLUX.1 Krea [dev]

  • + Excellent intricate border design with webs and thorns.
  • + High-contrast, polished illustration style.
  • + Creative use of parchment scrolls for text elements.
  • Several typos in the small text including 'Pasty', 'nights', and 'Tright'.
  • The title text 'Halloween' is poorly spaced and overlapping slightly.

GPT Image 1 Mini

  • + Perfect adherence to all requested text with no spelling errors.
  • + Beautifully moody and atmospheric 'vintage' aesthetic.
  • + Very clear, legible layout for invitation details.
  • The border is a bit dark and muddy compared to the requested 'thorns and webs' detail.
  • Slightly less 'polished' look in terms of sharpness compared to Image A.

Verdict: While FLUX.1 Krea produced a more visually striking and detailed border, GPT Image 1 Mini is the better functional invitation because it rendered every piece of text correctly. FLUX.1 Krea suffered from significant spelling errors and nonsensical words ('Pasty Halloween'), whereas GPT Image 1 Mini captured the vintage gothic atmosphere perfectly with professional legibility.

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 Krea [dev]
GPT Image 1 Mini

AI Judge Analysis

FLUX.1 Krea [dev]

  • + Excellent PBR materials with realistic subsurface scattering on the fish
  • + Accurate 45-degree isometric perspective
  • + Clean, bold typography that matches the prompt's layout request
  • The flag is placed physically in the food rather than as a UI icon
  • The diorama base is a bit generic and stark white

GPT Image 1 Mini

  • + Clean arrangement of multiple sushi types with appetizing textures
  • + Small icon-style flag follows the typographic layout more naturally
  • + Inclusion of chopsticks adds to the miniature scene feel
  • The camera angle is more of a front-oblique rather than a true 45-degree top-down isometric view
  • The lighting is flatter compared to the realistic shadows in Image A

Verdict: FLUX.1 Krea [dev] followed the technical camera requirements more precisely, achieving a perfect isometric perspective and more realistic lighting transitions. While GPT Image 1 Mini produced a slightly more appealing variety of sushi, its perspective was slightly too low, and it lacked the high-end 3D render feel found in the other model.

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 Krea [dev]
GPT Image 1 Mini

AI Judge Analysis

FLUX.1 Krea [dev]

  • + Excellent fur texture rendering
  • + Strong lighting and atmospheric god rays
  • + Coherent butterly designs
  • Failed to include the baby bunny
  • Duplicated the tabby kitten instead of adding all requested animals

GPT Image 1 Mini

  • + Included all four requested animals (dog, cat, bunny, fox)
  • + Perfectly captures the 'tumbling' and 'chasing' motion described
  • + Excellent adherence to the 'dew sparkles' and sunrise lighting
  • The fox kit's anatomy is slightly unusual in the facial structure
  • Minor blurring on the edges of the kitten's paws

Verdict: GPT Image 1 Mini is the clear winner because it successfully included all four distinct animal types requested in the prompt, whereas FLUX.1 Krea failed by leaving out the bunny and duplicating the kitten. GPT Image 1 Mini also better captured the dynamic action of the animals tumbling together in the meadow.

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 Krea [dev]
GPT Image 1 Mini

AI Judge Analysis

FLUX.1 Krea [dev]

  • + Excellent hand-drawn woodcut aesthetic that fits the vintage theme.
  • + Good use of subtle texture and 'aged paper' background as requested.
  • + Integrated the steam effect elegantly into the cloche design.
  • Major spelling error where 'FLORIAN' became 'FLANDR'IN'.
  • The layout is a bit cluttered with overlapping elements.

GPT Image 1 Mini

  • + Perfect adherence to text, correctly spelling 'Caffè Florian' and 'Est. 1720'.
  • + Clean, minimalist composition that works well as a vector-style logo.
  • + Accurate representation of a cloche dome with steam.
  • Failed to follow the 'light background' instruction, using a black background instead.
  • The gold/bronze color on black feels more modern-luxe than the requested 'vintage brown and cream' aesthetic.

Verdict: FLUX.1 Krea [dev] captured the 'vintage' and 'subtle texture' requirements with much more artistic flair, but completely failed to spell the name of the restaurant correctly. GPT Image 1 Mini provided perfect text rendering and a cleaner layout, though it ignored the negative prompt regarding a light background. GPT Image 1 Mini is the winner for professional utility, as a logo with the wrong name is unusable.

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 Krea [dev]
GPT Image 1 Mini

AI Judge Analysis

FLUX.1 Krea [dev]

  • + Crisp, high-quality vector typography for the main title.
  • + Appropriate use of dark navy aesthetic common in space themes.
  • Failed to provide correct icons for most steps (e.g., Saturn with rings for launch, astronauts for translunar).
  • Non-sensical step numbering and garbled secondary text.
  • Poor infographic flow that doesn't follow a logical mission trajectory.

GPT Image 1 Mini

  • + Excellent adherence to all 6 specific steps and their requested icons.
  • + Consistent and clean flat-vector style with a perfect NASA-inspired palette.
  • + Logical visual flow following the sequence of the mission with legible text labels.
  • Slightly grainy texture on the background instead of a perfectly smooth vector finish.
  • The 'translunar' loop icon is a bit messy compared to the other clean icons.

Verdict: GPT Image 1 Mini followed the complex infographic instructions perfectly, creating a logical 6-step sequence with the correct icons for each phase. FLUX.1 Krea produced a higher resolution image but failed significantly on the content, depicting a planet with rings for step 1 and failing to render cohesive iconography or text for the mission steps.

Next steps

Explore each model