Black Forest Labs' enhanced 12-billion parameter flow transformer with 6x faster generation than FLUX.1 [pro], delivering superior composition, detail, and artistic fidelity
Settled by community votes across 13 shared challenges, with an AI judge weighing in on each.
FLUX1.1 [pro]
#50 of 62 in Text-to-Image
GPT Image 1 Mini
#13 of 62 in Text-to-Image
Where the votes landed
FLUX1.1 [pro]
0%
win rate
Ties
0%
GPT Image 1 Mini
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
FLUX1.1 [pro]
- + Exquisite lighting and reflections on the glass and sphere surfaces.
- + Realistic botanical background with accurate refraction through the glass.
- + High-resolution texture on the red book cover.
- − The glass container is a tall rectangular prism rather than a 'cube'.
- − The sphere appears to be floating unnaturally in the center.
GPT Image 1 Mini
- + The glass container is a perfect cube as requested.
- + Realistic placement of the sphere resting on the bottom surface.
- + Accurate interpretation of 'small blue sphere' relative to the cube size.
- − The green plant is placed to the side rather than 'behind the cube' visible through the glass.
- − The lighting on the book is somewhat flat compared to the rest of the scene.
Verdict: FLUX1.1 [pro] produced a much more visually stunning image with superior lighting and materials, but it failed to generate a cube, providing a tall rectangle instead. GPT Image 1 Mini followed the geometric requirements and placement of the sphere better, though the plant placement was less accurate to the prompt and the overall render quality was more muted. FLUX1.1 [pro] is the winner for its photographic realism and complex handling of glass refraction.
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
FLUX1.1 [pro]
- + Excellent wet pavement reflections that enhance the cinematic feel.
- + Good use of bokeh and background lighting to create depth.
- + Strong adherence to the 'light rain' and 'passing cars' prompts.
- − Major anatomical and structural issues with the bicycle's frame and the man's pose.
- − The bicycle appears fragmented and physically impossible under the handlebars.
- − The man's hands on the handlebars do not look natural.
GPT Image 1 Mini
- + Superb skin texture and facial detail that looks highly realistic.
- + The bicycle's structure remains coherent and logical while being repaired.
- + Captures the 'candid' and 'natural' look perfectly with subtle rain droplets on surfaces.
- − Misses the 'motion blur from passing cars' request in the background.
- − The background cars are blurred by depth of field but don't clearly show motion.
Verdict: While FLUX1.1 [pro] does a better job of capturing the atmospheric elements like reflections and car motion, the bicycle's structure is completely broken and nonsensical. GPT Image 1 Mini provides a far more realistic image with incredible skin textures and a coherent subject, successfully looking like a genuine 50mm candid photograph despite missing the motion blur requirement.
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
FLUX1.1 [pro]
- + Extremely lifelike eye details with realistic light refraction.
- + Superior skin texture showing pores, dirt, and fine scarring with high fidelity.
- + Excellent depth of field with realistic foreground and background blur.
- − Fails to show the 'small beads' requested in the braids.
- − The engraving on the armor is less intricate than the competing image.
GPT Image 1 Mini
- + Beautifully intricate and coherent engraving on the plate armor.
- + Captures the warm torchlight ambiance very effectively across the whole scene.
- + Shows visible beads within the braided hair as requested.
- − Skin texture looks somewhat painterly or smoothed compared to Model A.
- − The eyes look slightly flat and lack the 'lifelike' sparkle of a high-end photograph.
Verdict: FLUX1.1 [pro] produces a much more realistic photographic portrait with incredible detail in the skin and eyes, though it missed the specific detail of beads in the hair. GPT Image 1 Mini adhered better to the specific decorative prompt elements and armor engraving but lacks the raw visual fidelity and 'lifelike' quality seen in the skin textures of FLUX1.1 [pro].
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
FLUX1.1 [pro]
- + Excellent photo-realistic food photography with authentic lighting
- + Captures the professional look of a tri-fold or complex menu layout
- + Includes actual price markers and descriptive text elements
- − The text is mostly gibberish upon close inspection
- − Grid for food photos is somewhat messy and inconsistent in cell sizing
GPT Image 1 Mini
- + Perfectly adheres to the grid request with clean, uniform photo blocks
- + Clear, legible section headers for Appetizers, Pizza, and Mains
- + Very clean, minimalist aesthetic that fits the modern prompt
- − Lacks actual menu item descriptions or prices under the headers
- − The food images appear slightly more generic or stock-like compared to Model A
Verdict: GPT Image 1 Mini adhered much more strictly to the prompt specifications, specifically the grid layout and the requested categories (Appetizers/Pizza/Mains), resulting in a perfect template design. While FLUX1.1 [pro] produced more vibrant and realistic food photography, its layout was more chaotic and the text was illegible.
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
FLUX1.1 [pro]
- + Excellent photorealistic texture on the burger patties and buns
- + Good cinematic lighting and high-quality background bokeh
- − Failed to explode the burger layers, resulting in a mostly intact stack
- − Text lacks the requested 'fiery, glowing effect' and is doubled/poorly arranged
- − Missing the starburst for the price
GPT Image 1 Mini
- + Strong prompt adherence for the 'exploded' architecture of the burger
- + Perfectly followed text instructions, including the fiery effect and starburst price tag
- + Colors are vibrant and evoke a magical/fiery theme well
- − The burger ingredients look slightly less realistic compared to Model A
- − Composition is a bit static despite the floating elements
Verdict: While FLUX1.1 [pro] has superior photorealistic textures, it failed significantly on the layout and text styling of the prompt. GPT Image 1 Mini adhered to every specific detail of the prompt, including the exploded burger layers, the starburst price tag, and the fiery text effects, making it the more successful advertisement as a whole.
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
FLUX1.1 [pro]
- + Excellent handwritten flow with natural slants and variations.
- + Beautifully rendered background with cozy café atmosphere and bokeh lighting.
- − Hallucinated text by splitting the octopus item into two separate lines with incorrect prices.
- − Failed to complete the final word correctly, rendering 'Chipkies' instead of 'Cookies'.
GPT Image 1 Mini
- + Perfect text accuracy, including the spelling of 'Cookies' and all price values.
- + Excellent chalk texture that looks authentically dusty and porous.
- + Successfully followed the layout for long menu items by wrapping text properly.
- − The cursive title is very blocky and lacks the 'elegant cursive' style requested.
- − The background is very plain compared to the requested 'cozy café' atmosphere.
Verdict: While FLUX1.1 [pro] creates a much more atmospheric and visually appealing café environment, it struggles significantly with following the specific menu instructions, hallucinating extra lines and misspelling the final item. GPT Image 1 Mini captures the authentic texture of chalk much better and reproduces the text prompt with 100% accuracy, making it the more reliable choice for this specific task despite the simpler background.
The Reversed Rodeo
Text-to-Image“Horse riding astronaut in space — horse on top, not vice versa. Surreal, highly detailed, cinematic.”
AI Judge Analysis
FLUX1.1 [pro]
- + Excellent cinematic lighting and color range.
- + High level of detail in the astronaut's suit and horse's mane.
- − Failed the negative constraint; the astronaut is riding the horse, not the other way around.
- − The horse has an extra leg visible at the bottom.
GPT Image 1 Mini
- + Atmospheric space background with good depth.
- + Clean composition and texture on the horse.
- − Failed the negative constraint; the astronaut is riding the horse.
- − Slightly less creative interpretation of the cinematic prompt compared to the lighting in model A.
Verdict: Both models failed to follow the specific negative constraint to place the horse on top of the astronaut, instead providing the common 'astronaut on a horse' trope. FLUX1.1 [pro] produced a more visually striking, cinematic image with superior lighting, while GPT Image 1 Mini was more grounded but ultimately less impressive in detail.
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
FLUX1.1 [pro]
- + Dynamic lighting with warm yellow tones consistent with taxi interior
- + High aesthetic quality and sharp focus on subjects
- − The passenger is sitting in the front passenger seat rather than the back seat
- − The capybara's paws are not visible on the steering wheel
- − The perspective is from the trunk or rear window rather than inside the cabin viewing the driver from the back
GPT Image 1 Mini
- + Strict adherence to the layout with the passenger correctly placed in the back seat
- + Accurately depicts the capybara with its paws on the steering wheel
- + Perfectly captures the 'bored' expression of the businesswoman
- − Lighting is slightly flatter and less cinematic than the competitor
- − The passenger's right hand holding the phone has some minor anatomical blurring
Verdict: GPT Image 1 Mini is the clear winner for prompt adherence, correctly placing the passenger in the back seat and showing the capybara's paws on the wheel as requested. While FLUX1.1 [pro] has more vibrant lighting and higher resolution, it failed the spatial instructions by placing the passenger in the front seat and missing the steering wheel interaction.
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
FLUX1.1 [pro]
- + Features a vivid, high-contrast glow on the jack-o-lantern and moon
- + Intricate thorn border and jagged paper edges enhance the gothic theme
- + Excellent cinematic lighting and depth of field
- − Significant text repetition and spelling errors ('Halloween Party Party', 'You inivted')
- − Does not adhere to the requested square format
- − Layout feels cramped with redundant lines of information at the bottom
GPT Image 1 Mini
- + Perfect text accuracy and clean typography layout
- + Adheres correctly to the square format requested
- + Authentic vintage parchment texture and moody gothic aesthetic
- − Visuals are slightly more muted and less 'cinematic' than Model A
- − The border details (webs and thorns) are quite dark and difficult to see
Verdict: While FLUX1.1 [pro] has superior lighting and illustration quality, it fails significantly on text rendering and format adherence. GPT Image 1 Mini provides a much more usable invitation with perfect text accuracy and the correct square aspect ratio, making it the more successful design overall.
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
FLUX1.1 [pro]
- + Excellent variety of sushi items on the diorama
- + High-quality soft clay-like textures with clean shading
- + Perfectly matches the 45-degree isometric angle requested
- − Failed to include the small flag icon
- − The 'SUSHI' text is somewhat thin and harder to read compared to 'JAPAN'
GPT Image 1 Mini
- + Successfully included all text elements and the Japanese flag icon
- + Distinct and clear font choice for both words
- + Very clean, minimal composition that follows 'minimal garnish' instruction
- − The diorama base has a slight perspective misalignment with the round plate
- − Lower complexity in the sushi variety compared to Model A
Verdict: While both models adhered well to the isometric 3D cartoon style, Model B (GPT Image 1 Mini) is the winner for following the prompt's secondary details more accurately, specifically by including the requested flag icon and keeping the text bold and legible. FLUX 1.1 [pro] produced a more visually rich scene with better textures, but missed a key prompt instruction.
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
FLUX1.1 [pro]
- + Excellent rim lighting and backlighting effect on the fur
- + Highly expressive, larger-than-life eyes that convey a wholesome vibe
- + Consistent color palette across the different animals
- − Missed one of the four requested animals (red fox kit)
- − The animals are sitting rather than 'playfully chasing and tumbling'
- − The butterflies look like glowing blobs rather than detailed insects
GPT Image 1 Mini
- + Successfully included all four requested animals (dog, cat, bunny, and fox)
- + Dynamic action pose matches the 'chasing and tumbling' request perfectly
- + Realistic lighting with visible god rays and dew sparkles in the grass
- − The fox kit has slightly unusual black paws that look a bit muddy
- − The bunny's ears are a bit small compared to typical baby bunnies
Verdict: GPT Image 1 Mini is the clear winner as it followed the complex prompt more accurately, including all four specific animals and depicting the requested action of running and chasing. FLUX1.1 [pro] produced a beautiful, high-quality image, but it failed to include the fox and the animals are static rather than active.
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
FLUX1.1 [pro]
- + Excellent vintage illustration style with detailed etching on the cloche.
- + Beautiful composition with a classic border and subtle background texture.
- + Captures the 'warm brown and cream tones' perfectly.
- − Failed the primary text prompt, spelling it 'Cafeé FRATILIAN'.
- − The steam effect is very thin and almost looks like a crack in the image.
GPT Image 1 Mini
- + Perfect text rendering for both 'Caffè Florian' and 'EST. 1720'.
- + Clean, minimalist vector aesthetic that is very readable.
- + Clear interpretation of the steam element.
- − Ignored the request for a 'light background', providing a black one instead.
- − The cloche dome is very basic compared to the artistic vintage style requested.
Verdict: GPT Image 1 Mini followed the textual instructions perfectly, providing accurate spelling and a clear layout, though it failed the background color requirement. FLUX1.1 [pro] produced a much more sophisticated and artistic vintage emblem that matched the requested 'light background' and 'texture', but it significantly hallucinated the brand name spelling. GPT Image 1 Mini is the better choice for a logo use-case where correct spelling is critical.
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
FLUX1.1 [pro]
- + Excellent NASA-inspired color palette.
- + Sophisticated layout that feels like a real modern poster.
- + High-quality vector aesthetic with clean lines.
- − Text is largely gibberish or misspelt.
- − The numerical sequence is disordered or non-linear.
- − The large central moon dominates and confuses the actual trajectory steps.
GPT Image 1 Mini
- + Perfect adherence to the 6 requested steps in the correct order.
- + Text is perfectly legible and correctly spelled.
- + Strong iconography that matches the specific prompts for each step.
- − The 'Translunar' trajectory graphic is messy and contains weird loops.
- − Composition is a bit crowded and simplistic compared to a professional poster.
- − The background is a slightly off-white/beige rather than the light gray requested.
Verdict: GPT Image 1 Mini is the clear winner for follow-through on the prompt's logical requirements, accurately depicting all six steps of the mission with perfect text rendering. While FLUX1.1 [pro] captures a more high-end 'professional designer' look and better color balance, it fails at the basic task of sequence and legibility.
Explore each model
OpenAI's cost-effective image generation model for when image quality isn't the top priority