Black Forest Labs' flagship image generation model delivering state-of-the-art quality with exceptional realism, precision, and consistency for both text-to-image and advanced image editing
Settled by community votes across 13 shared challenges, with an AI judge weighing in on each.
FLUX.2 [max]
25.8
arena score
#10 of 62 in Text-to-Image
Skill signature
· Text-to-Image
FLUX1.1 [pro]
18.4
arena score
#50 of 62 in Text-to-Image
Vote tally
Where the votes landed
FLUX.2 [max]
0%
win rate
Ties
0%
FLUX1.1 [pro]
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.2 [max]
FLUX1.1 [pro]
AI Judge Analysis
FLUX.2 [max]
- + Excellent depiction of window lighting and cast shadows
- + Highly realistic textures on the book cover and wooden table
- + The glass cube has a sophisticated mirrored base and realistic reflections
- − The plant is slightly more obscured than requested in the prompt
FLUX1.1 [pro]
- + Clear visibility of the green plant through the glass
- + Vibrant colors and sharp focus on the central subject
- − The glass container is more of a rectangular prism than a cube
- − The floating sphere lacks physical interaction with the base, looking less grounded
- − The lighting is more generic and less directional compared to 'soft window light'
Verdict: FLUX.2 [max] captures the nuance of the lighting and material textures significantly better, resulting in a more photo-realistic image. While FLUX1.1 [pro] adheres well to the subject placement, its object geometry is slightly off (rectangular instead of cubic) and the lighting feels less natural than FLUX.2 [max].
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.2 [max]
FLUX1.1 [pro]
AI Judge Analysis
FLUX.2 [max]
- + Excellent adherence to the 'repairing' action with realistic mechanical detail
- + Strong execution of the motion blur in background traffic
- + Natural skin textures and highly detailed, realistic bicycle components
- − The man's kneeling posture on wet pavement feels slightly less 'candid' than requested
FLUX1.1 [pro]
- + Beautiful mood and bokeh with strong cinematic reflections
- + Captures the 'imperfect framing' and '50mm' street aesthetic well
- − Fails the prompt as the man is standing/holding the bike rather than repairing it
- − Severe anatomical and structural errors including a floating pedal and malformed bike frame
- − Missing the motion blur for passing cars
Verdict: FLUX.2 [max] is the clear winner as it accurately depicts the requested action of 'repairing' the bicycle with high mechanical realism and perfect adherence to secondary prompts like motion blur. FLUX1.1 [pro] creates a moody image but fails significantly on the primary action and contains glaring structural hallucinations, such as a floating bicycle pedal and a disconnected frame.
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.2 [max]
FLUX1.1 [pro]
AI Judge Analysis
FLUX.2 [max]
- + Excellent depiction of ornate, engraved plate armor with realistic lighting reflections.
- + Strong adherence to all prompt elements including hair beads and leather strap textures.
- + Clear composition that shows both the character and the equipment details.
- − The facial scars look a bit like surface-level scratches rather than deep battle-worn tissue.
FLUX1.1 [pro]
- + Extreme facial detail with very lifelike, piercing eyes and realistic skin texture.
- + Great use of bokeh sparks and atmospheric depth.
- − Composition is so tight that the 'ornate engraved plate armor' is mostly obscured.
- − Fails to clearly include the requested beads in the braided hair.
- − Armor appears more generic and less 'ornate' than requested.
Verdict: FLUX.2 [max] is the superior image as it adheres much better to the specific technical requests in the prompt, particularly the ornate engraving on the armor and the specific hair details like beads. While FLUX1.1 [pro] has a more striking, high-contrast facial portrait, it crops the armor out and misses several key descriptive details.
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.2 [max]
FLUX1.1 [pro]
AI Judge Analysis
FLUX.2 [max]
- + Excellent typography with clean, readable, bold sans-serif fonts.
- + Highly professional layout that looks like a ready-to-use menu.
- + Perfect adherence to the grid-based food photo request.
- − The placeholder text contains gibberish spelling.
- − Some photos in the Appetizers section actually show large pizzas or mains.
FLUX1.1 [pro]
- + Elegant presentation for a casual dining mockup.
- + Good inclusion of all requested sections including appetizers and pizza.
- + Realistic food photography within the grid.
- − The font rendering is blurry and largely illegible compared to the other model.
- − The grid layout is slightly less structured, with small icons and text overlapping.
- − The layout is more of a flyer/mockup than a functional design.
Verdict: FLUX.2 [max] significantly outperforms FLUX1.1 [pro] by delivering a highly functional, clean, and professional menu design with crisp typography. While FLUX1.1 [pro] offers a nice conceptual mockup, its text rendering and layout coherence do not match the professional standards demonstrated by FLUX.2 [max].
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.2 [max]
FLUX1.1 [pro]
AI Judge Analysis
FLUX.2 [max]
- + Excellent typography with fiery, glowing effects that perfectly match the prompt.
- + Superior 'exploded' view where individual components are clearly separated and detailed.
- + Crisp photorealistic textures on the bun, meat, and tomatoes.
- − The starburst for the price is slightly more generic in graphic style compared to the high-detail background.
FLUX1.1 [pro]
- + Nice use of depth of field with the out-of-focus flying debris.
- + Good lighting on the food items themselves.
- − The burger is not really 'exploded' into individual layers as requested, remaining largely intact.
- − Failed to include the price in a starburst.
- − Text is repetitive and 'Magic Burger' is rendered in blue neon which contradicts the fiery theme requested.
- − Unwanted gibberish text at the bottom of the image.
Verdict: FLUX.2 [max] followed every instruction in the prompt, including the specific fiery text effects and the starburst price tag, while delivering a true exploded view. FLUX1.1 [pro] failed on several technical requirements, including the layout of the burger components and the specific styling of the text and price.
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.2 [max]
FLUX1.1 [pro]
AI Judge Analysis
FLUX.2 [max]
- + Excellent adherence to the full text prompt including the complex third item.
- + Superior chalk texture and realistic smudge marks on the board.
- + Perfect layout and consistent handwriting style across the entire board.
- − The date line has a slightly repetitive dash style but is otherwise flawless.
FLUX1.1 [pro]
- + Natural-looking cursive for the 'Today's specials' heading.
- + Good café background atmosphere and lighting.
- − Failed to render the full text for the third menu item correctly, resulting in 'Chipkies'.
- − Hallucinated extra lines of text and incorrect prices (like '$228').
- − The handwriting looks more like a digital brush than physical chalk on a slate.
Verdict: FLUX.2 [max] followed the prompt instructions perfectly, including the full text of the third item and maintaining a consistent, realistic chalk texture. In contrast, FLUX1.1 [pro] struggled with the text accuracy, distorting the menu items and prices while failing to capture the authentic powdery texture of chalk.
The Reversed Rodeo
Text-to-Image“Horse riding astronaut in space — horse on top, not vice versa. Surreal, highly detailed, cinematic.”
FLUX.2 [max]
FLUX1.1 [pro]
AI Judge Analysis
FLUX.2 [max]
- + Excellent galactic background with high cinematic quality
- + Highly detailed spacesuit and horse anatomy
- + Effective surreal composition with the asteroid base
- − Failed the negative constraint: clearly shows the astronaut riding the horse, not the 'horse on top'
FLUX1.1 [pro]
- + Dynamic action pose with a dramatic sky
- + Good color contrast between the white horse and fiery mane
- + Consistent lighting across the subject and environment
- − Failed the negative constraint: astronaut is riding the horse instead of the horse being on top
- − Anatomical issues with the horse's rear right leg
- − Environment looks more like a high-altitude mountain than deep space
Verdict: Both models failed the specific spatial logic requested in the prompt ('horse on top, not vice-versa'), instead defaulting to the standard image of a person riding a horse. FLUX.2 [max] is the preferred image because it captures the 'in space' setting more effectively with a cinematic galaxy and asteroid, whereas FLUX1.1 [pro] looks like a terrestrial mountain landscape.
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.2 [max]
FLUX1.1 [pro]
AI Judge Analysis
FLUX.2 [max]
- + Successfully placed the passenger in the back seat as requested
- + Detailed capybara texture and realistic taxi interior controls
- + Captured the professional 'driving' pose well
- − Human hands are coming out of the capybara's sleeves instead of animal paws
- − The capybara's head is not wearing the hat correctly; it is floating behind the ears
FLUX1.1 [pro]
- + Excellent lighting and cinematic bokeh in the background
- + Vibrant colors and high visual clarity
- + Creatively interprets the 'paws' for the driver
- − Failed to place the passenger in the back seat, placing her in the front passenger seat instead
- − The passenger is looking toward the driver rather than being bored with her phone
- − The scale of the capybara relative to the car interior is slightly off
Verdict: FLUX.2 [max] followed the complex spatial instructions much better, correctly placing the passenger in the back seat while the capybara drives. FLUX1.1 [pro] produced a more aesthetically pleasing image with better lighting, but it failed the layout prompt by placing both characters in the front seat. FLUX.2 [max] is the winner for accurate prompt adherence despite the anatomical anomaly of human hands.
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.2 [max]
FLUX1.1 [pro]
AI Judge Analysis
FLUX.2 [max]
- + Perfect text accuracy for all components, including the specific date and location.
- + Excellent composition that feels like a professional digital poster with clear hierarchy.
- + Integrated the scroll banner and background elements seamlessly into a high-quality cinematic scene.
- − The parchment texture is subtle, mostly appearing on the outer edges rather than the central background.
FLUX1.1 [pro]
- + Strong aesthetic and vibrant colors with a nice glow from the jack-o-lantern.
- + Includes a full moon which enhances the 'moody night sky' requirement.
- − Contains significant text errors and repetitions, including 'Party' written thrice and repeated date/time lines.
- − The scroll banner text is misspelled as 'You inivted to a n night of frights'.
- − Ignored the square format request by placing a vertical poster on a grey background.
Verdict: FLUX.2 [max] followed every instruction perfectly, including complex text requirements and the specific square format, resulting in a polished and professional invitation. FLUX1.1 [pro] struggled with the layout and text rendering, exhibiting several spelling errors and redundant lines of information. FLUX.2 [max] is the clear winner for its superior text precision and adherence to the layout constraints.
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.2 [max]
FLUX1.1 [pro]
AI Judge Analysis
FLUX.2 [max]
- + Excellent typography with clean, bold text and a correct flag icon.
- + Perfect adherence to the isometric perspective and diorama base request.
- + Highly professional 3D render look with subtle PBR textures and soft lighting.
- − The diorama base is a bit large relative to the plate size.
FLUX1.1 [pro]
- + Bibrant colors and appealing cartoon style.
- + Effective use of soft lighting and clean background.
- − Failed to include the requested flag icon.
- − The text layout is less balanced, with 'SUSHI' being very small and hard to read.
- − Included more garnish/items than the requested 'minimal' amount.
Verdict: FLUX.2 [max] significantly outperformed in prompt adherence by correctly including all text elements and the Japanese flag icon, while maintaining a perfect isometric 45° angle. FLUX1.1 [pro] missed the flag, had poor text hierarchy, and did not follow the request for a simple, minimal plate as effectively.
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.2 [max]
FLUX1.1 [pro]
AI Judge Analysis
FLUX.2 [max]
- + Successfully included all four requested animals (dog, cat, rabbit, fox).
- + Excellent atmosphere with visible god rays and dew sparkles on the grass.
- + Clearer 8K-style resolution with distinct fur textures for all animals.
- − The fox kit has slightly strange proportions on its front legs.
- − The butterfly wings are a bit generic in design.
FLUX1.1 [pro]
- + Captures a very heartwarming and expressive 'joyful' vibe.
- + The lighting effects are warm and dreamlike.
- − Failed the prompt by missing the red fox kit completely.
- − The kitten and rabbit look very similar in color and texture, reducing variety.
- − The 'butterflies' are rendered as simple glowing blobs rather than detailed insects.
Verdict: FLUX.2 [max] is the clear winner as it adhered to the complex prompt by including all four specific animals, whereas FLUX1.1 [pro] missed the fox entirely. FLUX.2 [max] also better realized the '8K' and 'dew sparkles' requirements, providing a more detailed and immersive meadow 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.2 [max]
FLUX1.1 [pro]
AI Judge Analysis
FLUX.2 [max]
- + Perfect text accuracy for all requested strings including the grave accent.
- + Clean, minimalist vector aesthetic that fits the brand description.
- + High-quality subtle paper texture on the background.
- − The steam lines are a bit simplistic and less integrated into the vector style.
FLUX1.1 [pro]
- + Brilliant vintage engraving style with high artistic merit.
- + Sophisticated use of negative space for steam and highlights.
- + Elegant decorative border and frame composition.
- − Significant spelling errors in the brand name, rendering it 'Cafeé FRATILIAN'.
- − Fails to place 'Est. 1720' inside the banner as requested.
Verdict: FLUX.2 [max] (Model A) is the clear winner as it followed every instruction, specifically providing the correct text and placing it accurately within the banner elements. While FLUX1.1 [pro] (Model B) produced a more visually impressive 'vintage' illustration, the catastrophic failure in spelling the brand name makes it unusable for a logo task.
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.2 [max]
FLUX1.1 [pro]
AI Judge Analysis
FLUX.2 [max]
- + Excellent text rendering with no spelling errors in the names or mission steps.
- + Strict adherence to the NASA-inspired color palette and flat vector style.
- + Logical left-to-right progression that clearly communicates the story.
- − Repeats the label 'Earth Orbit' three times for different icons.
- − The Saturn V rocket illustration is a bit generic and lacks some of the iconic shuttle/rocket distinction.
FLUX1.1 [pro]
- + Stronger 'infographic' aesthetic with a central focal planetary body.
- + Better sense of scale and space in the composition.
- + Includes a clear header identifying the mission.
- − Poor typography with significant spelling errors ('Apollo 1', 'Trann strip', 'Deseort').
- − Incorrect icon usage, showing multiple Earths when the landing occurs on the Moon.
- − Confusing numbering system on the left sidebar.
Verdict: FLUX.2 [max] is the superior infographic because it is actually readable and provides accurate information, despite some repetitive labeling. FLUX1.1 [pro] has a more dynamic layout but fails significantly on text legibility and factual consistency by repeating Earth icons for lunar steps and misspelling the mission name as 'Apollo 1'.
Next steps
Explore each model
Black Forest Labs' enhanced 12-billion parameter flow transformer with 6x faster generation than FLUX.1 [pro], delivering superior composition, detail, and artistic fidelity