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]
25.9
arena score
#10 of 62 in Text-to-Image
Skill signature
· Text-to-Image
FLUX1.1 [pro] Ultra
17.9
arena score
#51 of 62 in Text-to-Image
Vote tally
Where the votes landed
FLUX.2 [max]
0%
win rate
Ties
0%
FLUX1.1 [pro] Ultra
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] Ultra
AI Judge Analysis
FLUX.2 [max]
- + Excellent depiction of soft window lighting with realistic shadows and highlights
- + Highly realistic textures on the leather-bound book and the wooden table surface
- + Physically grounded composition with the sphere resting on a mirrored base within the cube
- − The sphere is quite large relative to the cube, making it less of a 'small' sphere
- − The plant in the background is very blurry due to a shallow depth of field
FLUX1.1 [pro] Ultra
- + Perfect adherence to the 'small' sphere requirement
- + The glass cube has realistic thickness and green-tinted edges common in real glass
- + Rich, vibrant colors and clear visibility of the plant through the glass
- − The blue sphere appears to be floating unnaturally without a shadow or resting point
- − The lighting is a bit flat compared to the more atmospheric lighting in the other image
Verdict: FLUX.2 [max] produces a more photorealistic and atmospheric image with superior lighting and texture work, though the sphere is larger than requested. FLUX1.1 [pro] Ultra interprets the spatial relationship and relative sizes better, but the levitating sphere feels less physically realistic than the grounded composition of 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] Ultra
AI Judge Analysis
FLUX.2 [max]
- + Excellent shallow depth of field and bokeh realism.
- + The bicycle details and rainy texture feel highly authentic.
- + The elderly man's posture and skin texture are very natural and match the candid prompt.
- − The motion blur of the car is slightly less dynamic than Model B.
FLUX1.1 [pro] Ultra
- + Features a very strong motion blur that adds a sense of city movement.
- + The pavement reflections are clear and aesthetically pleasing.
- − The man appears to be standing or leaning rather than actively 'repairing' the bike.
- − The bicycle design is slightly less detailed and the framing feels too centered.
- − Shadows and lighting on the man feel slightly more artificial compared to the environment.
Verdict: FLUX.2 [max] captures the 'repairing' aspect and the '50mm' aesthetic much more effectively, providing a truly candid, close-up feel with realistic textures. While FLUX1.1 [pro] Ultra has great motion blur, it feels less like a repair scene and more like someone waiting to cross a street, failing the specific action of the prompt.
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] Ultra
AI Judge Analysis
FLUX.2 [max]
- + Excellent adherence to details like braided hair with beads and ornate engraved plate armor.
- + Highly realistic skin textures with visible scars, dirt, and lifelike eyes.
- + Strong atmospheric lighting that captures the warm torchlight and bokeh sparks perfectly.
- − Small anatomical oddity where a bead strand seems to emerge directly from the neck skin.
- − Background bokeh is a bit generic compared to the high-detail foreground.
FLUX1.1 [pro] Ultra
- − The image failed to load or is a solid black frame.
- − No prompt adherence visible.
Verdict: FLUX.2 [max] provided a high-quality, professional-grade portrait that captured every specific detail of the prompt, from the bead-threaded braids to the battle-worn texture of the armor. Since the output for FLUX1.1 [pro] Ultra resulted in a completely black image, FLUX.2 [max] is the winner by default and by merit of its strong performance.
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] Ultra
AI Judge Analysis
FLUX.2 [max]
- + Excellent structure that reads like a real menu.
- + Clear sections for Appetizers, Pizza, and Mains as requested.
- + Clean, professional grid-based layout for the food photography.
- − Font legibility on descriptions is slightly distorted.
- − Category and item mapping is inconsistent (Pizza under Mains).
FLUX1.1 [pro] Ultra
- + Dynamic mock-up presentation with a realistic paper fold.
- + High-quality, vibrant food photography.
- + Bold, modern sans-serif fonts.
- − Confusing text placement with headers disconnected from content.
- − Text goes off the page on the top section.
- − Layout is cluttered and lacks logical flow.
Verdict: FLUX.2 [max] produced a much more functional and realistic menu design that actually looks like it could be used in a restaurant, featuring clear categorization and a clean grid. FLUX1.1 [pro] Ultra has a nice mock-up aesthetic, but the actual graphic design is messy, with text clipping and poor organization.
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] Ultra
AI Judge Analysis
FLUX.2 [max]
- + Excellent text integration with the requested fiery, glowing effect on 'Magic Burger'.
- + Great dynamic sense of motion with the sauce swirl and floating crumbs.
- + Accurately follows the starburst request for the price tag.
- − The composition is a bit crowded vertically, making the top of the burger feel crushed by the text.
FLUX1.1 [pro] Ultra
- + Stunning cinematic lighting and high-quality rendering of the fiery coal background.
- + Perfect, crisp typography for the main title with a halo glow.
- + Very clean separation of ingredients showing the 'exploded' view clearly.
- − Failed to include the starburst for the '€6.99' price as requested.
- − Included some small, nonsensical AI-generated text/logos at the bottom corners.
Verdict: Both models performed exceptionally well on this complex prompt. FLUX.2 [max] followed the specific graphic design elements better, particularly the starburst price tag and the fiery treatment of the text, whereas FLUX1.1 [pro] Ultra produced a more aesthetically pleasing, cinematic image with superior lighting, despite missing the starburst detail.
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] Ultra
AI Judge Analysis
FLUX.2 [max]
- + Excellent adherence to text instructions with perfect spelling and no repetition.
- + Very realistic chalk texture including authentic smudges and dust on the board surface.
- + Sophisticated handwriting style that feels human and cohesive across the entire board.
- − The lighting is slightly dramatic, casting a heavy shadow on the right side of the board.
- − The cursive for the title is more of a stylized script than traditional cursive, but it still fits the prompt.
FLUX1.1 [pro] Ultra
- + Good contrast and clarity in the lettering against the chalkboard.
- + Accurately captures the 'cozy café' atmosphere in the background elements.
- − Significant text errors including 'TODAY SPECIALS' (missing 'S) and 'mushroomm ris'.
- − Repeats the final menu item and the footer text multiple times, creating a cluttered look.
- − Includes gibberish text like 'friistratnisnios' beneath the first item.
Verdict: FLUX.2 [max] is the clear winner as it followed the complex text requirements perfectly without any spelling errors or hallucinations. In contrast, FLUX1.1 [pro] Ultra struggled with the menu items, repeating phrases multiple times and failing to spell basic words correctly, which made the final output incoherent despite having a pleasant aesthetic.
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] Ultra
AI Judge Analysis
FLUX.2 [max]
- + Excellent cinematic lighting and texture on the horse and astronaut.
- + High level of detail in the asteroid and background galaxy.
- + Logical placement of the rider and mount.
- − Failed the negative constraint; the astronaut is riding the horse, not the other way around.
- − The concept is fairly standard and lacks the requested 'surreal' inversion.
FLUX1.1 [pro] Ultra
- + Dynamic composition with a sense of motion and scale.
- + Clean, bright visual style with clear rendering of the astronaut's gear.
- + Interesting inclusion of satellite-like debris in the background.
- − Completely failed the specific inversion prompt; the astronaut is riding the horse.
- − Significant anatomical error with an extra leg appearing behind the horse's front left leg.
Verdict: Both models failed the specific prompt instruction to place the 'horse on top' of the astronaut, both defaulting to the standard trope of an astronaut riding a horse. FLUX.2 [max] is the winner simply for producing a more coherent image without the glaring anatomical glitch (five legs) found in the FLUX1.1 [pro] Ultra output.
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] Ultra
AI Judge Analysis
FLUX.2 [max]
- + Successfully placed the human character in the back seat as requested.
- + Realistic cinematic lighting from the phone screen on the passenger's face.
- + Accurate capybara texture and facial expression.
- − Generated human hands for the capybara instead of paws.
- − The proportions of the interior are a bit cramped compared to a real taxi.
FLUX1.1 [pro] Ultra
- + High resolution and very clean visual quality.
- + Correctly interpreted the request for paws on the steering wheel.
- + Vibrant colors and clear background bokeh.
- − Failed the spatial composition by placing the passenger in the front seat next to the driver.
- − The passenger is also holding the steering wheel, causing a physical contradiction.
- − Human face looks slightly overly airbrushed/artificial.
Verdict: FLUX.2 [max] followed the complex spatial instructions much better, correctly placing the businesswoman in the back seat to create the intended humorous contrast. While FLUX1.1 [pro] Ultra has higher image clarity and correctly rendered paws, it failed significantly on the layout by putting the passenger in the front and giving her a second set of controls, which ruins the logic 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.2 [max]
FLUX1.1 [pro] Ultra
AI Judge Analysis
FLUX.2 [max]
- + Perfect text accuracy for all requested fields
- + Sophisticated cinematic lighting and atmospheric background
- + Subtle and professional integration of the border and thorns
- − The jack-o-lantern is placed centrally but breaks the parchment aesthetic slightly by appearing 3D in the middle
FLUX1.1 [pro] Ultra
- + Excellent 'vintage parchment' aesthetic with a scroll design
- + Clear and stylish border with thorns and webs
- − Failed the main title text by omitting the word 'Party'
- − Contains redundant and misspelled text ('noickt') below the banner
- − The jack-o-lantern looks more like a 2D illustration compared to the realism of the rest of the image
Verdict: FLUX.2 [max] followed the prompt instructions perfectly, rendering all text accurately and creating a cohesive, high-quality cinematic atmosphere. FLUX1.1 [pro] Ultra struggled with the text elements, missing words from the title and generating garbled redundant text in the middle of the invitation.
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] Ultra
AI Judge Analysis
FLUX.2 [max]
- + Excellent adherence to the 45 degree isometric perspective.
- + Text is perfectly sharp, bold, and accurately rendered.
- + Very clean, minimal aesthetic that fits the requested cartoon miniature style.
- − The diorama base is a bit plain compared to the subject matter.
FLUX1.1 [pro] Ultra
- + Beautiful material rendering, especially on the salmon texture.
- + Atmospheric lighting with subtle steam and soft shadows.
- + Creative interpretation with more varied set pieces.
- − Included unnecessary elements like a plant and a bug that were not requested.
- − The 'JAPAN' text is slightly less clean and integrated compared to Model A.
- − Includes a strange red beetle on the tray.
Verdict: FLUX.2 [max] followed the prompt's layout and specific text requirements with high precision, creating a clean and professional graphic output. FLUX1.1 [pro] Ultra created a more visually rich scene with better textures, but it ignored the 'minimal garnish' instruction and added several unrequested objects. FLUX.2 [max] is the winner for its superior adherence to the isometric technical style and layout.
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] Ultra
AI Judge Analysis
FLUX.2 [max]
- + Excellent anatomical accuracy for all four distinct animal species
- + Perfect lighting with realistic dew sparkles and sun rays
- + Detailed texture on fur and flower petals
- − The fox looks slightly stiff in its pose
- − A few butterfly shapes are a bit simplified
FLUX1.1 [pro] Ultra
- + Very cute and expressive 'big eyes' interpretation
- + Dreamy and soft lighting atmosphere
- − Anatomical errors: the rabbit has feline-like eyes and a cat-like nose
- − All animals have a very similar face shape, making the kitten and fox look almost identical
- − Less 'hyper-photorealistic' and more 'digital art/illustration' style
Verdict: FLUX.2 [max] is the clear winner as it successfully rendered four distinct species with accurate anatomy while maintaining the photorealistic requirement. FLUX1.1 [pro] Ultra produced a very cute image, but the animals lack species differentiation (the rabbit and kitten look like the same model with different ears) and the style leans too far into a digital illustration rather than a photograph.
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] Ultra
AI Judge Analysis
FLUX.2 [max]
- + Perfect text accuracy including the accented 'è'.
- + Clean minimalist vector aesthetic that perfectly matches the 'minimalist logo' instruction.
- + Excellent balance of elements and readable typography.
- − Steam lines are a bit thin compared to the rest of the stroke weights.
FLUX1.1 [pro] Ultra
- + Strong use of warm brown and cream tones.
- + High-quality shading on the cloche dome illustration.
- + Captures the vintage aesthetic well with bold shapes.
- − Spelling error in the main name ('Framilian' instead of 'Florian').
- − The composition is a bit crowded for a 'minimalist' logo request.
Verdict: FLUX.2 [max] followed the prompt instructions much better, specifically regarding the text 'Caffè Florian' and the 'minimalist' stylistic requirement. FLUX1.1 [pro] Ultra created a visually appealing vintage badge but failed on the primary text spelling and was too ornate for a minimalist prompt.
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] Ultra
AI Judge Analysis
FLUX.2 [max]
- + Excellent text legibility and accuracy for most terms
- + Clean, consistent infographic layout with logical flow
- + Good interpretation of the NASA-inspired color palette
- − Repeat labels like 'Earth Orbit' appearing over several different steps
- − The rocket design is a generic shuttle/stylized rocket rather than a Saturn V
- − Inconsistent iconography for the moon in the last two panels
FLUX1.1 [pro] Ultra
- + Highly creative and aesthetically pleasing composition
- + Excellent vector art style with professional spacing
- + Clearly identifies the topic with a large, bold header
- − Information flow is confusing and non-linear
- − Significant amount of gibberish text in the body sections
- − Failed to follow the requested 6-step logical sequence
Verdict: FLUX.2 [max] provides a much more functional infographic with high text accuracy and a logical progression of the mission steps, despite some repetitive labeling. FLUX1.1 [pro] Ultra has a superior artistic and professional vector aesthetic, but it fails as an infographic because the text is largely nonsensical and the mission stages are disorganized. FLUX.2 [max] is the winner for better prompt adherence and informational clarity.
Next steps
Explore each model
Black Forest Labs' ultra-high resolution image generation model, an enhanced version of FLUX1.1 [pro] optimized for premium quality output