Black Forest Labs' precision image generation model with maximum control, reliable text rendering, and complete creative control supporting up to 4MP output
Settled by community votes across 13 shared challenges, with an AI judge weighing in on each.
FLUX.2 [flex]
24.8
arena score
#14 of 62 in Text-to-Image
Skill signature
· Text-to-Image
FLUX1.1 [pro] Ultra
18.5
arena score
#49 of 62 in Text-to-Image
Vote tally
Where the votes landed
FLUX.2 [flex]
0.0%
win rate
Ties
0.0%
FLUX1.1 [pro] Ultra
100.0%
win rate
0.0%
0.0% ties
100.0%
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 [flex]
FLUX1.1 [pro] Ultra
AI Judge Analysis
FLUX.2 [flex]
- + Excellent adherence to lighting instructions with a clear soft glow from the left.
- + The glass cube has realistic thickness and refraction.
- + Colors are rich and saturated, particularly the red of the book.
- − The sphere appears significantly larger than the 'small' sphere requested.
- − The book has no text on the spine and a very simplified texture.
FLUX1.1 [pro] Ultra
- + Provides a small blue sphere as requested, creating a better sense of scale.
- + High visual fidelity on textures, such as the grain of the book cover and the dust on the glass.
- + Text on the book spine adds a layer of realism to the object.
- − The blue sphere is levitating, which looks physically unnatural.
- − The glass cube edges appear slightly distorted where they meet the table.
Verdict: FLUX1.1 [pro] Ultra produced a more detailed and accurately scaled image, capturing the 'small' nature of the sphere and adding realistic textures to the book and glass. However, FLUX.2 [flex] handled the physics of the scene better, as the sphere in FLUX1.1 was inexplicably floating in the center of the cube.
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 [flex]
FLUX1.1 [pro] Ultra
AI Judge Analysis
FLUX.2 [flex]
- + Excellent depiction of skin texture and elderly features
- + The lighting and reflections on the pavement are very realistic
- + Better adherence to the 'imperfect framing' and 'shallow depth of field' requirements
- − The bike anatomy is slightly warped with the chain appearing to lead nowhere
FLUX1.1 [pro] Ultra
- + Strong execution of the motion blur from passing cars
- + High overall clarity and sharp details on the subject
- + Compelling wet pavement reflections and rainy atmosphere
- − The man appears to be standing and pushing the bike rather than actively 'repairing' it
- − The skin texture looks slightly too clean and digital compared to the 'natural' request
Verdict: FLUX.2 [flex] feels more authentic to the request for a 'candid' shot with its tighter focus on the man's hands and face, accurately capturing natural skin aging and a sense of repair. FLUX1.1 [pro] Ultra has better motion blur effects for the cars, but the subject is just standing near the bike, making FLUX.2 [flex] the winner for better prompt adherence and realism.
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 [flex]
FLUX1.1 [pro] Ultra
AI Judge Analysis
FLUX.2 [flex]
- + Exquisite detail on the engraved plate armor and leather straps.
- + Captures all prompt elements including braided hair with beads and bokeh sparks.
- + Realistic skin texture with appropriate grime and scarring.
- − The torch in the background has a slightly artificial blue flame at the base.
- − The scars look a bit like surface paint rather than deep tissue healing.
FLUX1.1 [pro] Ultra
- − The image failed to load or is a solid black frame.
- − Complete failure to generate viewable content.
Verdict: FLUX.2 [flex] successfully generated a high-quality, detailed portrait that adheres to every aspect of the prompt, showing impressive texture work on the armor and clothing. FLUX1.1 [pro] Ultra failed to produce an image, resulting in a black frame. Therefore, FLUX.2 [flex] is the winner by default and by merit of quality.
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 [flex]
FLUX1.1 [pro] Ultra
AI Judge Analysis
FLUX.2 [flex]
- + Excellent typography and readability with clean sans-serif fonts
- + Perfect adherence to requested sections (Appetizers, Pizza, Mains)
- + High quality food photography and professional grid layout
- − The placeholder text (lorem ipsum style) is messy in some areas
FLUX1.1 [pro] Ultra
- + Dynamic angled presentation creates a realistic mockup feel
- + Vibrant colors and high-energy composition
- − Failed to organize the content into logical sections as requested
- − Minor spelling errors like 'Pizzzans' and 'Appet Love'
- − Grid layout is cluttered and less functional for a menu
Verdict: FLUX.2 [flex] produced a much more functional and professional menu design, clearly delineating the requested sections for Appetizers, Pizza, and Mains with superior legibility. FLUX1.1 [pro] Ultra created a visually busy mockup that struggled with text accuracy and logical organization, making it less suitable as a menu design template.
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 [flex]
FLUX1.1 [pro] Ultra
AI Judge Analysis
FLUX.2 [flex]
- + Excellent text integration with the requested fiery, glowing effect on all elements
- + Highly photorealistic food textures including the sesame bun, dripping sauce, and crisp lettuce
- + Strong adherence to the 'starburst' requirement for the price tag
- − The burger feels slightly less 'exploded' than Model B, appearing more like a tall stack
- − The background embers are a bit repetitive in pattern
FLUX1.1 [pro] Ultra
- + Dynamic 'exploded' composition with many flying ingredients and debris
- + Impressive lighting from the bottom coals reflecting on the burger components
- + High clarity and resolution in the rendered text
- − Failed to include the price in a starburst as requested
- − The background includes unnecessary and nonsensical footer text at the bottom
- − The burger structure is physically confusing with multiple patty layers blended strangely
Verdict: FLUX.2 [flex] is the clear winner for its superior prompt adherence, particularly regarding the 'starburst' price tag and the glowing text effects. While FLUX1.1 [pro] Ultra has a more chaotic and exciting 'exploded' layout, it suffers from hallucinated text at the bottom and fails to follow specific layout instructions for the pricing.
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 [flex]
FLUX1.1 [pro] Ultra
AI Judge Analysis
FLUX.2 [flex]
- + Excellent typography with perfect spelling of all requested menu items.
- + Consistent and elegant cursive chalk handwriting style as requested.
- + Realistic chalk texture with believable smudges and lighting.
- − The handwriting is so uniform it almost looks like a digital script font despite the texture.
FLUX1.1 [pro] Ultra
- + Natural variation in handwriting captured the 'hand-drawn' feel well.
- + Good use of chalk texture on the edges of the board.
- − Numerous spelling and repetition errors including 'muushroomm' and 'friistratnisnios'.
- − Failed the apostrophe in 'TODAY’S' and included several redundant lines of text.
- − Messy and disorganized layout compared to the prompt's request for elegance.
Verdict: FLUX.2 [flex] successfully rendered all text with 100% accuracy and followed the stylistic instructions for an elegant cursive title. In contrast, FLUX1.1 [pro] Ultra struggled significantly with text coherence, resulting in numerous spelling errors and repetitive lines of text that made the menu illegible.
The Reversed Rodeo
Text-to-Image“Horse riding astronaut in space — horse on top, not vice versa. Surreal, highly detailed, cinematic.”
FLUX.2 [flex]
FLUX1.1 [pro] Ultra
0% wins
0% ties
100% wins
AI Judge Analysis
FLUX.2 [flex]
- + Successfully followed the difficult spatial reasoning prompt of having the horse on top.
- + Creates a surreal and cinematic atmosphere with high-quality nebulas and lighting.
- + The interaction between the horse holding the astronaut's shoulders is creative and fits the 'surreal' tag.
- − The horse's front legs merging into the astronaut's hands is slightly anatomically confusing.
FLUX1.1 [pro] Ultra
- + High visual clarity and clean rendering of the planetary background.
- + Good detail on the spacesuit and horse's mane.
- − Failed the negative constraint entirely by placing the astronaut on top of the horse.
- − Composition is more generic and less 'surreal' than requested.
Verdict: FLUX.2 [flex] is the clear winner because it correctly interpreted the complex spatial instruction to have the horse on top of the astronaut, whereas FLUX1.1 [pro] Ultra defaulted to a standard horse-riding pose despite the specific prompt instructions. FLUX.2 [flex] also delivered a more cinematic and surreal aesthetic that better matches the requested tone.
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 [flex]
FLUX1.1 [pro] Ultra
AI Judge Analysis
FLUX.2 [flex]
- + Perfect adherence to the prompt's layout with the woman in the back seat.
- + Detailed capybara texture and realistic driver's uniform.
- + Captures the busy, vibrant bokeh of Manhattan streets.
FLUX1.1 [pro] Ultra
- + High resolution and clean rendering.
- + The capybara's expression is very calm and focused.
- + Interesting cinematic lighting.
- − Major failure on spatial logic with the passenger appearing to sit in the front passenger seat.
- − The woman is holding her phone over the steering wheel area, confusing the roles of driver and passenger.
- − The capybara's hat is a simple baseball cap rather than a professional driver's cap.
Verdict: FLUX.2 [flex] successfully followed the complex instruction to place the businesswoman in the back seat, creating a coherent narrative of a taxi ride. FLUX1.1 [pro] Ultra failed significantly by placing the passenger in the front seat right next to the driver, which contradicts the core instruction and the standard taxi layout.
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 [flex]
FLUX1.1 [pro] Ultra
AI Judge Analysis
FLUX.2 [flex]
- + Excellent text rendering with no spelling errors.
- + Sophisticated, artistic parchment edge effect and moody atmosphere.
- + Perfect adherence to all requested elements including specific date/time.
- − The jack-o-lantern is placed slightly over the scroll banner, making the composition a bit tight.
FLUX1.1 [pro] Ultra
- + Ornate border with highly detailed thorns and webs.
- + Strong composition with a clear central focal point and scroll aesthetic.
- − Redundant text and spelling errors ('noickt or').
- − Title text is missing the word 'Party' as requested in the prompt.
- − The 'central' jack-o-lantern is actually positioned in the top half.
Verdict: FLUX.2 [flex] followed all prompt instructions perfectly, including the complex text requirements and the full event details without errors. FLUX1.1 [pro] Ultra created a more elaborate border, but it struggled with text accuracy, repeating the invitation banner and misspelling words. FLUX.2 [flex] is the superior choice for its professional finish and perfect text adherence.
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 [flex]
FLUX1.1 [pro] Ultra
AI Judge Analysis
FLUX.2 [flex]
- + Excellent typography including the bold text and flag icon exactly as requested.
- + Clean, minimalist aesthetic that feels like a polished 3D render.
- + Adheres strictly to the 'small raised diorama base' and 'minimal garnish' instructions.
- − The sushi models are a bit plastic-looking, lacking the PBR textures mentioned in the prompt.
FLUX1.1 [pro] Ultra
- + Superior texture work and light scattering, especially on the salmon nigiri.
- + More sophisticated composition with attractive 3D elements like the plant and steam.
- + Captures the soft, refined 3D lighting very effectively.
- − Included unnecessary elements like a small ladybug and excessive garnish.
- − The text is less 'bold' and prominent compared to the request.
- − The flag icon is very small and integrated rather than floating top-center as implied.
Verdict: FLUX.2 [flex] followed the layout and typography requirements more precisely, creating a clean graphic design suitable for an icon or card. FLUX1.1 [pro] Ultra produced a much higher quality 3D render with beautiful lighting and texture, though it struggled with the specific text placement and included extraneous details like a small insect. FLUX.2 [flex] is the winner for strict adherence to the prompt's layout and font instructions.
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 [flex]
FLUX1.1 [pro] Ultra
AI Judge Analysis
FLUX.2 [flex]
- + Excellent adherence to the 'chasing and tumbling' action described in the prompt
- + Superior detail in fur textures and individual dew drops on the grass
- + Captures the specific lighting effects like god rays and background mist perfectly
- − The fox kit looks slightly older/more mature than the other baby animals
FLUX1.1 [pro] Ultra
- + Strongly emphasizes the 'big expressive eyes' and 'wholesome' cute factor
- + Soft, dreamy lighting and color palette create a cohesive aesthetic
- − The animals are largely static and sitting rather than 'tumbling' or 'chasing'
- − Leans toward a digital illustration or 'Disney' style rather than being hyper-photorealistic
- − Anatomical features on the fox and bunny are a bit simplified
Verdict: FLUX.2 [flex] produced a much more dynamic and realistic scene that accurately captured the action of animals playing, along with high-fidelity environmental details like dew and god rays. FLUX1.1 [pro] Ultra created a very cute, stylized image, but it failed the 'hyper-photorealistic' requirement and ignored the active verbs in the prompt in favor of a static group portrait.
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 [flex]
FLUX1.1 [pro] Ultra
AI Judge Analysis
FLUX.2 [flex]
- + Excellent typography with perfect spelling of 'Caffè Florian'
- + Clean minimalist vector aesthetic that feels modern yet vintage
- + Accurately represents all prompt elements including the banner and steam
- − The steam element is very faint and thin
FLUX1.1 [pro] Ultra
- + Rich, complex vector emblem style
- + Good use of the 'Est. 1720' text and logo circularity
- − Incorrectly spelled the brand name as 'Caffé Framilian'
- − Lacks the 'minimalist' quality requested in the prompt
- − The typography is much thicker and less elegant than Model A
Verdict: FLUX.2 [flex] adhered perfectly to the spelling and the minimalist style requested, producing a professional-looking logo. FLUX1.1 [pro] Ultra failed on the text spelling and produced a much busier design that ignored the 'minimalist' keyword, despite having a nice vintage feel.
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 [flex]
FLUX1.1 [pro] Ultra
AI Judge Analysis
FLUX.2 [flex]
- + Excellent typography with clean, legible text including the 'Apollo 11' title.
- + Adheres strictly to the requested steps and color palette.
- + Superior hierarchy and layout that is easy to follow logically.
- − Missed the final 'Landing' step from the numbered list, stopping at 'Descent'.
- − The connection between the translunar arc and the moon is slightly disjointed.
FLUX1.1 [pro] Ultra
- + Creative use of the lunar surface as a base for the infographic.
- + Includes more complex vector illustrations and detailed secondary elements.
- − Text is largely nonsensical 'lorem ipsum' style or gibberish (e.g., 'THE ABOUT FING IF').
- − The logical flow of the infographic is confusing and non-linear.
- − Fails to maintain the clean, minimalist 'flat-vector' aesthetic requested by including cluttered details.
Verdict: FLUX.2 [flex] successfully captures the clean, modern infographic aesthetic with legible and professional typography. FLUX1.1 [pro] Ultra attempts a more complex composition but fails significantly on text rendering and clarity, resulting in a cluttered page with unreadable information. FLUX.2 [flex] is the clear winner for its functional design and adherence to the NASA-inspired theme.
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