Black Forest Labs' 12-billion parameter flow transformer for high-quality text-to-image generation, suitable for personal and commercial use with streaming support
Settled by community votes across 13 shared challenges, with an AI judge weighing in on each.
FLUX.1 [dev]
#16 of 62 in Text-to-Image
FLUX.2 [flex]
#14 of 62 in Text-to-Image
Where the votes landed
FLUX.1 [dev]
0%
win rate
Ties
0%
FLUX.2 [flex]
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
FLUX.1 [dev]
- + Excellent photorealistic textures on the leather book and wooden table.
- + Highly realistic light refraction and reflections through the glass cube.
- − The sphere appears more cyan/teal than the requested true blue.
- − The glass cube has internal glass structural lines that make it look like multiple plates rather than a simple cube.
FLUX.2 [flex]
- + Perfect adherence to the 'blue' color request for the sphere.
- + Accurately places the plant behind the glass with realistic distortion and visibility.
- + Clean, simple geometry for the glass cube.
- − The sphere's texture is slightly flat and matte compared to the environment.
- − Lighting on the table is a bit more diffused/uniform than Model A.
Verdict: Both models followed the complex spatial instructions perfectly. FLUX.1 [dev] produced a more tactile and photorealistic image, especially regarding textures and light refraction, while FLUX.2 [flex] achieved better color accuracy for the blue sphere and presented a cleaner composition of the green plant through the glass.
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
FLUX.1 [dev]
- + Excellent depiction of raindrops in the air and on the subject's clothing.
- + Captures the request for motion blur from a passing car accurately.
- + Very natural skin texture and realistic, candid body language.
- − The subject appears to be just holding the bike rather than actively repairing it.
- − The bicycle is missing its front wheel, which looks like a structural error rather than an intentional repair state.
FLUX.2 [flex]
- + Strong composition that feels like an authentic street photograph with 'imperfect framing'.
- + Better adherence to the 'repairing' action with the subject kneeling and working on the chain.
- + Excellent lighting and reflections on the wet pavement.
- − The bike's handlebars and frame geometry are somewhat distorted and physically impossible.
- − The motion blur on the cars is a bit more static/frozen compared to Model A.
Verdict: FLUX.2 [flex] wins this comparison by better capturing the specified action ('repairing') and the requested 'imperfect framing' of a candid street photo. While FLUX.1 [dev] handles the atmospheric effects like rain and motion blur with slightly more technical precision, its failure to show the man actually repairing the bike (and the missing wheel) makes it less successful overall.
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
FLUX.1 [dev]
- + Extremely high visual quality with lifelike eyes and skin texture.
- + Beautiful use of shallow depth of field and soft bokeh.
- + Compelling lighting with subtle reflections on the armor.
- − Missed several prompt elements like beads in the hair and faint scars.
- − Armor lacks the requested ornate engravings.
- − Subject appears more like a modern person in a costume than a battle-worn paladin.
FLUX.2 [flex]
- + Excellent adherence to all prompt details including beads, scars, and ornate engravings.
- + Perfectly captures the 'battle-worn' aesthetic with dirt and visible wounds.
- + Stunning detail on the leather straps and textured cloth underlayer.
- − Lighting on the face is slightly flat compared to the dramatic lighting on the armor.
- − The bokeh sparks are a bit uniform in size and distribution.
Verdict: While FLUX.1 [dev] produces a technically beautiful portrait with incredible skin and eye realism, it fails to include many of the specific descriptive elements requested. FLUX.2 [flex] is the clear winner as it perfectly captures every detail of the prompt, from the beaded braids and scars to the intricate engravings on the armor and the texture of the underlayers.
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
FLUX.1 [dev]
- + Excellent typography rendering with clean, readable fonts
- + Sophisticated minimalism with organic white-space usage
- + High-quality, realistic food photography
- − Failed the request for a 'grid' of food photos
- − Missing the specific 'Pizza' section heading requested in the prompt
FLUX.2 [flex]
- + Perfect adherence to the 'grid' layout for food photos
- + Includes all requested sections (Appetizers, Pizza, Mains)
- + Bold use of color blocks for section identification
- − Text rendering is messy with many orthographic errors compared to Model A
- − Layout feels a bit cluttered for a 'minimalist' prompt
Verdict: FLUX.2 [flex] had much better prompt adherence by including the specific grid of photos and all three requested category headers, whereas FLUX.1 [dev] missed the pizza section and the grid. However, FLUX.1 [dev] produced a much more professional and realistic graphic design with superior text clarity and a cleaner minimalist aesthetic.
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
FLUX.1 [dev]
- + Excellent photorealistic rendering of food textures
- + Clean, balanced composition with a vertical 'exploded' view
- − Completely missed the 'MAGIC BURGER' title text
- − Failed to place the price in a starburst as requested
- − Background lacks the fiery intensity described in the prompt
FLUX.2 [flex]
- + Perfect adherence to all text requirements including 'MAGIC BURGER' and starburst price
- + Strong sense of motion with crumbs and dripping sauce
- + Excels at the 'fiery, glowing effect' for the background and typography
- − The 'exploded' effect is less uniform compared to model A
- − Slight over-saturation in the red and orange tones
Verdict: While FLUX.1 [dev] produced a very clean and realistic food image, it ignored several key text instructions. FLUX.2 [flex] successfully followed every detail of the prompt, including the specific title, secondary message, and the price inside a starburst, while capturing the requested fiery aesthetic and sense of motion.
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
FLUX.1 [dev]
- + Excellent text legibility and spelling accuracy throughout the board.
- + Strong adherence to the specific menu items and date requested.
- + Clean composition with consistent spacing.
- − The text looks more like a digital marker or vector font than realistic chalk.
- − The title 'TODAY SPECIALS' is missing the possessive 'S' requested in the prompt.
- − The 'handwriting' is too uniform, lacking the requested realistic chalk texture and natural variations.
FLUX.2 [flex]
- + Superb chalk texture with smudge marks and dusty residues that feel authentic.
- + Accurately rendered both the title text and the requested date with natural handwriting slants.
- + Perfectly captures the 'elegant cursive' style for the title as specified in the prompt.
- − Some text at the bottom is slightly less legible due to the chalk texture.
- − Slightly less centered horizontal alignment for the top few lines compared to Model A.
Verdict: FLUX.2 [flex] is the clear winner as it successfully captured the 'realistic chalk handwriting' and 'elegant cursive' requirements which FLUX.1 [dev] failed to execute, opting for a clean but digital-looking font instead. FLUX.2 [flex] also included authentic chalkboard details like eraser smudges and variable chalk pressure that significantly enhanced the visual quality.
The Reversed Rodeo
Text-to-Image“Horse riding astronaut in space — horse on top, not vice versa. Surreal, highly detailed, cinematic.”
AI Judge Analysis
FLUX.1 [dev]
- + Clean, cinematic lighting and high resolution
- + Smooth horse anatomy and realistic astronaut suit textures
- − Failed to follow the specific spatial instruction (horse is being ridden, not on top)
FLUX.2 [flex]
- + Excellent adherence to the complex spatial prompt with the horse on top of the astronaut
- + Highly surreal and creative interpretation of the concept
- + Detailed background elements including a galaxy and asteroids
- − The astronaut's hands and the horse's front legs have slight anatomical merging artifacts
Verdict: While FLUX.1 [dev] produced a safer, higher-quality image, it completely ignored the specific instruction to have the horse on top. FLUX.2 [flex] successfully interpreted the difficult surrealist request, creating a unique composition that perfectly matches the 'horse on top' prompt, making it the clear winner for adherence.
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
FLUX.1 [dev]
- + Excellent soft lighting and photorealistic rendering of the capybara's fur.
- + Accurate bored expression on the passenger looking at her phone.
- + High-quality blurred bokeh in the background lights.
- − The passenger is seated in the front passenger seat rather than the back seat.
- − The capybara's paws are not placed logically on the steering wheel.
- − The composition is missing the 'professional' driver uniform detail beyond the cap.
FLUX.2 [flex]
- + Correctly places the passenger in the back seat as requested.
- + Captures a more professional 'taxi driver' uniform and hat style.
- + Better perspective showing both the interior and the Manhattan street environment.
- − The hands/paws on the wheel look like a strange hybrid of human hands and animal fur.
- − The passenger's face is slightly less detailed and more generic than Model A.
- − The reflection/lighting on the car exterior is a bit busy and distracting.
Verdict: While FLUX.1 [dev] produced a more aesthetically pleasing image with better lighting and fur texture, it failed significantly on the spatial layout by placing the passenger in the front seat. FLUX.2 [flex] followed the prompt's structural requirements more accurately, placing the businesswoman in the back seat and providing a more convincing taxi driver ensemble for the capybara.
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
FLUX.1 [dev]
- + Excellent thorn border and vibrant jack-o-lantern lighting
- + Vibrant, high-contrast colors and cinematic feel
- + Strong illustrative style
- − Significant text errors including 'Falloween Ranty' and 'You Tre'
- − Formatting of date and time includes redundant characters and errors
- − Missing the webs mentioned in the prompt
FLUX.2 [flex]
- + Perfect text rendering for all requested details and banner text
- + Accurate representation of 'dark parchment' and gothic aesthetic
- + Excellent inclusion of all prompt elements like webs and skulls
- − The jack-o-lantern rendering is slightly more basic than Model A
- − Composition is a bit bottom-heavy with small text
Verdict: FLUX.2 [flex] is the clear winner as it successfully rendered all text elements accurately, including the complex banner and specific event details, while adhering to the 'parchment' aesthetic. FLUX.1 [dev] produced a visually striking image but failed significantly on text legibility and accuracy, creating garbled words and incorrect date formatting.
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
FLUX.1 [dev]
- + Excellent soft lighting and refined textures.
- + High visual appeal with a clean, centered 3D aesthetic.
- + High-quality rendering of the diorama base and background.
- − Text rendering is inaccurate and includes hallucinations.
- − The sushi variety is repetitive, using only one type of nigiri.
- − Included extra flowers not explicitly requested.
FLUX.2 [flex]
- + Perfect adherence to text instructions with no spelling errors.
- + Greater variety in sushi types including maki and different nigiri.
- + Very clean isometric composition and bold, clear graphics.
- − Lighting is slightly flatter compared to Image A.
- − The 'Japan' text is perhaps slightly too large relative to the diorama.
Verdict: While FLUX.1 [dev] produced a more artistically delicate image with superior lighting, it failed significantly on the text rendering. FLUX.2 [flex] followed every instruction perfectly, including perfect text and a more diverse range of sushi, while maintaining the requested 3D miniature style.
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
FLUX.1 [dev]
- + Cohesive, illustrative art style with consistent character design.
- + Strong warmth and saturated color palette.
- − Failed the 'hyper-photorealistic' part of the prompt by looking like a 3D animation/cartoon.
- − Missing the kitten entirely, substituting it with two puppies.
- − Creatures look more like toys or characters than real animals.
FLUX.2 [flex]
- + Excellent adherence to the 'hyper-photorealistic' requirement with realistic fur and textures.
- + Accurately includes all four requested animals: puppy, kitten, bunny, and fox kit.
- + Beautifully rendered lighting effects with god rays and dew sparkles.
- − The fox's front left leg has a slight anatomical clipping issue against its body.
- − The butterflies appear somewhat flat compared to the realism of the animals.
Verdict: FLUX.2 [flex] successfully captured all elements of the prompt, including the specific animals and the hyper-photorealistic style. In contrast, FLUX.1 [dev] produced a stylized cartoon image that failed to include the kitten. FLUX.2 [flex] is the clear winner for its superior realism and prompt adherence.
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
FLUX.1 [dev]
- + Excellent typography style that fits the 'vintage' and 'retro' keywords
- + Includes all requested elements including banner and steam
- + Good use of subtle paper texture in the background
- − Significant spelling errors in the main brand name ('Flarilaan') and bottom text ('Reseaurant')
- − Addition of random numbers (11011, 1941) that were not in the prompt
FLUX.2 [flex]
- + Perfect text rendering with zero spelling errors
- + Clean, minimalist vector aesthetic that adheres to the prompt
- + Well-balanced arching typography and banner placement
- − The line weight on the steam is a bit thin compared to the rest of the logo
- − Less detailed textures than Model A
Verdict: While FLUX.1 [dev] produced a more complex and atmospheric vintage design, it failed significantly on text accuracy by misspelling the primary brand name. FLUX.2 [flex] followed all instructions perfectly, providing a clean, professional, and correctly spelled logo that fully meets the minimalist vector brief.
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
FLUX.1 [dev]
- + Features a more complex, artistic layout for a single-page poster.
- + Includes a dedicated iconography bar at the bottom.
- + Accurately uses the requested NASA-inspired muted color palette.
- − The text is almost entirely illegible gibberish.
- − The scientific content is nonsensical, featuring planets that look like Saturn and Mars instead of the Earth-Moon trajectory.
- − The layout is cluttered and difficult to follow as an infographic.
FLUX.2 [flex]
- + Excellent text rendering with clear, legible titles and labels.
- + Follows the logical progression of the Apollo 11 mission steps accurately.
- + Clean, modern vector aesthetic that aligns perfectly with the 'flat-vector' request.
- − Missing the final step (Landing) in the visual sequence.
- − The layout is a bit simplistic, using a basic grid rather than a more creative infographic path.
Verdict: FLUX.2 [flex] is the clear winner because it produces legible, accurate text and follows the mission's logic, making it a functional infographic. FLUX.1 [dev] fails on the communicative purpose of an infographic by providing nonsensical text and incorrect celestial bodies, despite having a more complex artistic composition.
Explore each model
Black Forest Labs' precision image generation model with maximum control, reliable text rendering, and complete creative control supporting up to 4MP output