Fast distilled version of Black Forest Labs' FLUX.2 [dev] optimized for speed and cost efficiency.
Settled by community votes across 13 shared challenges, with an AI judge weighing in on each.
FLUX.2 [dev] Flash
#7 of 62 in Text-to-Image
FLUX1.1 [pro]
#50 of 62 in Text-to-Image
Where the votes landed
FLUX.2 [dev] Flash
0%
win rate
Ties
0%
FLUX1.1 [pro]
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.2 [dev] Flash
- + Excellent realism with convincing textures on the glass and wood
- + Accurate representation of shelf-like glass thickness and reflections
- + Natural photographic lighting and depth of field
- − The plant is slightly more to the side than directly 'behind' the cube center
FLUX1.1 [pro]
- + Perfectly centered composition following the prompt's spatial instructions
- + Vibrant colors and clean, sharp edges on the glass and sphere
- − The sphere is levitating without explanation, which looks less grounded/natural
- − The 'cube' is tall and rectangular rather than truly cubic
Verdict: FLUX.2 [dev] Flash produces a much more realistic image that feels like a real photograph, with the blue sphere resting naturally on the bottom of the cube. While FLUX1.1 [pro] follows the spatial layering well, it depicts a levitating sphere and a rectangular prism rather than a cube, making it less physically convincing than FLUX.2 [dev] Flash.
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.2 [dev] Flash
- + Excellent adherence to the 'repairing' aspect of the prompt with visible tools and focused posture.
- + Includes realistic motion blur from passing cars in the background.
- + Highly detailed and realistic mechanical components of the bicycle and skin textures.
- − The bike frame geometry is slightly warped near the pedal area.
FLUX1.1 [pro]
- + Strong cinematic aesthetic with beautiful bokeh and lighting.
- + Perfectly captures the 'heavy rain' atmosphere on the pavement.
- − Fails the 'repairing' prompt as the man is simply holding or leaning on the bike.
- − Severe anatomical and mechanical errors, including the man's feet merging with objects and a disconnected bike frame.
- − Lacks the requested motion blur on background vehicles.
Verdict: FLUX.2 [dev] Flash followed the instructions much more accurately, depicting a man actively engaged in a repair with tools and motion-blurred traffic. FLUX1.1 [pro] produced a more stylized, atmospheric image but failed significantly on the specific action of the prompt and contained major structural hallucinations in the man's legs and the bicycle 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.”
AI Judge Analysis
FLUX.2 [dev] Flash
- + Excellent adherence to the 'beads in braids' requirement with clear visibility.
- + Showcases ornate engraved armor and leather straps in high detail.
- + Centered, balanced composition that fits the 'close portrait' description well.
- − The 'faint scars' are rendered more like fresh bloody cuts.
- − The image has a slightly more artificial 'digital' sheen compared to Model B.
FLUX1.1 [pro]
- + Exceptional realism in the skin texture, sweat, and dirt.
- + Dynamic lighting and intense, lifelike eye detail that gives the character personality.
- + Highly cinematic shallow depth of field with natural-looking bokeh sparks.
- − The braids and beads are very subtle and partially cut off by the crop.
- − The engraving on the armor is less distinct than in Model A.
Verdict: FLUX.2 [dev] Flash followed the specific prompt details like beads and braided hair much more accurately, creating a clear and well-composed fantasy portrait. However, FLUX1.1 [pro] produced a far more lifelike and cinematic image with superior skin textures and lighting, even if it sacrificed some of the smaller decorative prompt requirements.
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.2 [dev] Flash
- + Stronger adherence to the 'grid' request for photos.
- + Clear, bold sans-serif headers as requested.
- + Good use of vibrant color accents through frames and headers.
- − Nonsensical pizza images under the 'Appetizers' heading.
- − Significant spelling errors in the main title and sub-sections.
- − The footer and logo areas contain garbled artifacts.
FLUX1.1 [pro]
- + Sophisticated composition with a lifestyle/presentation vibe.
- + Clean typography that feels more professional and modern.
- + More diverse food photography including pasta and side dishes.
- − Photos are placed at the bottom rather than an integrated grid.
- − Sections do not strictly follow the 'appetizers/pizza/mains' prompt (e.g., 'Man & Dreafry').
- − The grid of photos contains some repetitive or blurry elements.
Verdict: FLUX.2 [dev] Flash followed the structured 'grid' prompt more closely but failed on content logic by placing large pizzas under the 'Appetizers' heading and including distracting spelling errors. FLUX1.1 [pro] produced a much more professional and aesthetically pleasing layout that captures the 'modern minimalist' feel, even though the photo placement was less rigid than the prompt suggested. FLUX1.1 [pro] is the winner for its superior visual quality and design sensibility.
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.2 [dev] Flash
- + Perfectly executes the 'exploded' burger concept with clearly separated, suspended components.
- + Flawlessly integrates all requested text elements with the specified fiery, glowing effect.
- + Superior rendering of the starburst element for the price point as requested in the prompt.
- − The lighting on the lettuce and tomato is a bit flat compared to the dramatic background.
FLUX1.1 [pro]
- + High visual drama with intense fiery lighting and sharp focus on the central burger.
- + Clean, professional typography for the title and secondary message.
- − Fails the 'exploded' request as the main burger is fully assembled, with only secondary debris floating.
- − Misses the fiery starburst requirement for the price tag.
- − Includes redundant 'MAGIC BURGER' text and gibberish legal text at the bottom.
Verdict: FLUX.2 [dev] Flash is the clear winner as it followed every instruction, specifically the 'exploded' layout and the fiery starburst for the price tag. FLUX1.1 [pro] produced a high-quality food photograph but failed to separate the burger components as requested and included distracting redundant text.
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.2 [dev] Flash
- + Excellent text rendering with no spelling errors
- + Highly realistic chalk texture with convincing dust smudges
- + Consistent handwriting style that matches the prompt's request
- − The date is in a slightly different style than the cursive title
- − The framing is tight on the left and right edges
FLUX1.1 [pro]
- + Elegant cursive for the main title
- + Good atmospheric lighting in the background
- − Contains multiple spelling and logic errors like 'Chipkies' and '$228'
- − The text looks more like a digital font overlay than real chalk
- − Failed to correctly render the list of items by repeating 'Grilled Octopus'
Verdict: FLUX.2 [dev] Flash significantly outperformed FLUX1.1 [pro] in this challenge by delivering accurate text and a much more realistic chalk texture. While FLUX1.1 [pro] struggled with hallucinations, including price errors and typos like 'Chipkies', FLUX.2 [dev] Flash followed the recipe-style prompt perfectly with natural-looking handwriting.
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.2 [dev] Flash
- + Excellent anatomical rendering of the horse and astronaut
- + Clean, cinematic lighting with a realistic space backdrop
- + High level of detail in the textures of the space suit
- − Failed the specific negative constraint to have the horse on top of the astronaut
- − Standard interpretation of the prompt without surreal composition
FLUX1.1 [pro]
- + Dynamic pose with an interesting lighting and cloud composition
- + Detailed mane and tail textures
- + Vibrant colors and high visual impact
- − Failed the specific negative constraint to have the horse on top of the astronaut
- − Some minor artifacting where the astronaut joins the horse's back
Verdict: Both FLUX.2 [dev] Flash and FLUX1.1 [pro] failed to follow the specific surreal instruction for the horse to be on top of the astronaut, instead providing the standard astronaut-on-horse image. FLUX.2 [dev] Flash is the winner because its technical execution is cleaner, with more realistic proportions and a superior cinematic space background compared to the slightly messy lighting in FLUX1.1 [pro].
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.2 [dev] Flash
- + Excellent adherence to the 'both front paws on the steering wheel' requirement
- + Accurate framing from the front of the vehicle showing both characters clearly
- + High level of detail in the capybara's fur and the leather texture of the cap
- − The woman appears to be in the front passenger seat rather than the back seat
- − Minor distortion on the woman's right hand holding the phone
FLUX1.1 [pro]
- + Successfully places the passenger in the back seat as requested
- + Strong cinematic lighting and soft bokeh in the background
- + Good text rendering on the driver's cap
- − The capybara is not holding the steering wheel and appears to be sitting sideways
- − The seating arrangement is physically awkward, with the passenger facing the driver's back closely
Verdict: FLUX.2 [dev] Flash followed the anatomical and technical details of the prompt much better, specifically regarding the capybara's paws on the steering wheel. While FLUX1.1 [pro] correctly placed the passenger in the back seat, it failed to render the capybara actually driving the vehicle, resulting in a less coherent composition.
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.2 [dev] Flash
- + Perfectly follows the request for a square format image.
- + Excellent text rendering with no spelling errors and elegant gothic typography.
- + Superior composition that integrates the border, thorns, and webs into the frame naturally.
- − Includes a small line of garbled text ('Hurk: O3696') between the date and time.
- − Overall color palette is slightly muted compared to the vibrant jack-o-lantern.
FLUX1.1 [pro]
- + Vibrant, cinematic lighting on the jack-o-lantern and moon.
- + Successfully incorporates all requested elements including the full moon.
- − Failed the square format requirement, providing a portrait-oriented poster on a grey background.
- − Significant text errors including 'You inivted to a n night of frights' and unnecessary repetition of 'Party', 'Time', and 'Location'.
- − Missing the requested spider webs in the thorny border.
Verdict: FLUX.2 [dev] Flash is the clear winner as it strictly adheres to the square format requirement and renders the complex typography with much higher accuracy. While FLUX1.1 [pro] has more vibrant lighting, it struggles significantly with spelling and duplicates several lines of information, whereas FLUX.2 provides a cohesive and polished layout.
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.2 [dev] Flash
- + Excellent typography rendering with the requested flag icon.
- + Beautiful lighting and high-quality PBR textures that feel premium.
- + Clean isometric composition with a clear diorama base.
- − The sushi variety is limited to basically two types.
FLUX1.1 [pro]
- + Features a wider variety of sushi styles on the diorama platter.
- + Achieves a very soft and appealing 'cartoon' miniature aesthetic.
- + Good adherence to the requested isometric perspective.
- − Failed to include the requested flag icon.
- − Text rendering for 'SUSHI' is much smaller and less impactful than requested.
- − Materials look more plastic-like rather than the requested 'realistic PBR'.
Verdict: FLUX.2 [dev] Flash followed the text and icon requirements perfectly, producing a professional graphic design feel with high-quality material rendering. While FLUX1.1 [pro] provided a more diverse plate of sushi, its failure to include the flag icon and the weaker typography styling makes FLUX.2 [dev] Flash the more accurate result for this specific prompt.
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.2 [dev] Flash
- + Successfully included all four requested animal types.
- + Excellent adherence to technical details like dew sparkles and god rays.
- + High level of fur detail and clear, expressive eyes for every animal.
- − The animals are posed in a static group rather than actively 'tumbling' as requested.
- − Duplicate animals are present (two bunnies, two fox kits).
FLUX1.1 [pro]
- + Captures a more dynamic sense of wonder and movement.
- + Beautifully soft, backlit fur textures that create a glowing aesthetic.
- + Composition feels less cluttered and more balanced.
- − Failed to include the red fox kit from the prompt.
- − The kitten's anatomy, specifically the front paws, looks slightly merged or unnatural.
- − Missed the specific requested butterfly type, showing smaller yellow specs instead of detailed monarchs.
Verdict: FLUX.2 [dev] Flash followed the complex prompt more literally by including all the requested animal species, though it added duplicates to fill the frame. FLUX1.1 [pro] produced a more artistically pleasing image with superior lighting, but failed the prompt adherence by omitting the fox kit and the specific 'dew sparkles' detail. FLUX.2 [dev] Flash is the winner for its better mapping of the multi-subject prompt.
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.2 [dev] Flash
- + Excellent typography with perfect spelling of the brand name and the grave accent.
- + Clean vector emblem style that adheres strictly to the minimalist prompt.
- + Balanced composition with high-quality texture on the background.
- − The steam is a bit thick and stylized compared to the rest of the logo.
FLUX1.1 [pro]
- + Intricate woodcut-style engraving on the cloche dome.
- + Beautiful ornamental border and decorative flourishes.
- − Failed the spelling of the brand name, writing 'Cafeé FRATILIAN' instead of 'Caffè Florian'.
- − The typography is cluttered with unnecessary lines and extra characters.
Verdict: FLUX.2 [dev] Flash followed the text requirements perfectly, producing a professional and clean logo that is ready for use. FLUX1.1 [pro] produced a more ornate and artistically detailed illustration, but it failed significantly on the text rendering, misspelling the primary brand name.
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.2 [dev] Flash
- + Excellent typography and label legibility.
- + Accurate representation of the requested steps with highly detailed illustrative icons.
- + Strong adherence to the requested NASA-inspired color palette and flat-vector style.
- − The layout is a bit cluttered with redundant labels for the same stage.
- − Text artifacts in the 'Launch' and 'Moon' labels.
FLUX1.1 [pro]
- + Clean, minimalist composition that feels very modern.
- + Consistent iconography style used throughout the side menu.
- − Failed significantly on text rendering, with most labels being illegible or nonsensical.
- − The main rocket graphic is a generic cartoon style rather than the requested Saturn V.
- − Doesn't clearly illustrate the specific sequence of the mission requested in the prompt.
Verdict: FLUX.2 [dev] Flash is the clear winner as it successfully recreates the specific infographic stages requested with impressive detail and mostly legible text. FLUX1.1 [pro] produced a visually pleasing layout, but it failed to follow the specific content requirements and the text is entirely gibberish.
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