Black Forest Labs' open-weights image generation model with frontier performance, available for non-commercial local deployment
Settled by community votes across 13 shared challenges, with an AI judge weighing in on each.
FLUX.2 [dev]
#19 of 62 in Text-to-Image
FLUX1.1 [pro]
#50 of 62 in Text-to-Image
Where the votes landed
FLUX.2 [dev]
100.0%
win rate
Ties
0.0%
FLUX1.1 [pro]
0.0%
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]
- + Excellent adherence to the 'small' sphere requirement
- + Realistic physics and grounding on the table surface
- + Subtle and professional lighting that matches the window source
- − The glass box appears more like an open container than a sealed cube
FLUX1.1 [pro]
- + High clarity on the glass edges and reflections
- + Vibrant colors and high-resolution textures on the book.
- − The sphere is disproportionately large compared to the prompt
- − The sphere appears to be levitating unnaturally
- − The cube dimensions are more rectangular than cuboid
Verdict: FLUX.2 [dev] followed the prompt much more accurately, particularly regarding the size of the sphere and the sense of it being 'small'. FLUX1.1 [pro] produced a more striking image with sharper details, but failed on the scale of the interior object and presented an unrealistic levitation effect.
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]
- + Excellent skin texture and facial details
- + Accurate depiction of motion blur from passing cars
- + Perfect interpretation of the 'repairing' action with focus on the hands
- − The structural integrity of the bicycle frame is slightly confusing near the handlebars
FLUX1.1 [pro]
- + Beautiful cinematic lighting and reflections on the pavement
- + Strong sense of atmosphere and environment
- − The bicycle is severely distorted and missing a rear half
- − The man is simply holding the bike rather than repairing it
- − Failed to incorporate the requested motion blur from passing cars
Verdict: FLUX.2 [dev] followed the technical requirements of the prompt much more effectively, specifically the 'repairing' action and the 'motion blur' from traffic. While FLUX1.1 [pro] created a moody atmosphere, the bike was physically nonsensical and it missed key mechanical prompt instructions.
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]
- + Excellent adherence to the full costume prompt, showing the ornate engraving, leather straps, and armor details clearly.
- + Accurately includes the small beads in the hair braids as requested.
- + Effective lighting composition with the torch visible and its light reflecting realistically off the metal.
- − The facial scars look a bit like surface paint rather than deep, lifelike skin texture.
- − The overall image has a slightly softer, more 'rendered' look compared to the cinematic grit of Model B.
FLUX1.1 [pro]
- + Stunning realistic skin texture and incredibly lifelike eyes with intricate iris details.
- + Very high visual quality on the fine hair strands and dirt/sweat on the face.
- + Stronger sense of 'battle-worn' through intense facial expression and more natural-looking grime.
- − Fails to include the 'small beads' in the hair as specified in the prompt.
- − The armor details are mostly cropped out or blurred, reducing the visibility of the 'ornate engraved plate' and 'leather straps' requested.
- − The 'close portrait' instruction was taken to an extreme, sacrificing context for facial detail.
Verdict: FLUX.2 [dev] followed the technical requirements of the prompt much better, providing a full view of the ornate armor, leather straps, and hair beads that were requested. While FLUX1.1 [pro] produced a far more lifelike and intense facial portrait with superior skin texture, it missed several specific descriptors such as the beads and the detailed costume layers. FLUX.2 [dev] is the preferred choice for accurately realizing the entire scene described.
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]
- + Excellent professional layout that looks like a high-quality two-page menu.
- + Strong color coordination with vibrant accents that match the prompt's aesthetic.
- + High-resolution food photos that integrate well with the text sections.
- − Text is mostly gibberish despite having a professional structure.
- − The 'PIZZAU' and 'PIZZA' headers are redundant and inconsistent.
FLUX1.1 [pro]
- + Creative presentation showing the menu alongside cutlery for context.
- + Good variety in the photo grid with multiple food types shown.
- + Better adherence to the 'Appetizers' heading placement at the top.
- − The tall, narrow aspect ratio makes the text nearly unreadable and cramped.
- − Layout feels more like a flyer than a standard restaurant menu.
- − Significant artifacts in the cutlery and small icons.
Verdict: FLUX.2 [dev] is the clear winner for its superior layout and professional design, effectively capturing the 'modern minimalist' aesthetic requested. While both models struggled with legible text, FLUX.2 [dev] produced high-quality food photography and a clean grid structure, whereas FLUX1.1 [pro] produced a cramped, less practical design with noticeable visual artifacts.
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]
- + Excellent adherence to the 'exploded burger' request with clear separation of ingredients.
- + Perfectly executed text effects with the requested fiery, glowing style.
- + Superior layout and design as a cohesive advertisement.
FLUX1.1 [pro]
- + High level of photorealistic detail in the burger textures.
- + Good use of motion blur on floating elements around the burger.
- + Clean background with atmospheric depth.
- − Failed to provide an 'exploded' burger, showing a stacked burger instead.
- − Ignored several text instructions, including the starburst and the fiery glowing effect on the font.
- − Redundant text 'MAGIC BURGER' appears twice with different styles.
Verdict: FLUX.2 [dev] significantly outperformed the competition by strictly adhering to the spatial and stylistic requirements of the prompt, including the exploded burger layout and the specific fiery text effects. FLUX1.1 [pro] produced a high-quality image but failed on the core request for an exploded view and missed several typographic details like the starburst.
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]
- + Excellent chalk texture with realistic smudges and variations in pressure.
- + Text rendering is near-perfect and follows all complex prompt instructions including specific items and prices.
- + Composition feels very natural to a real café setting with a frameless smudge-prone board.
- − The text at the very bottom has a slight alignment curve that looks a bit digital.
- − Minor smudging artifact behind the word 'with' on the second item.
FLUX1.1 [pro]
- + Clean, elegant cursive title that matches the requested 'elegant' aesthetic well.
- + Strong bokeh effect in the background enhances the 'cozy café' atmosphere.
- − Severe hallucinations in the text, creating extra lines and incorrect prices like '$228'.
- − Spelling errors such as 'Herbss' and 'Chipkies'.
- − The handwriting looks more like a digital font script than physical chalk on a board.
Verdict: FLUX.2 [dev] significantly outperformed FLUX1.1 [pro] in this challenge by accurately rendering all requested text and prices with a realistic chalk texture. FLUX1.1 [pro] failed to maintain the menu structure, introducing multiple spelling errors and nonsensical pricing, while the handwriting itself lacked the authentic chalk-on-blackboard grit seen in FLUX.2 [dev].
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]
- + Excellent photorealistic lighting and textures
- + Clear, cinematic composition with a sharp background
- + Naturalistic horse anatomy and fur detail
- − Completely failed the negative constraint/instruction for the horse to be on top
- − Common, cliché interpretation of the prompt
FLUX1.1 [pro]
- + Dynamic, artistic lighting with a more surreal atmosphere
- + Strong sense of motion and scale
- + Complex background with multiple planets and atmospheric clouds
- − Failed the specific instruction for the horse to be on top of the astronaut
- − Anatomical issues with the horse's neck and chest area
- − Visible AI artifacting/distortion on the horse's body and face
Verdict: Both models failed the specific spatial logic challenge of placing the horse on top of the astronaut, instead defaulting to the common trope of an astronaut riding a horse. FLUX.2 [dev] is preferred because it delivers a much higher level of photorealistic detail and anatomical accuracy compared to the distorted textures and warped anatomy found 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]
- + Excellent adherence to the 'paws on steering wheel' instruction
- + Realistic textures on the capybara's fur and the taxi hat
- + The passenger is correctly placed in the back seat as requested
- − The capybara's hands look slightly more primate-like than typical capybara paws
- − The viewpoint is from outside looking in, rather than a scene 'inside' the taxi
FLUX1.1 [pro]
- + Beautiful cinematic bokeh lighting on the background city streets
- + Higher aesthetic quality and sharp detail on the capybara's face
- − The passenger is sitting in the front passenger seat instead of the back seat
- − The capybara's paws are not on the steering wheel as requested
- − The woman's positioning is cramped and physically awkward within the car interior
Verdict: FLUX.2 [dev] followed the complex spatial instructions much better, correctly placing the businesswoman in the back seat and the capybara's paws on the wheel. While FLUX1.1 [pro] has superior lighting and aesthetic appeal, it failed multiple prompt requirements by moving the passenger to the front and ignoring the steering wheel placement.
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]
- + Excellent text rendering with perfect spelling and no repetition.
- + Unified composition that fits the square format perfectly.
- + Great interpretation of the 'parchment' and 'thorn' border elements.
FLUX1.1 [pro]
- + Beautiful cinematic lighting with a glowing moon and higher contrast.
- + Intricate, delicate line work in the thorny border.
- − Significant text errors, including repeating the date, time, and location twice.
- − Small banner text is misspelled ('You inivted to a n night of frights').
- − Failed to provide a square format, instead opting for a vertical poster layout.
Verdict: FLUX.2 [dev] followed every instruction perfectly, including the specific text strings and the square aspect ratio. In contrast, FLUX1.1 [pro] struggled with text coherence, repeating entire lines of information and misspelling words, and ignored the requested square format.
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]
- + Perfectly adheres to the text elements including the Japan flag icon.
- + Excellent realistic PBR materials, especially on the fish textures and rice grains.
- + Properly follows the 'diorama base' and 'plate' instructions.
- − The drop shadow on the text feels a bit basic compared to the 3D scene.
FLUX1.1 [pro]
- + Lovely stylized 3D cartoon aesthetic with soft lighting.
- + Dynamic variety of sushi pieces.
- + Great use of soft, rounded typography that matches the art style.
- − Completely missed the requested flag icon.
- − The 'SUSHI' text is very small and lacks the requested prominence.
- − Ingredients like the tomatoes and certain sushi toppings look less like sushi and more like generic clay models.
Verdict: FLUX.2 [dev] is the winner as it followed every specific detail of the prompt, including the flag icon and the hierarchy of the text. While FLUX1.1 [pro] has a very appealing 'cartoon' style, it failed to include the requested flag and did not follow the instruction for a specific plate and minimal garnish as accurately as FLUX.2 [dev].
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]
- + Followed the prompt accurately by including all four specified animals: puppy, kitten, bunny, and fox.
- + Excellent realism in fur textures and anatomy for all animals.
- + Captures a wide range of flower colors and crisp butterfly details.
- − The animals are sitting relatively still rather than actively 'tumbling' as requested.
- − Included two rabbits instead of a fox and a rabbit separately, though a fox is present elsewhere.
FLUX1.1 [pro]
- + Features high-energy, expressive facial expressions that match the 'joyful' vibe.
- + Effective use of backlighting and glowing butterflies to create a magical atmosphere.
- − Failed to include the red fox kit entirely.
- − The animals' anatomy is slightly more stylized/cutesy, leaning away from the 'hyper-photorealistic' request.
- − The background is more blurred, losing the 'lush wildflower meadow' detail.
Verdict: FLUX.2 [dev] is the clear winner because it successfully included all four requested animal species (puppy, kitten, bunny, and fox) whereas FLUX1.1 [pro] missed the fox entirely. FLUX.2 [dev] also achieved a higher level of photorealistic detail in the fur and environment, adhering more closely to the 8K masterpiece requirement.
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]
- + Perfect text rendering for both terms and the establishment date
- + Strong alignment with the minimalist and vector emblem style
- + Excellent use of the warm brown and cream color palette
- − The steam icon is a bit generic and simplistic
FLUX1.1 [pro]
- + More intricate and atmospheric vintage texture and border
- + The cloche has more sophisticated shading and detail
- − Failed the primary text task by misspelling 'Florian' as 'FRATILIAN'
- − The 'Café' text has an unusual font choice that makes the 'f' and 'e' look slightly garbled
Verdict: FLUX.2 [dev] followed all instructions perfectly, including the exact spelling of the brand name and the specific 'minimalist' and 'vector' style requested. FLUX1.1 [pro] produced a more ornate and visually complex illustration, but failed significantly on the text accuracy, misspelling 'Florian'. FLUX.2 [dev] is the clear winner for its functional design and adherence to the prompt specifications.
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]
- + Stronger adherence to the flat-vector infographic style with clean, illustrative icons.
- + Correctly organized the sequential steps of the mission in a logical grid.
- + Handled the NASA-inspired color palette effectively with crisp white text.
- − Included redundant or hallucinated steps that don't match the numbering system.
- − The text labeling for specific icons contains several spelling errors (e.g., 'Trarquility', 'Ualsist Ordit').
FLUX1.1 [pro]
- + Excellent visual hierarchy with a central focal element.
- + Good use of the light gray and navy color palette for a modern feel.
- − Failed to provide a clear sequence of icons for the specific steps requested.
- − The iconography is inconsistent and the small-scale text is mostly illegible gibberish.
- − The layout feels more like a general graphic than a functional infographic.
Verdict: FLUX.2 [dev] followed the prompt's structural and stylistic requirements much more closely, providing specific icons for 'Launch', 'Earth Orbit', and the 'Lunar Module' as requested. While FLUX1.1 [pro] created an aesthetically pleasing center-weighted graphic, it failed to deliver the sequential step-by-step infographic format and its textual content is much less coherent. FLUX.2 [dev] is the winner for better instruction following and clarity of iconography.
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