Black Forest Labs' state-of-the-art image generation model with maximum quality and speed, supporting text-to-image and multi-reference image editing with up to 4MP output
Settled by community votes across 13 shared challenges, with an AI judge weighing in on each.
FLUX.2 [pro]
#8 of 62 in Text-to-Image
FLUX1.1 [pro]
#50 of 62 in Text-to-Image
Where the votes landed
FLUX.2 [pro]
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 [pro]
- + Excellent photographic realism and depth of field
- + Accurate representation of a red hardcover book with spine details
- + Natural lighting and shadows on the wooden table surface
- − The glass cube has an open side rather than being a solid enclosure
FLUX1.1 [pro]
- + Strong colors and clear visibility of the plant through the glass
- + Perfect sphere geometry with realistic window reflections
- + The sphere appears centered within the volume of the cube
- − The glass cube is rectangular/tall rather than a standard cube shape
- − The red book appears more like a thin fabric-covered slab without traditional book proportions
Verdict: FLUX.2 [pro] followed the prompt more naturally, creating a realistic scene with a believable book and a true cube shape, even though the cube had an open front. FLUX1.1 [pro] produced a more vibrant image but failed on the geometry of the objects, rendering a rectangular prism instead of a cube and a simplified representation of a book.
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 [pro]
- + Excellent depiction of a bicycle repair task with logical interaction
- + Highly realistic skin texture and fabric detail
- + Beautifully rendered reflections and water ripples that enhance the mood
- − The motion blur of the car is subtle compared to the sharp background buildings
FLUX1.1 [pro]
- + Strong bokeh effect in the background lights creates a cinematic feel
- + Effective wet pavement texture and reflections
- − Physical incoherence as the bicycle is missing its rear half
- − The man is simply holding the handlebars rather than repairing it
- − Anatomical issues with the man's hands merging into the bike
Verdict: FLUX.2 [pro] is the clear winner as it depicts a logical, realistic scene of a man actually repairing a bicycle. In contrast, FLUX1.1 [pro] fails on basic anatomy and object coherence, producing a bike that is missing its frame and wheels at the back while the man's hands appear fused to the grips.
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 [pro]
- + Excellent adherence to the 'beads in hair' prompt element.
- + Clear and intricate floral engravings on the armor plate.
- + Warm, atmospheric lighting that clearly originates from the visible torch.
- − The scars look a bit like surface-level scratches rather than deep battle wounds.
- − Leather strap texture is slightly softer compared to the armor.
FLUX1.1 [pro]
- + Extremely lifelike eyes with impressive iris detail.
- + Superior skin texture showing pores, sweat, and grit.
- + Striking use of shallow depth of field and bokeh sparks.
- − Failed to include the small beads in the braided hair as requested.
- − The armor engravings are less distinct and partially obscured.
- − Warm torchlight is less evident, with a cooler overall color temperature.
Verdict: FLUX.2 [pro] adhered much better to the specific prompt instructions, particularly regarding the hair beads and the intricate floral engravings on the armor. While FLUX1.1 [pro] produced a more photorealistic face with incredible eye detail, it missed several key decorative elements and favored a moodier, cooler lighting scheme over the requested warm torchlight.
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 [pro]
- + Very clean and professional grid layout with high-quality headers
- + Excellent font choice that aligns perfectly with the 'bold sans-serif' and 'modern' prompt
- + Good color coordination with vibrant category-specific accents
- − Text duplication issues where 'Garlic Bread' and 'Margherita Pizza' are repeated under every section
- − One photo of steak is mislabeled as 'MageFiza Pizza'
FLUX1.1 [pro]
- + Stylishly presented as a physical mockup with realistic depth/shadows
- + Successfully incorporates 'Appetizers', 'Pizza', and 'Mains' (misspelled as Man & Dreafry)
- − Text legibility is poor with significantly garbled characters
- − Food images are clustered at the bottom rather than integrated into a cohesive grid for the whole menu
- − Layout feels a bit cluttered compared to the minimalist request
Verdict: FLUX.2 [pro] followed the design brief much more effectively, producing a clean, professional menu with a distinct grid and bold headers. While FLUX1.1 [pro] attempted a nice lifestyle mockup, the actual design layout was less minimalist and the text rendering was significantly lower in quality.
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 [pro]
- + Excellent adherence to the 'exploded burger' request with clear separation of ingredients.
- + Perfect text rendering for all three requested elements with the specified fiery glow.
- + High-quality photorealistic textures on the lettuce, meat, and melting cheese.
FLUX1.1 [pro]
- + Dynamic sense of depth with particles flying toward the camera.
- + Bright, high-contrast lighting on the burger bun and embers.
- − Failed the 'exploded burger' requirement; the burger is mostly assembled rather than suspended in mid-air.
- − Repeated the 'MAGIC BURGER' text twice and missed the starburst requirement.
- − Included illegible hallucinated text at the bottom of the image.
Verdict: FLUX.2 [pro] followed every detail of the prompt, including the exploded layout of the burger and the specific placement of the fiery text and starburst. FLUX1.1 [pro] failed to deconstruct the burger as requested and missed several text-formatting instructions, resulting in a more cluttered and less accurate advertisement.
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 [pro]
- + Excellent chalk texture with realistic smudging and dusting on the slate surface.
- + High text accuracy that perfectly follows the prompt's content and style requirements.
- + Natural letter variations and alignment that truly mimic human handwriting.
- − The slate board texture makes the edges look a bit more like stone than a standard café chalkboard.
- − The '2026' is slightly less cursive than the main title line.
FLUX1.1 [pro]
- + Clean, readable layout with attractive decorative dividers.
- + Good atmospheric lighting in the background café setting.
- − Significant text errors including 'Herbss', 'Chipkies', 'giluten', and price inaccuracies like '$228'.
- − The text looks more like a digital font overlay rather than organic chalk handwriting on a board.
- − Repeated lines for the octopus dish which was not requested.
Verdict: FLUX.2 [pro] is the clear winner as it followed the complex text instructions perfectly, maintaining correct spelling, prices, and a realistic chalk texture. FLUX1.1 [pro] failed on almost every specific detail of the text, introducing numerous typos, hallucinations, and a digital-looking font that lacked the requested chalk variations.
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 [pro]
- + Successfully followed the difficult logic of 'horse on top' of the astronaut.
- + High cinematic quality with beautiful lighting on the Earth and galaxies.
- + Clean, sharp details on the spacesuit and horse's mane.
- − The transition area where the horse is 'riding' the astronaut is a bit physically confusing/cluttered.
- − Includes a second partial horse body merged with the astronaut.
FLUX1.1 [pro]
- + Dramatic, painterly aesthetic with vibrant color contrast.
- + Excellent anatomical rendering of the horse and lighting on the helmet.
- − Failed the primary logic constraint of 'horse on top, not vice versa'.
- − Atmosphere looks more like a cloudy sky on Earth than actual deep space.
Verdict: FLUX.2 [pro] is the clear winner because it successfully interpreted the 'horse on top' surreal prompt, whereas FLUX1.1 [pro] defaulted to a standard astronaut riding a horse. FLUX.2 [pro] also felt more like a space setting with the visible planet and galaxies, despite some minor anatomical clipping between the horse and the astronaut.
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 [pro]
- + Excellent photorealism with detailed textures on the capybara fur and jacket.
- + Highly accurate composition showing the driver and passenger in their correct respective seat positions.
- + Highly realistic dashboard and interior lighting that matches a New York taxi.
- − The anthropomorphic hands on the steering wheel are slightly uncanny compared to natural capybara paws.
FLUX1.1 [pro]
- + Atmospheric bokeh lighting in the background creates a nice city-at-night feel.
- + Good character design for the capybara and the passenger.
- − The composition is incorrect, placing the driver and passenger side-by-side in the front seat.
- − The capybara is not holding the steering wheel as requested; only one arm is visible and gestured toward the passenger.
- − The perspective makes the car interior feel cramped and less like a standard taxi.
Verdict: FLUX.2 [pro] followed the prompt's spatial instructions much better, correctly placing the businesswoman in the back seat and the capybara at the wheel. FLUX1.1 [pro] failed to maintain the taxi's seating arrangement, placing both characters in the front, and failed to depict the paws on the steering wheel. FLUX.2 [pro] also offers a higher level of realism in the textures and interior details.
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 [pro]
- + Excellent typography with perfect spelling and high legibility.
- + Sophisticated parchment border with integrated webs and thorns.
- + Polished cinematic lighting and atmospheric composition.
FLUX1.1 [pro]
- + Atmospheric twisted trees and moon placement.
- + Vibrant color palette with glowing Jack-o-lantern.
- − Significant text errors including redundant 'Party Party' and spelling mistakes like 'inivited'.
- − Repeated event information at the bottom of the poster.
- − Failed to provide a square format as requested, providing a vertical flyer instead.
Verdict: FLUX.2 [pro] is the clear winner as it followed every instruction, including the square format and specific text strings, with zero spelling errors. FLUX1.1 [pro] failed to maintain the requested aspect ratio and suffered from severe text hallucinations and redundancies.
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 [pro]
- + Excellent typography rendering with the requested hierarchy and a small flag icon.
- + Strong adherence to the 'diorama base' and '45° isometric' camera angle instructions.
- + Clean, high-quality shading that mimics 3D PBR materials well.
- − The sushi rice texture is a bit large-grained, appearing more like individual beads than realistic rice.
FLUX1.1 [pro]
- + Beautiful soft lighting and color palette that feels very 'miniature cartoon'.
- + High variety in the sushi types which makes for a more interesting scene.
- + Text is perfectly centered and legible.
- − Missed the request for a flag icon.
- − The 'SUSHI' text is very small compared to the large bold request.
- − Includes extra elements like tomatoes and unknown jars that weren't requested.
Verdict: FLUX.2 [pro] followed all instructions including the specific text layout and the addition of the flag icon, while maintaining a clear isometric perspective. FLUX1.1 [pro] created a more aesthetically pleasing, soft-focus image but missed technical details of the prompt such as the flag and the specific text sizing.
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 [pro]
- + Successfully includes all four requested animals (dog, cat, rabbit, fox).
- + Excellent fur texture and realistic environmental lighting.
- + Sophisticated composition with interaction between all subjects.
- − The fox's front leg anatomy looks slightly elongated/flattened.
FLUX1.1 [pro]
- + Beautiful backlighting and bokeh effect.
- + Captured the 'puppy dog eyes' expression very effectively.
- + Lively and colorful palette.
- − Failed to include all requested animals, missing the red fox kit completely.
- − Anatomy of the kitten's paws is strange and merged.
- − The butterflies appear as glowing yellow shapes rather than realistic insects.
Verdict: FLUX.2 [pro] is the clear winner as it adhered to the complex prompt by including all four distinct animals, whereas FLUX1.1 [pro] missed the fox entirely. FLUX.2 [pro] also features much higher anatomical accuracy and more realistic butterfly details compared to the stylized, glowing elements in the second image.
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 [pro]
- + Perfect text rendering for both the brand name and the 'Est. 1720' banner
- + Clean vector emblem style that adheres strictly to the minimalist prompt
- + Accurate representation of a cloche dome with stylized steam
- − The circle frame is slightly interrupted by the text, though this is a common design choice
FLUX1.1 [pro]
- + Elegant vintage aesthetic with detailed woodcut-style shading
- + Good preservation of the warm brown and cream color scheme
- + High artistic quality for a logo concept
- − Major spelling errors, rendering 'Fratilian' instead of 'Florian'
- − The design is quite ornate and busy, clashing with the 'minimalist' requirement in the prompt
- − The 'Est. 1720' is just text and not on a banner as requested
Verdict: FLUX.2 [pro] is the clear winner as it followed every instruction, including specific text spelling, the banner placement, and the minimalist vector style. FLUX1.1 [pro] produced a visually striking image but failed significantly on the text rendering (spelling it 'FRATILIAN') and ignored the 'minimalist' and 'banner' constraints.
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 [pro]
- + Excellent typography and readability for main headings.
- + Clean, professional flat-vector aesthetic that matches the 'modern infographic' request.
- + Logical vertical flow that follows the requested mission steps sequentially.
- − The rocket used is a generic space shuttle style rather than the requested Saturn V.
- − Body text under headings is illegible gibberish.
FLUX1.1 [pro]
- + Strong heading text with 'APOLLO 11'.
- + Creative use of a central moon graphic as the focal point.
- + Good adherence to the requested color palette.
- − Confusing layout with non-sequential numbering (1, 1, 2, 3, 5, 4).
- − Iconography is somewhat messy and inconsistent compared to Model A.
- − Fails to clearly represent the specific mission steps requested in a coherent way.
Verdict: FLUX.2 [pro] followed the infographic structure much more effectively, providing a clear vertical sequence of the mission steps with professional-grade vector styling and readable main headers. While FLUX1.1 [pro] had a strong main title, its layout was disorganized, with numbering errors and cluttered icons that failed to communicate the specific requested stages of the mission.
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