Black Forest Labs' aesthetically-tuned 12-billion parameter flow transformer optimized for high-quality images with incredible aesthetics, suitable for personal and commercial use
Settled by community votes across 13 shared challenges, with an AI judge weighing in on each.
FLUX.1 Krea [dev]
#47 of 62 in Text-to-Image
FLUX.2 [flex]
#14 of 62 in Text-to-Image
Where the votes landed
FLUX.1 Krea [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 Krea [dev]
- + Excellent photographic realism with natural lens blur and lighting.
- + Convincing glass material with realistic reflections and depth.
- + Accurately places the plant behind the cube, visible through the glass.
- − The shadow/reflection of the sphere inside the cube looks slightly confusingly merged with the back face.
FLUX.2 [flex]
- + Perfect adherence to all spatial instructions in the prompt.
- + Clean, minimalist composition with clear separation of objects.
- + Correct lighting direction from the left as requested.
- − The glass refractive properties are less convincing than the other model.
- − The overall image looks slightly more like a 3D render than a real photograph.
Verdict: Both models followed the prompt perfectly, placing all elements in the correct positions. FLUX.1 Krea [dev] is the winner due to its superior photographic quality and more sophisticated handling of light and glass textures, whereas FLUX.2 [flex] has a slightly flatter, more artificial appearance.
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 Krea [dev]
- + Excellent depiction of light rain and soft pavement reflections
- + Captures a very natural, unposed 'candid' feel with slightly off-center framing
- + Great realism in the background traffic and wet asphalt texture
- − The man is standing and holding the bike rather than actively repairing it
- − The bicycle's anatomy is slightly distorted near the frame and pedals
FLUX.2 [flex]
- + Perfectly adheres to the action of 'repairing' by having the man crouched over the chain
- + Excellent shallow depth of field with beautiful bokeh in the background
- + Stronger motion blur on passing vehicles as requested
- − The framing feels more 'staged' for a professional photo than a 'candid street photo'
- − Minor structural issues with the bicycle tire and pedal connection
Verdict: FLUX.2 [flex] is the winner because it accurately depicts the primary action of the man repairing the bike, whereas FLUX.1 Krea [dev] shows him simply standing with it. While FLUX.1 Krea [dev] captured a more convincing 'candid' street photography vibe, FLUX.2 [flex] followed more of the technical prompt cues like motion blur and shallow depth of field.
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 Krea [dev]
- + Excellent moody lighting with strong contrast
- + High-quality intricate engravings on the pauldrons
- + Subtle and realistic dirt/blood spatters on the face
- − The sparks look more like static circles than dynamic embers
- − The beads in the hair are very uniform and less detailed
FLUX.2 [flex]
- + Perfectly captures the request for multiple braids with beads
- + Realistic skin texture with visible scars and pores
- + Fantastic texture on the leather straps and knit cloth underlayer
- − The lighting is a bit flat compared to the dramatic shadows of Image A
- − The torch in the background is slightly distracting
Verdict: FLUX.2 [flex] adhered better to the technical details of the prompt, particularly the leather textures, knit underlayer, and the specific request for braids/beads. While FLUX.1 Krea [dev] offered a more cinematic and moody lighting setup, FLUX.2 [flex] produced a more lifelike character portrait with better surface detail.
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 Krea [dev]
- + Excellent photo-grid alignment
- + Clean and highly professional typography hierarchy
- + Captures a sophisticated casual dining aesthetic
- − Includes a duplicate section header for 'Appetizers'
- − Text becomes illegible and contains gibberish characters in the item descriptions
FLUX.2 [flex]
- + Clean integration of color blocks for section headers
- + Good variety of high-quality food photography
- + Legible price formatting and reasonable font choices
- − The main header incorrectly says 'APPETIZERS' instead of 'MENU'
- − The layout is slightly cluttered with overlapping elements in the photo grid
Verdict: FLUX.1 Krea (dev) produces a more cohesive and professional layout that feels like a real restaurant menu, though it struggles with text accuracy and repeats a category. FLUX.2 (flex) has better handled color accents and individual product images, but fails on the primary header and creates a slightly less 'minimalist' feel. FLUX.1 Krea (dev) is the winner for its superior composition and professional design polish.
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 Krea [dev]
- + Crisp and clear text rendering for the main titles.
- + Good photographic texture on the burger bun and lettuce.
- + Effective use of the 'fiery background' with actual coals at the bottom.
- − Failed to place the price in a starburst as requested.
- − The burger layers are not very 'exploded'; the patty and cheese are touching.
- − Contains garbled small text at the bottom and a placeholder icon in the top left.
FLUX.2 [flex]
- + Perfect adherence to the 'fiery, glowing effect' for the text.
- + Excellent 'exploded' view with clear separation between all burger components.
- + Successfully placed the price inside a glowing starburst.
- − The 'LIMITED TIME ONLY' text is slightly thinner and less impactful than Model A.
- − Some minor physics artifacts in the dripping sauce.
Verdict: FLUX.2 [flex] followed every instruction of the complex prompt, including specific details like the starburst price tag and the glowing fiery text effect. FLUX.1 Krea [dev] produced a high-quality image but missed several functional requirements like the starburst and the exploded separation of components.
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 Krea [dev]
- + Successfully rendered the specific date requested
- + Captures a clean chalkboard aesthetic
- − Numerous spelling errors like 'Gruffle' and 'Chvcnuations'
- − Text looks more like a digital font than natural chalk handwriting
- − Repeated the mushroom item and hallucinated extra lines
FLUX.2 [flex]
- + Excellent text accuracy with no spelling mistakes
- + Convincing chalk texture with realistic smudges and handwriting variations
- + Atmospheric composition with warm café lighting
- − The date line is slightly less 'elegant cursive' than the title above it line
Verdict: FLUX.2 [flex] successfully followed the prompt with high accuracy, producing perfectly spelled menu items in a realistic chalk style. FLUX.1 Krea [dev] failed on text coherence, introducing multiple spelling errors and repeating menu items, while the text style appeared too clean and digital compared to the requested handwritten look.
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 Krea [dev]
- + Excellent lighting and cinematic composition
- + High-quality textures on the space suit and horse hair
- − Failed to follow the spatial instruction of the horse being on top
- − Anatomical issues where the horse's legs merge into mechanical parts
FLUX.2 [flex]
- + Successfully followed the difficult spatial prompt with the horse on top
- + Highly creative and surreal interpretation of 'riding' in space
- + Dynamic lighting with vibrant colors and cosmic details
- − The astronaut's hands and the horse's front hooves have slight merging artifacts
- − The composition is a bit crowded with floating rocks
Verdict: FLUX.2 [flex] successfully interpreted the challenging request for the horse to be 'on top' of the astronaut, creating a literal and surreal interpretation that perfectly matched the prompt. FLUX.1 Krea [dev] ignored the specific spatial instruction, defaulting to a standard astronaut-riding-a-horse image with significant anatomical merging errors.
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 Krea [dev]
- + Excellent texture on the capybara's fur.
- + Accurate prompt adherence regarding the yellow taxi cap.
- + Strong cinematic lighting inside the car.
- − Unexpected secondary female passenger in the front seat.
- − The passenger in the back looks directly at the camera rather than being bored with the phone.
- − The steering wheel appears to be emerging from the capybara's paw awkwardly.
FLUX.2 [flex]
- + Perfect adherence to the passenger's expression and activity.
- + Detailed and realistic taxi interior including the dashboard elements.
- + Correct number of people as per the prompt.
- − The capybara's hands look slightly more humanoid/primate-like than capybara paws.
- − The taxi driver hat has a badge that looks more like a police officer's cap than a standard taxi cap.
Verdict: FLUX.2 [flex] is the clear winner as it correctly followed the instructions for the passenger's behavior and number of occupants, whereas FLUX.1 Krea [dev] added an extra person and had the passenger looking at the camera. FLUX.2 [flex] also captured a more convincing New York street atmosphere through the windows and a more detailed vehicle interior.
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 Krea [dev]
- + Features a highly detailed ornate gothic border with cobwebs.
- + Strong cinematic lighting with a vibrant glowing jack-o-lantern.
- + Creative use of layered banners for hierarchy.
- − Serious text errors including 'Pasty Halloween' and multiple typos in the fine print.
- − The layout feels slightly disorganized with dates and locations split and repeated incorrectly.
FLUX.2 [flex]
- + Perfect text rendering for all requested strings, including the specific date and location.
- + Excellent adherence to the 'dark parchment' aesthetic with torn edges.
- + Clean, professional composition that functions well as an actual invitation.
- − The twisted trees in the background are somewhat simplified compared to Model A.
- − Lighting on the jack-o-lantern is a bit flatter than the first model.
Verdict: FLUX.2 [flex] is the clear winner because it successfully rendered all requested text without spelling errors, whereas FLUX.1 Krea [dev] failed on basic words like 'Halloween' and 'Frights'. FLUX.2 [flex] also captured the vintage parchment texture much more effectively while maintaining a clean, readable 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.1 Krea [dev]
- + Excellent 3D shader work with realistic PBR light reflections on the fish texture.
- + Strong adherence to the 'small diorama' aesthetic with a sharp-edged base.
- + Clean, integrated typography that matches the cartoonish style.
- − The salmon texture looks slightly more like a pattern than natural fish flesh.
- − The flag is placed physically in the food rather than as a floating icon as suggested by the layout.
FLUX.2 [flex]
- + Beautiful composition of various sushi types providing more visual variety.
- + Soft, clay-like premium textures that perfectly fit the 'miniature 3D cartoon' request.
- + Layout of text and flag is very clean and professionally centered.
- − The base diorama is a bit flat compared to the 'raised' request.
- − The text is plain black which feels slightly less integrated than the stylized text in the other model.
Verdict: Both models followed the prompt exceptionally well, but FLUX.2 [flex] produced a more varied and appealing sushi platter with a superior 'claymation' style texture. FLUX.1 Krea [dev] had better surface reflections and lighting, but the single piece of sushi felt less representative of the 'signature dish' than the assortment in FLUX.2 [flex].
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 Krea [dev]
- + Excellent fur texture and lighting on the kitten and fox
- + Vibrant, warm color palette that fits the 'joyful' vibe
- − Failed to include the baby bunny completely, substituting it with a second kitten
- − Several anatomical errors including the puppy missing a front leg and floating butterflies with missing bodies
FLUX.2 [flex]
- + Successfully included all four requested animals: puppy, kitten, bunny, and fox
- + Superior composition with a clear background, visible god rays, and realistic dew sparkles
- + Higher anatomical accuracy and more dynamic movement in the poses
- − The fox's open mouth looks slightly less natural compared to the other animals
Verdict: FLUX.2 [flex] is the clear winner as it followed the complex prompt requirements significantly better, including the bunny which FLUX.1 Krea [dev] missed entirely. Furthermore, FLUX.2 [flex] produced a more coherent image with better anatomical consistency and more effective use of environmental effects like god rays and dew.
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 Krea [dev]
- + Excellent vintage texture and engraving style
- + Dynamic use of banners and decorative flourishes
- + Accurately places the cloche dome as central to the design
- − Significant spelling error in the main restaurant name ('FLANORIN' instead of 'Florian')
- − Cluttered composition that sacrifices the 'minimalist' request
FLUX.2 [flex]
- + Perfect text rendering for both 'Caffè Florian' and 'Est. 1720'
- + Clean and minimalist vector execution adhering to the logo style
- + Well-balanced composition with an arched text layout
- − The steam is a bit faint and lacks the vintage character of the rest of the icon
- − Texture on the background is extremely subtle to the point of being nearly flat
Verdict: While FLUX.1 Krea [dev] captures a more authentic vintage aesthetic with impressive linework, it fails significantly on the primary text, misspelling the restaurant name. FLUX.2 [flex] successfully interprets the 'minimalist' constraint and provides perfect typography, making it the more functional logo despite its simpler style.
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 Krea [dev]
- + Features a bold, high-contrast title.
- + Utilizes a clean vector lunar surface at the bottom.
- − Failed to follow the requested 6-step infographic structure.
- − Icons are nonsensical and unrelated to the specific Saturn V or lunar module requests.
- − Contains jumbled, unreadable text and illogical numbering.
FLUX.2 [flex]
- + Excellent adherence to the 6-step infographic structure with accurate labels.
- + Uses crisp, consistent iconography including a Saturn V and Lunar Module.
- + Perfectly captures the requested NASA-inspired color palette and flat-vector style.
- − The layout for step 6 is slightly crowded at the bottom right.
- − The descent stage icon appears to be suspended by vertical lines that look like a rendering artifact.
Verdict: FLUX.2 [flex] successfully created a coherent, logical infographic that follows every step of the prompt with readable text and accurate icons. In contrast, FLUX.1 Krea [dev] failed to provide a structured infographic, instead producing a chaotic assortment of unrelated icons and distorted text that does not map to the Apollo mission steps.
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