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]
#48 of 62 in Text-to-Image
FLUX.2 [dev] Turbo
#3 of 62 in Text-to-Image
Where the votes landed
FLUX.1 Krea [dev]
0%
win rate
Ties
0%
FLUX.2 [dev] Turbo
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 photorealistic lighting and depth of field.
- + Accurate glass reflections including the internal blue sphere.
- + High visual quality with realistic textures on the book and table.
- − The plant is completely blurred out and behind the book/cube rather than clearly visible through the glass.
FLUX.2 [dev] Turbo
- + Perfect adherence to the instruction for the plant to be visible through the glass.
- + Natural window light source visible in the frame.
- + Clear spatial arrangement of all requested objects.
- − The sphere appears to be slightly floating or off-center from its shadow.
- − Overall composition is slightly less cinematic compared to Image A.
Verdict: Both models followed the complex spatial prompt very well. FLUX.1 Krea (dev) produced a more aesthetically pleasing, high-contrast photographic image, but FLUX.2 [dev] Turbo followed the specific instruction to make the plant visible through the glass much more effectively.
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]
- + Captures the motion blur of the passing cars effectively
- + Includes a very natural skin texture on the man's face
- + Good use of wet pavement reflections
- − The man is simply holding the bicycle rather than repairing it
- − The bicycle design is a bit generic and clean for the context
- − The face appears slightly more stylized/painterly compared to the realistic prompt
FLUX.2 [dev] Turbo
- + Stronger adherence to the specific action of 'repairing' with tools and loose parts on the ground
- + Highly realistic skin textures and clothing details
- + Excellent rendering of light rain and atmospheric depth
- − The front wheel of the bicycle is clipping through the pavement
- − Small anatomical artifact on the subject's right hand digits
Verdict: FLUX.2 [dev] Turbo followed the prompt's narrative more closely by showing the man actively working on the bike with parts scattered on the ground, whereas FLUX.1 Krea [dev] simply showed him standing with it. While FLUX.2 had a minor clipping issue with the front tire, its superior texture, lighting, and storytelling make it the more compelling and accurate image.
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 mood and cinematic lighting.
- + High contrast between the dark environment and the glowing sparks.
- + Clean, professional-looking bokeh effects.
- − The 'beads' in the hair are very uniform and lack color variation.
- − The scars look more like surface blood or mud than healed tissue.
FLUX.2 [dev] Turbo
- + Outstanding facial details with realistic skin texture and lifelike eyes.
- + Excellent adherence to the 'beads' prompt with varied colors and placements.
- + Superior texture on leather straps and metal weathering.
- − Visible torch in the background is a bit distracting and slightly messy in rendering.
- − Spark bokeh is a bit more chaotic and sharp compared to the first image.
Verdict: While FLUX.1 Krea [dev] produces a very cinematic and clean portrait, FLUX.2 [dev] Turbo provides much better adherence to the specific details of the prompt. FLUX.2 [dev] Turbo captures the 'lifelike eyes', colorful beads, and detailed leather textures with greater fidelity, making it the more accurate and visually rich interpretation.
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]
- + Strong vertical alignment and professional typography
- + Clean, balanced layout with a clear grid system
- + High-quality food photography that fits the restaurant theme
- − Repeated the 'Appetizers' section heading unnecessarily
- − Text content becomes garbled and illegible in the lists
FLUX.2 [dev] Turbo
- + Creative use of color blocks as 'vibrant accents'
- + Better text legibility overall
- + Good categorization that matches the prompt sections
- − The grid of photos feels a bit cluttered and lacks a clear focal point
- − Some odd pricing values like '$2.50' next to '$160' create logical inconsistency
Verdict: FLUX.1 Krea [dev] produces a more realistic and professional layout that looks like a final menu design, despite some gibberish text in the internal lists. FLUX.2 [dev] Turbo follows the request for vibrant accents better with its color bars, but the photo grid is a bit overwhelming and the pricing logic is chaotic. FLUX.1 Krea [dev] is the likely winner for its superior aesthetic balance and cleaner minimalist execution.
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]
- + Excellent photographic texture on the meat patty and bun
- + Clean, professional graphic design for the main headings
- + Intense, cinematic lighting on the lower coals and fire
- − Failed to place the price in a starburst
- − The 'Limited Time Only' text appears twice in different styles
- − Missing the requested 'fiery effect' on the text
FLUX.2 [dev] Turbo
- + Perfectly followed the text styling instructions with fiery, glowing fonts
- + Dynamic composition with splashes of sauce and floating embers
- + Accurately placed the price within a fiery starburst
- − The meat patty looks slightly less realistic and more like a rendering
- − Slightly less 'exploded' verticality compared to a standard deconstructed food shot
Verdict: FLUX.2 [dev] Turbo adhered significantly better to the stylistic text requirements, successfully rendering the fiery glow and the price starburst as requested. While FLUX.1 Krea [dev] produced a more photorealistic burger patty, it missed several key layout instructions, resulting in a more generic advertisement look.
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]
- + Natural chalk texture on the board edges.
- + Includes all requested text and then some additional creative details.
- − Failed the request for 'elegant cursive' in the title.
- − Several spelling errors like 'Gruffle', 'Loman', and 'Chvcruations'.
- − Text appearance is very clean, resembling a digital font more than hand-chalked letters.
FLUX.2 [dev] Turbo
- + Perfectly captures the authentic chalk texture with variations in stroke weight and dusting.
- + Correctly followed the 'elegant cursive' instruction for the title.
- + Accurately spelled all requested menu items with realistic line breaks.
- − The pricing for the cookies is slightly redundant ('9' and '$9').
Verdict: FLUX.2 [dev] Turbo significantly outperformed FLUX.1 Krea [dev] by adhering precisely to the handwriting styles requested, particularly the elegant cursive title. While FLUX.1 Krea [dev] suffered from multiple spelling hallucinations and a 'font-like' appearance, FLUX.2 [dev] Turbo provided a highly realistic chalk texture and accurate text rendering.
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 adherence to the 'horse on top' spatial instruction
- + Surreal mechanical integration of the horse into the astronaut's suit structure
- + High-contrast cinematic lighting
FLUX.2 [dev] Turbo
- + High level of environmental detail in the background
- + Realistic rendering of textures on the spacesuit and horse's mane
- + Cinematic composition with dynamic particle effects
- − Failed the negative spatial constraint to have the horse on top
- − Anatomical issues with the astronaut's leg position
- − Clipped composition at the very top of the frame
Verdict: This was a trick prompt designed to test spatial reasoning. FLUX.1 Krea [dev] (Image A) succeeded by placing the horse on top of the astronaut/equipment as requested, creating a surreal and unique image. FLUX.2 [dev] Turbo (Image B) ignored the specific 'not vice versa' instruction and produced a standard astronaut-riding-horse image, despite its high visual quality.
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 coat and jacket textures on the capybara.
- + Clear lighting that highlights the animal's face.
- + Accurate dark jacket and yellow hat inclusion.
- − The passenger appears to be in the front seat or middle, not clearly the back seat.
- − Includes a strange extra person or reflection artifact in the background.
- − The hat looks more like a construction helmet than a taxi driver cap.
FLUX.2 [dev] Turbo
- + Perfect adherence to character placement with the passenger clearly in the back seat.
- + Highly realistic capybara anatomy and 'professional' facial expression.
- + Realistic taxi driver cap and high-quality background bokeh.
- − The capybara's paws look slightly more like human hands/primate fingers than actual capybara feet.
- − Stronger grain compared to Model A.
Verdict: FLUX.2 [dev] Turbo followed the compositional instructions much better than FLUX.1 Krea [dev], correctly placing the businesswoman in the back seat and providing a much more realistic capybara driver. While FLUX.1 Krea [dev] had nice fur textures, it failed the spatial arrangement and included ghostly visual artifacts in the background.
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]
- + Excellent gothic border with web and thorny elements
- + Elegant typography style for the header
- − Several typos including 'Pasty Halloween' and duplicated words in the small text
- − Garbled event details at the bottom of the image
FLUX.2 [dev] Turbo
- + Near-perfect text rendering for the title and all event details
- + Strong atmospheric composition with detailed twisted trees and thorns
- + Accurate interpretation of the 'dark parchment' and 'scroll banner' elements
- − The jack-o-lantern sits slightly high relative to the scroll banner
Verdict: FLUX.2 [dev] Turbo significantly outperformed FLUX.1 Krea [dev] by accurately rendering all the specific text details requested in the prompt, whereas FLUX.1 Krea [dev] suffered from major spelling errors like 'Pasty' and 'Tright'. FLUX.2 [dev] Turbo also captured the 'parchment' aesthetic more convincingly with a cohesive artistic style.
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 typography with a friendly, cartoonish aesthetic
- + Very clean and minimal diorama base following the high-clarity request
- + Strong use of the light blue background for contrast
- − The sushi texture looks a bit more like plastic than realistic PBR materials
- − The flag is placed physically on the plate, which is a slight departure from graphic design styles
FLUX.2 [dev] Turbo
- + Outstanding PBR materials for the salmon and rice textures
- + Professional layout of text and icon consistently following the prompt's placement rules
- + Balanced composition with tasteful garnish and high-quality wood grain on the base
- − The background has slight grain/noise compared to the solid flat color requested
Verdict: Both models followed the prompt exceptionally well, but FLUX.2 [dev] Turbo takes the lead due to superior texture rendering and material realism, which fits the 'PBR materials' request better than the plastic-like finish of FLUX.1 Krea [dev]. While FLUX.1 Krea [dev] has delightful typography, FLUX.2 [dev] Turbo's overall 3D diorama looks more professional and high-fidelity.
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 soft lighting and atmospheric god rays.
- + Fur textures are extremely plush and well-rendered.
- + Very clean composition with no major anatomical errors.
- − Failed to include the baby bunny entirely.
- − Included two kittens instead of one kitten and one bunny.
FLUX.2 [dev] Turbo
- + Followed the prompt instructions much better by including all four specified animals.
- + Great dynamic action with animals mid-tumble.
- + Adds nice environmental details like dew droplets that catch the light.
- − The fox's tail is awkwardly fused to its leg or looks like a third leg.
- − The kitten has an extra-long, slightly distorted tail.
Verdict: FLUX.2 [dev] Turbo followed the prompt more accurately by including all requested animals (retriever, kitten, fox, and bunny), whereas FLUX.1 Krea [dev] missed the bunny and added a second kitten instead. While FLUX.1 Krea [dev] has slightly cleaner aesthetics and softer lighting, FLUX.2 [dev] Turbo is the preferred choice for its superior prompt adherence and storytelling through the animals' poses.
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 engraving-style detail on the dome and banner
- + Captures an authentic historical vintage aesthetic
- − Failed the primary text spelling with 'FLANDR'IN' instead of 'FLORIAN'
- − Top of the cloche looks slightly distorted like a chimney
FLUX.2 [dev] Turbo
- + Perfect adherence to text prompt including spelling and accent
- + Clean vector-style execution with high readability
- + Accurately placed 'Est. 1720' in the banner as requested
- − Minimalist design is slightly less artistic than the competitor
- − Steam detail is very simplistic compared to the rest of the logo
Verdict: While FLUX.1 Krea (dev) has a very high-quality hand-drawn illustration style, it failed significantly on the text spelling. FLUX.2 [dev] Turbo followed all instructions perfectly, providing correct typography and proper banner placement, resulting in a much more usable logo design.
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]
- + Clean vector aesthetic with consistent line weights.
- + Follows the requested color palette accurately.
- + Bold, legible main heading.
- − Failed to provide the requested icons for Saturn V and Lunar Module.
- − Includes confusing, non-sequential numbering and gibberish text.
- − Logic of the infographic is poor, including four human figures instead of three.
FLUX.2 [dev] Turbo
- + Excellent adherence to the specific requested steps and icons.
- + High-quality text rendering and correct mission names (Armstrong, Aldrin, Collins).
- + Clean layout that effectively guides the eye through the mission's progression.
- − Repeats planets and labels twice (e.g., two Earths, two Translunar labels) creating some visual clutter.
- − Slightly more detail than a strict 'flat-vector' style would typically have.
Verdict: FLUX.2 [dev] Turbo significantly outperformed the other model by accurately following the six-step sequence of the Apollo 11 mission, including specific icons like the Saturn V and Lunar Module. While FLUX.1 Krea [dev] captured a nice vector style, it failed nearly all specific content requirements, providing generic icons and scrambled numerical steps.
Explore each model
Distilled version of Black Forest Labs' FLUX.2 [dev] outperforming it at a cheaper price. Developed by fal.ai.