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
Imagen 4.0 Ultra Generate 001
#34 of 62 in Text-to-Image
Where the votes landed
FLUX.1 Krea [dev]
0%
win rate
Ties
0%
Imagen 4.0 Ultra Generate 001
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]
- + Perfect adherence to all prompt elements including the specific placement of the plant.
- + Highly realistic textures on the wooden table and the glass cube's imperfections.
- + Accurate physics-based reflections within the glass and blue sphere.
- − The plant is less distinct in the background compared to Model B.
- − The book texture is slightly repetitive.
Imagen 4.0 Ultra Generate 001
- + High clarity and sharp focus on the plant in the background.
- + Excellent text rendering on the spine of the book.
- + Strong, aesthetic lighting that emphasizes the wooden texture of the table.
- − The blue sphere appears to be floating unnaturally without supporting physics.
- − The plant is not clearly visible through the glass as requested, as the glass seems to act more like a mirror or remain too clear.
Verdict: FLUX.1 Krea [dev] followed the prompt more accurately, particularly regarding the plant's visibility through the glass cube and the realistic resting position of the sphere. While Imagen 4.0 Ultra Generate 001 produced a sharper image with impressive text rendering, the levitating sphere and lack of distortion through the glass made the scene feel less coherent.
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 motion blur in passing cars
- + Natural reflections on the wet pavement
- + Good interpretation of 'imperfect framing' for a candid street look
- − The subject is holding the bicycle rather than repairing it
- − Hands and clothing textures appear slightly soft
Imagen 4.0 Ultra Generate 001
- + Strong adherence to the 'repairing' aspect of the prompt
- + Incredible texture on the skin and rain-slicked jacket
- + Superior anatomical detail in the hands
- − Minimal motion blur in the passing car
- − Composition feels more 'staged' than 'candid street photo'
Verdict: FLUX.1 Krea better captures the atmosphere of the prompt, specifically the motion blur and the feeling of a candid 50mm street snap. However, Imagen 4.0 Ultra is much more successful in depicting the specific action of 'repairing' the bike and provides far superior skin and clothing textures, making it the more technically impressive 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 handling of shallow depth of field and bokeh.
- + Highly realistic texture on the engraved plate armor and leather strap.
- + Dramatic and moody lighting that fits the 'battle-worn' theme.
- − The hair braiding is very minimal compared to the request.
- − The 'scars' look more like fresh blood spatters than healed battle scars.
Imagen 4.0 Ultra Generate 001
- + Superb adherence to the braided hair and beads request.
- + Clearly visible facial scars and dirt textures.
- + Strong representation of the torchlight lighting effect with the torch included.
- − The depth of field is deeper than requested, with many sparks in sharp focus.
- − The composition feels slightly more staged and less natural in its lighting than Model A.
Verdict: Both models followed the prompt well, but they excelled in different areas. FLUX.1 Krea produced a more cinematic and realistic portrait with superior metal textures and lighting, while Imagen 4.0 Ultra Generate 001 showed much better adherence to the specific character design elements like the extensive braids and facial scars. FLUX.1 Krea is the likely winner for its overall photographic quality and mood.
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 layout balance between text and imagery.
- + Includes prices and detailed menu descriptions.
- + High-quality, realistic food photography.
- − Repeats the 'Appetizers' section header twice.
- − Text rendering is slightly garbled and less legible than the competitor.
Imagen 4.0 Ultra Generate 001
- + Excellent typography with clear, legible headers.
- + Perfectly executed grid layout for food photos.
- + Consistently follows the minimalist white background prompt.
- − The menu content is sparse with only names and prices.
- − Missing a dedicated pizza section header in terms of layout grouping (it is placed beside Appetizers).
Verdict: Imagen 4.0 Ultra Generate 001 provides a much cleaner and more professional design that perfectly captures the 'modern minimalist' aesthetic, offering superior text legibility. While FLUX.1 Krea [dev] creates a more realistic document with pricing and descriptions, it suffers from redundant headers and slightly messy typography rendering.
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 photorealistic texture on the bun and patty.
- + Clear, legible typography for the main title.
- + Includes realistic flames and embers at the base for a dramatic effect.
- − Failed to place the price in a starburst as requested.
- − The burger is not fully exploded; many components are still touching or overlapping heavily.
- − Includes gibberish text at the bottom and a duplicate 'Limited Time Only' icon.
Imagen 4.0 Ultra Generate 001
- + Perfect adherence to the 'exploded' instruction with clear spacing between all layers.
- + Accurately followed the styling request for the fiery text and the starburst price tag.
- + Dynamic composition with a swirling ember background that creates a strong sense of motion.
- − The textures look slightly more stylized/illustrative compared to the photorealism of the other image.
- − The starburst shape is a bit jagged and noisy rather than a clean design element.
Verdict: Imagen 4.0 Ultra Generate 001 followed the prompt instructions much more closely, successfully delivering the 'exploded' layout and the specific fiery glowing text effects requested. While FLUX.1 Krea (dev) has slightly more realistic food textures, it failed to separate the burger components adequately and missed the starburst requirement for the price.
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 smudging and texture on the board.
- + Good use of varying font styles (caps and cursive).
- − Numerous spelling errors including 'Gruffle', 'Kcoman', and 'Ulrvcuations'.
- − The text strokes look more like a digital pen than actual dry chalk.
- − Failed to follow the requested menu items accurately.
Imagen 4.0 Ultra Generate 001
- + Excellent prompt adherence with near-perfect spelling for all requested items.
- + The lettering looks much more like authentic hand-drawn chalk with tapered strokes.
- + Captures the requested 'natural variations in letter size' effectively.
- − The lighting reflection in the center of the board slightly obscures the text.
- − Lettering is slightly less 'elegant' than the cursive requested in the prompt.
Verdict: Imagen 4.0 Ultra is the clear winner as it accurately rendered all specific menu items and prices with nearly perfect spelling, whereas FLUX.1 Krea suffered from significant hallucinations and typos. Imagen also captured a much more realistic chalk texture and handwriting style that feels authentic to a café setting.
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]
- + Successfully placed the astronaut underneath the horse as requested
- + Features high-contrast cinematic lighting and realistic textures
- + Interesting mechanical integration between the horse and the astronaut's gear
- − Anatomical issues where the horse's legs merge into the astronaut's equipment
- − Slightly messy composition with ambiguous spatial positioning of limbs
Imagen 4.0 Ultra Generate 001
- + Excellent character design with a custom space helmet for the horse
- + High-quality rendering of cosmic elements like the nebula and planetoid
- + Clean composition with no anatomical artifacts
- − Failed the negative constraint to put the horse on top of the astronaut
- − Results in a standard interpretation of the prompt rather than the requested surreal inversion
Verdict: FLUX.1 Krea [dev] is the only model that successfully followed the difficult spatial instruction to place the horse on top of the astronaut. While Imagen 4.0 Ultra produced a much cleaner and more aesthetically pleasing traditional 'astronaut on a horse' image, it failed the specific core prompt requirement.
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]
- + The exterior view of the taxi lighting and the blurry city background are very realistic.
- + Captures the bored expression of the woman in the back seat perfectly.
- + The taxi sign on top of the car is a nice touch for context.
- − The capybara's cap looks like a miniature plastic novelty rather than a driver's hat.
- − There is an extra woman in the passenger seat not mentioned in the prompt.
- − The positioning of the capybara's paws on the wheel is less defined than the other model.
Imagen 4.0 Ultra Generate 001
- + Excellent interior perspective that makes the viewer feel like they are inside the car.
- + The capybara's hands/paws are clearly on the steering wheel as requested.
- + High-quality rendering of textures, including the fur and the leather interior.
- − The passenger is in the front seat, whereas the prompt specified the back seat.
- − The woman's expression is slightly more frustrated than 'bored/normal'.
- − The capybara's paws look somewhat like human hands with claws, which is slightly uncanny.
Verdict: FLUX.1 Krea [dev] followed the passenger placement instruction better by putting the woman in the back seat, although it added an unnecessary third character. Imagen 4.0 Ultra Generate 001 produced a much more dynamic and well-composed interior shot with better texture quality, but failed significantly by placing the passenger in the front seat next to the driver.
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 moody atmosphere and cinematic lighting consistent with the 'vintage gothic' prompt.
- + Intricate border design that integrates webs and thorns naturally.
- + Strong artistic style with a hand-drawn illustration quality.
- − Significant text errors including misspelled 'Pasty' and repetitive words in the footer.
- − The layout of the event details is cramped inside the bottom scroll.
Imagen 4.0 Ultra Generate 001
- + Perfect adherence to all text requirements with zero spelling errors.
- + Clear and balanced composition with a prominent moon and readable banner.
- + Stronger inclusion of physical 'thorns' in the border as requested.
- − The visual style leans more towards a modern 3D digital illustration than 'vintage gothic'.
- − The lighting is quite bright and saturated, reducing the requested 'moody night sky' effect.
Verdict: While FLUX.1 Krea (dev) captures the atmospheric 'vintage gothic' aesthetic much better, it fails significantly on the text rendering, including a major misspelling in the title. Imagen 4.0 Ultra (Generate 001) produces a much more functional invitation with perfect text accuracy and clear layout, even if the art style feels a bit more like a modern cartoon than a vintage poster.
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 integrated into the 3D scene style
- + Beautiful PBR materials on the salmon nigiri with realistic texture and sheen
- + Clean, minimalist composition that hits the '45° top-down' target perfectly
- − The flag is placed in a way that creates a strange shadow and feels slightly like an afterthought
- − Only shows a single sushi piece, which might be too minimalist for some
Imagen 4.0 Ultra Generate 001
- + Rich variety of sushi types including nigiri and maki with great attention to detail
- + Follows the text and flag placement instructions more precisely according to traditional graphic layout
- + Captures the 'isometric miniature' look well with sharp edges on the diorama base
- − The floating plate logic is slightly off, appearing to hover midway over the base
- − The typography is very basic and looks like a flattened 2D overlay rather than part of the 3D scene
Verdict: FLUX.1 Krea produced a more cohesive artistic image with superior materials and lighting, making the sushi look nearly edible despite the cartoon style. However, Imagen 4.0 Ultra Generate 001 followed the complex content instructions better, providing a full platter of sushi and following the specific text/flag layout instructions more accurately. FLUX.1 Krea is preferred for visual quality, while Imagen 4.0 is preferred for prompt adherence regarding variety.
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 unavailable for this challenge.
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 utilization of woodcut/engraving texture
- + Strong vintage aesthetic with distressed border decor
- + Good integration of the banner elements
- − Failed the main text prompt, rendering 'Café Flanelín' instead of 'Caffè Florian'
- − Contains nonsensical AI gibberish text at the bottom
- − Cloche shape resembles a building dome more than a plate cover
Imagen 4.0 Ultra Generate 001
- + Perfect text rendering of 'CAFFÈ FLORIAN' and the date
- + Highly accurate cloche icon that fits the minimalist vector style
- + Clean and professional layout well-suited for a real restaurant logo
- − Texture is very subtle, bordering on a plain flat background
- − Less 'character' or artistic flair compared to the engraving style of the competitor
Verdict: While FLUX.1 Krea (dev) has a very appealing vintage texture and artistic style, it completely failed to spell the brand name correctly. Imagen 4.0 Ultra Generate 001 followed every part of the prompt, including accurate text, a better cloche representation, and a professional minimalist layout, making it the superior 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]
- + Strong typography for the main title.
- + High-quality vector aesthetic with clean lines.
- − Failed to include the specific icons requested (e.g., Saturn V, lunar module).
- − Nonsensical numerical steps and iconography that don't match the prompt's logical flow.
- − Contains random elements like Saturn (with rings) and multiple human figures not requested.
Imagen 4.0 Ultra Generate 001
- + Successfully captured the infographic layout with a central timeline and side annotations.
- + Adhered much better to the requested color palette.
- + Includes a NASA-style logo and structured list of steps.
- − Text consists of gibberish/lorem ipsum placeholder text.
- − Icons are abstract and messy rather than crisp, recognizable vectors.
- − The vertical flow is somewhat cluttered and difficult to read.
Verdict: Imagen 4.0 Ultra Generate 001 followed the prompt's structural instructions much more closely, delivering a vertical infographic with steps and the correct color story. FLUX.1 Krea [dev] produced a cleaner visual with better text, but the content failed to follow any of the requested steps or scientific context, including irrelevant imagery like Saturn.
Explore each model
Google's Imagen 4.0 Ultra model offering the highest fidelity and resolution for professional-grade image generation