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]
24.5
arena score
#18 of 62 in Text-to-Image
Skill signature
· Text-to-Image
Imagen 4.0 Ultra Generate 001
21.9
arena score
#33 of 62 in Text-to-Image
Vote tally
Where the votes landed
FLUX.2 [dev]
40.0%
win rate
Ties
0.0%
Imagen 4.0 Ultra Generate 001
60.0%
win rate
40.0%
0.0% ties
60.0%
Shared challenges
13
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.”
FLUX.2 [dev]
Imagen 4.0 Ultra Generate 001
AI Judge Analysis
FLUX.2 [dev]
- + The glass cube looks realistic and tangible, resembling a glass brick.
- + Correctly places a blue sphere inside the cube resting on the bottom surface.
- + Excellent refraction of the plant through the glass walls.
- − The sphere appears to be slightly floating or off-center rather than firmly grounded.
- − The book texture is a bit generic and simple.
Imagen 4.0 Ultra Generate 001
- + High visual clarity with sharp edges on the glass and detailed book text.
- + The plant is clearly visible behind the cube as requested.
- + The lighting and shadows on the wooden table are well-rendered.
- − The blue sphere is physically impossible, appearing to float in the dead center of a solid glass block.
- − The reflection/refraction within the cube is confusing, showing a ghosting effect of the sphere.
Verdict: FLUX.2 [dev] followed the prompt more realistically, placing the sphere at the bottom of the glass container. While Imagen 4.0 Ultra Generate 001 has higher detail in the book and textures, it rendered the sphere floating in the middle of the glass, which looks like a digital artifact rather than a physical object inside a vessel.
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.”
FLUX.2 [dev]
Imagen 4.0 Ultra Generate 001
100% wins
0% ties
0% wins
AI Judge Analysis
FLUX.2 [dev]
- + Excellent adherence to the motion blur request for passing cars.
- + Very realistic skin texture and age-appropriate features.
- + Strong technical execution of the wet pavement reflections and light rain visualization.
- − The bicycle structure is physically incoherent with tangled wires and impossible frame geometry.
- − Subject is positioned dangerously close to high-speed blurred traffic, creating a logical inconsistency.
Imagen 4.0 Ultra Generate 001
- + Highly detailed skin texture and facial features with a very realistic photographic look.
- + The bicycle components, while simplified, are much more coherent and recognizable than Model A.
- + Excellent rendering of water droplets on the man's jacket and the ground.
- − Failed to include the requested motion blur of passing cars, as the background vehicles are static.
- − The white spots on the ground look more like petals or litter than rain reflections/splashes.
Verdict: FLUX.2 [dev] followed the complex motion blur and street-photography framing prompts much better, though the bicycle itself is a mess of AI artifacts. Imagen 4.0 Ultra produced a much cleaner and more believable subject and prop, but completely ignored the 'motion blur from passing cars' instruction. FLUX.2 [dev] is preferred for capturing the requested atmosphere and technical motion effects, despite the structural failures of the bike.
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.”
FLUX.2 [dev]
Imagen 4.0 Ultra Generate 001
AI Judge Analysis
FLUX.2 [dev]
- + Excellent depiction of battle-worn skin with realistic scars and dirt
- + Dynamic lighting with a soft, natural glow from the torch
- + Great shallow depth of field with cinematic bokeh
- − The leather straps look a bit flat in texture compared to the rest of the image
- − Fewer braided beads than specified
Imagen 4.0 Ultra Generate 001
- + Exceptional detail on the engraved armor and metal textures
- + Highly ornate braided hair with many beads and rings as requested
- + Strong, crisp resolution on the leather and cloth underlayer textures
- − The scars look like surface-level scratches rather than deep, lived-in battle scars
- − Lighting feels slightly more artificial and less ambient than the first image
Verdict: FLUX.2 [dev] excels in capturing the cinematic atmosphere and 'battle-worn' essence with more realistic skin texture and lighting. Imagen 4.0 Ultra Generate 001 provides superior detail in the props, such as the armor engravings and numerous hair beads, giving it a sharper but slightly less organic feel.
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.”
FLUX.2 [dev]
Imagen 4.0 Ultra Generate 001
AI Judge Analysis
FLUX.2 [dev]
- + Strong professional layout resembling a multi-page physical menu.
- + Excellent use of typography and colorful accents.
- + High-quality, appetizing food photography.
- − Text is largely gibberish.
- − Pricing values are inconsistent and unrealistic.
Imagen 4.0 Ultra Generate 001
- + Strict adherence to the 'grid' layout requested in the prompt.
- + Greater legibility in the short text labels and prices.
- + Very clean, minimalist aesthetic with ample white space.
- − The layout is a bit repetitive and feels more like a website thumbnail gallery than a menu.
- − Several food photos appear repetitive or truncated at the edges of the grid.
Verdict: FLUX.2 [dev] produces a more realistic and professional-looking menu layout with sophisticated typography and design flair, whereas Imagen 4.0 Ultra Generate 001 interprets the 'grid' instruction more literally, resulting in a cleaner but less dynamic composition. While Imagen 4.0 has better text legibility, FLUX.2 [dev] feels more like a finished design project for a casual dining establishment.
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.”
FLUX.2 [dev]
Imagen 4.0 Ultra Generate 001
AI Judge Analysis
FLUX.2 [dev]
- + Excellent typography with a distinct, glowing neon effect.
- + The fiery starburst for the price is highly energetic and thematic.
- + Good use of negative space for a clean advertising layout.
- − The 'exploded' effect is a bit static, with components appearing neatly stacked rather than flying apart.
- − The lettuce and tomato look slightly plastic and less photorealistic than Image B.
Imagen 4.0 Ultra Generate 001
- + Excellent textures on the toasted bun and grilled patty for high photorealism.
- + Dynamic composition with a swirling ember background that conveys motion.
- + Perfect adherence to the 'exploded' request with ingredients visibly separated and angled.
- − The text is less integrated into the 'fiery' theme compared to Model A.
- − The starburst at the bottom feels slightly disconnected from the central action.
Verdict: FLUX.2 [dev] excels in graphic design and typography, creating a very polished ad layout with superior fiery text effects. However, Imagen 4.0 Ultra Generate 001 produces a much more dynamic and photorealistic burger with better ingredient textures and a stronger sense of motion, which better fits the 'exploded' portion of the prompt. While FLUX.2 is better for a final poster, Imagen 4.0 Ultra is the winner for visual fidelity and adherence to the dynamic motion requirements.
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.”
FLUX.2 [dev]
Imagen 4.0 Ultra Generate 001
AI Judge Analysis
FLUX.2 [dev]
- + Superb chalk texture with realistic dusty residue and smudging
- + Excellent variety in letter sizes and natural handwriting quirks
- + Completed the 'Brown Butter' text intelligently despite the prompt cut-off
- − The 'w' in 'with' on the second item is slightly garbled/overlaid
- − Title is not strictly in 'elegant cursive' as requested, leaning more towards print
Imagen 4.0 Ultra Generate 001
- + Extremely clean and legible text rendering
- + Text follows a consistent and elegant style throughout
- + Composition is perfectly centered and balanced within the frame
- − Lacks realistic chalk texture, appearing more like a digital font or chalk marker
- − Background smudging feels like a repetitive digital filter rather than natural board use
- − No natural variations in letter size or slant as requested in the prompt
Verdict: FLUX.2 [dev] significantly outperforms Image B in terms of texture and authenticity, capturing the tactile feel of physical chalk on a board with dust and smudges. While Imagen 4.0 Ultra is more legible and perfectly centered, it fails to deliver the 'chalk texture' and 'natural variations' requested, looking like a digital approximation rather than a handwritten board.
The Reversed Rodeo
Text-to-Image“Horse riding astronaut in space — horse on top, not vice versa. Surreal, highly detailed, cinematic.”
FLUX.2 [dev]
Imagen 4.0 Ultra Generate 001
AI Judge Analysis
FLUX.2 [dev]
- + Excellent texture on the horse's fur and the astronaut's suit details.
- + High cinematic quality with realistic atmospheric lighting and a sense of movement.
- + Clear background elements like the Earth and Moon provided context for the space setting.
- − Failed the specific spatial instruction; the astronaut is riding the horse, not the other way around.
- − The astronaut's posture is slightly stiff compared to the horse's dynamic pose.
Imagen 4.0 Ultra Generate 001
- + Creative use of props like the horse's space helmet and lit-up hoof gear.
- + Balanced composition with the asteroid and ringed planet background.
- + Clean, sharp rendering with surreal lighting effects.
- − Failed the specific spatial instruction; the astronaut is riding the horse, which is the standard interpretation.
- − The horse's anatomy feels a bit static and less organic than Model A.
Verdict: Both models failed the specific prompt trick asking for the horse to be on top of the astronaut. However, FLUX.2 [dev] produced a more visually stunning and realistic image with better textures and a more dynamic sense of action, whereas Imagen 4.0 Ultra had a more literal 'space' interpretation by adding sci-fi gear to the horse.
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.”
FLUX.2 [dev]
Imagen 4.0 Ultra Generate 001
AI Judge Analysis
FLUX.2 [dev]
- + Excellent photorealistic lighting and textures
- + Perfectly captures the 'bored' expression of the passenger
- + Composition feels like an authentic camera angle through the windshield
- − The capybara's paws look more like human hands with animal skin than actual paws
Imagen 4.0 Ultra Generate 001
- + Successfully includes the capybara's sharp claws on the steering wheel
- + Very clean and sharp rendering of the taxi interior and city bokeh
- − The passenger looks stressed or surprised rather than bored
- − Slightly more artificial, digital art feel compared to Image A
Verdict: FLUX.2 [dev] achieves a higher level of photorealism and better captures the specific 'bored' mood of the passenger, making the surreal scene feel more grounded. Imagen 4.0 Ultra produces a cleaner image with better claw details on the driver, but the passenger's expression and the overall lighting feel less like a real photograph.
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.”
FLUX.2 [dev]
Imagen 4.0 Ultra Generate 001
AI Judge Analysis
FLUX.2 [dev]
- + Excellent typography with perfect spelling and spacing.
- + Successfully captures the 'dark parchment' and 'vintage gothic' aesthetic through colors and textures.
- + Sophisticated border integration that aligns well with the twisted tree background.
- − The jack-o-lantern is quite dark, which results in slightly less internal 'glow' compared to the other model.
Imagen 4.0 Ultra Generate 001
- + Dynamic composition with a nice curved scroll banner.
- + Vibrant lighting effects with the glowing pumpkin and moon contrast.
- + Includes all requested elements including bats and webs clearly.
- − The 'Vintage gothic' aesthetic feels a bit more like a modern digital illustration than parchment.
- − The border appears a bit busy and overlaps the text slightly at the bottom.
Verdict: Both models followed the prompt instructions perfectly, including the complex text requirements. FLUX.2 [dev] is the winner because it better captures the specific 'vintage gothic' and 'parchment' texture requested, whereas Imagen 4.0 Ultra feels more like a clean modern cartoon. FLUX.2 [dev] also exhibits slightly better layout balance for a formal invitation.
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.”
FLUX.2 [dev]
Imagen 4.0 Ultra Generate 001
AI Judge Analysis
FLUX.2 [dev]
- + Excellent typography layout and centering as requested.
- + Very smooth, high-quality PBR textures on the sushi and wasabi.
- + Accurate miniature diorama aesthetic with a nice wood-accented base.
- − The sushi variety is a bit limited compared to typical signature displays.
Imagen 4.0 Ultra Generate 001
- + Great variety of sushi types including nigiri and gunkan.
- + Very sharp, clean rendering of 3D materials.
- + Adheres well to all prompt elements including the isometric perspective.
- − The flag is placed to the side instead of being below the text as requested.
- − The 'SUSHI' text is quite small compared to 'JAPAN'.
Verdict: Both models followed the prompt exceptionally well, producing clean, high-quality 3D diorama designs. FLUX.2 [dev] is the winner because it followed the specific layout instructions for the text and flag more accurately, creating a more balanced and centered composition, whereas imagen-4-0-ultra-generate-001 placed the flag off-center.
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.”
FLUX.2 [dev]
Imagen 4.0 Ultra Generate 001
25% wins
0% ties
75% wins
AI Judge Analysis
FLUX.2 [dev]
- + Excellent hyper-photorealistic textures, particularly the backlighting on the fur.
- + Very natural composition with realistic lighting and 'god rays' that feel integrated into the scene.
- + Accurate species representation with high anatomical fidelity for all four animals.
- − The animals are sitting relatively still rather than 'chasing' or 'tumbling' as requested.
- − The 'dew sparkles' are present but subtle compared to the other model.
Imagen 4.0 Ultra Generate 001
- + Strong adherence to the action keywords, showing the animals playfully 'chasing' and standing on hind legs.
- + Highly vibrant and whimsical colors that enhance the 'joyful' vibe.
- + Clear inclusion of all prompt elements, including prominent dew drops and many butterflies.
- − Lacks photorealism, leaning more toward a digital illustration or 3D render style.
- − The kitten's anatomy and pose look slightly awkward and less realistic than the other animals.
- − Over-sharpened details make the fur look somewhat artificial.
Verdict: FLUX.2 [dev] produces a significantly more realistic and aesthetically pleasing 'masterpiece' with sophisticated lighting and texture, though the animals are more stationary than the prompt suggested. Imagen 4.0 Ultra captures the playful action and 'chasing' aspect much better, but the visual style feels more like a cartoon or stock illustration rather than the requested hyper-photorealistic scene. FLUX.2 [dev] is the winner for its superior visual quality and expert handling of light and fur.
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.”
FLUX.2 [dev]
Imagen 4.0 Ultra Generate 001
AI Judge Analysis
FLUX.2 [dev]
- + Excellent typography integrated into a dynamic ribbon design
- + Rich, warm tonal palette that matches the 'vintage' request perfectly
- + Effective use of subtle texture on the background to enhance the retro feel
- − The ribbon geometry is slightly complex and cluttered for a 'minimalist' logo
Imagen 4.0 Ultra Generate 001
- + Cleaner, more minimalist vector style that is easier to read
- + Accurate representation of the cloche dome with fine hatching details
- + Perfect text rendering with consistent spacing
- − The overall layout feels a bit disjointed with many horizontal elements
- − The steam effect is a bit thin compared to the bold lines of the text
Verdict: Both models followed the prompt exceptionally well, producing high-quality vintage logos with correct spelling and historical data. FLUX.2 [dev] captures a more cohesive 'emblem' feel with its integrated ribbon, while Imagen 4.0 Ultra Generate 001 provides a cleaner, more modern interpretation of minimalism with superior line work clarity.
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.”
FLUX.2 [dev]
Imagen 4.0 Ultra Generate 001
AI Judge Analysis
FLUX.2 [dev]
- + Excellent iconography that captures the requested phases through descent and landing.
- + Clean, modern design with clear step-by-step illustrations.
- + Strict adherence to the requested NASA-inspired color palette.
- − Text is repeated or slightly garbled in a few areas like 'SATURN ICON' and 'LTUREST LIAMDIES'.
- − The layout is a bit repetitive, using a simple grid rather than an integrated flow.
Imagen 4.0 Ultra Generate 001
- + Strong 'poster' feel with a more complex layout and background elements.
- + Good use of negative space for the main infographic area.
- + Includes a NASA-style logo and extra thematic icons.
- − Visual text is largely gibberish and does not follow the requested steps.
- − Icons are more abstract and less descriptive of the specific Apollo 11 mission phases.
- − Fails to clearly illustrate the 6 requested steps in order.
Verdict: FLUX.2 [dev] followed the prompt's logical structure much better, successfully illustrating specific phases like Translunar and Descent with appropriate icons, even if its layout was simpler. Imagen 4.0 Ultra generated a more stylistically unified poster, but it failed the core task of creating an infographic about the specific steps requested, opting for gibberish text and unrelated symbols.
Next steps
Explore each model
Google's Imagen 4.0 Ultra model offering the highest fidelity and resolution for professional-grade image generation