Black Forest Labs' 12 billion parameter distilled image generation model optimized for speed, capable of generating high-quality images in just 4 inference steps
Settled by community votes across 13 shared challenges, with an AI judge weighing in on each.
FLUX.1 [schnell]
18.7
arena score
#48 of 62 in Text-to-Image
Skill signature
· Text-to-Image
Imagen 4.0 Ultra Generate 001
22.1
arena score
#34 of 62 in Text-to-Image
Vote tally
Where the votes landed
FLUX.1 [schnell]
0%
win rate
Ties
0%
Imagen 4.0 Ultra Generate 001
0%
win rate
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.1 [schnell]
Imagen 4.0 Ultra Generate 001
AI Judge Analysis
FLUX.1 [schnell]
- + Excellent plant visibility through the glass
- + Vibrant colors and high resolution
- + Captures the soft window light effect well
- − Added an extra blue sphere on top of the book
- − The sphere inside is very large compared to the 'small sphere' request
Imagen 4.0 Ultra Generate 001
- + Perfect adherence to the spatial requirements
- + Realistic text rendering on the book spine
- + Sophisticated glass refraction and shadow work
- − The plant is very dark and difficult to see through the glass compared to Model A
Verdict: Imagen 4.0 Ultra followed the complex spatial instructions perfectly, placing a single small sphere inside the cube and a book on top. FLUX.1 [schnell] failed the prompt adherence by adding a second sphere on top of the book and making the internal sphere too large, though it did a better job of showing the plant through the glass.
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.1 [schnell]
Imagen 4.0 Ultra Generate 001
AI Judge Analysis
FLUX.1 [schnell]
- + Excellent depiction of a wet pavement with realistic orange light reflections.
- + Captures a believable candid urban environment with period-correct feeling signage.
- − Failed to include visible rain drops or significant motion blur on the cars.
- − The bicycle geometry is slightly warped near the handlebars and chain guard.
Imagen 4.0 Ultra Generate 001
- + Highly detailed 'light rain' effect with visible droplets on the jacket and in the air.
- + Superior skin texture and hand positioning that accurately conveys the act of 'repairing'.
- + Excellent use of shallow depth of field and 'imperfect framing' as requested.
- − The transition between the wall and the bicycle tire is slightly messy.
Verdict: While FLUX.1 [schnell] creates a beautiful atmospheric scene, Imagen 4.0 Ultra follows the prompt criteria much more comprehensively, specifically the 'light rain' and 'repairing' actions. Imagen 4.0 Ultra also excels in 'natural skin texture' and delivers a more authentic candid street photo aesthetic versus the slightly staged look of FLUX.1.
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.1 [schnell]
Imagen 4.0 Ultra Generate 001
AI Judge Analysis
FLUX.1 [schnell]
- + Extremely intense and lifelike eyes
- + High-frequency skin texture and sweat detail
- + Dynamic lighting and soft bokeh background
- − Composition is a bit too tight, obscuring the plate armor
- − Hair beads are barely visible
- − The 'braids' look more like twisted hair clumps
Imagen 4.0 Ultra Generate 001
- + Excellent adherence to the 'hair braided with small beads' instruction
- + Beautifully detailed engraving on the plate armor
- + Includes the actual torch and bokeh sparks as requested
- − Skin texture looks slightly plasticky or over-smoothed compared to Model A
- − The torch flame has a slightly artificial, sticker-like quality
Verdict: While FLUX.1 [schnell] captures a more realistic and intense facial portrait, Imagen 4.0 Ultra is the superior choice for prompt adherence, accurately depicting the braided hair with beads, the ornate engravings, and the bokeh sparks. Imagen 4.0 Ultra provides a better balanced composition that showcases the armor and the torchlight source.
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.1 [schnell]
Imagen 4.0 Ultra Generate 001
AI Judge Analysis
FLUX.1 [schnell]
- + Strong minimalist aesthetic with high whitespace utilization.
- + Features legible core headers using clean sans-serif typography.
- − Body text is essentially unintelligible gibberish.
- − The food photos are repetitive and lack diversity in dish types.
- − One of the requested category headers is misspelled ('ORFEFUS' instead of 'Appetizers').
Imagen 4.0 Ultra Generate 001
- + Excellent grid layout that effectively organizes the menu sections.
- + Higher quality and more varied food photography that looks professional.
- + Better inclusion of prices and coherent, albeit stylized, font work.
- − The 'Appetizers' and 'Pizza' headers are placed side-by-side in a way that creates some layout confusion for the photos below.
- − Includes some minor artifacts in the text characters.
Verdict: Imagen 4.0 Ultra is the superior choice as it provides a much more functional and professional grid layout with higher-quality, diverse food photography. While FLUX.1 [schnell] captures a minimalist vibe well, it fails on content variety and contains significant text errors, including the misspelling of a main section header.
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.1 [schnell]
Imagen 4.0 Ultra Generate 001
AI Judge Analysis
FLUX.1 [schnell]
- + Includes fiery embers and smoke as requested
- + Vibrant colors and high-contrast lighting
- − Failed the exploded burger concept by keeping the main burger intact
- − Poor text rendering with several misspellings and redundant numbers
- − Random non-burger food debris floating around the scene
Imagen 4.0 Ultra Generate 001
- + Perfectly executed the exploded burger composition with all layers visible
- + Flawless text rendering for all three requested messages
- + Strong fiery aesthetic with glowing text effects and starburst design
- − Lighting on the lettuce is slightly flat compared to the bottom bun
Verdict: Imagen 4.0 Ultra follows the prompt instructions with a much higher degree of accuracy, successfully rendering a deconstructed burger and three specific text elements without errors. FLUX.1 [schnell] failed to create the 'exploded' effect and produced garbled text, making it ineffective for the intended advertisement purpose.
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.1 [schnell]
Imagen 4.0 Ultra Generate 001
AI Judge Analysis
FLUX.1 [schnell]
- + The handwriting style looks very authentic and casual.
- + Good background cafe bokeh and frame detail.
- − Numerous spelling errors including 'Pril' and 'Octtoopus'.
- − Fails to follow the specific pricing and items requested.
- − Includes gibberish text at the bottom.
Imagen 4.0 Ultra Generate 001
- + Perfect text accuracy for all requested items and dates.
- + Excellent chalkboard texture with realistic chalk smudges.
- + Clear, elegant handwriting that remains very readable while looking hand-drawn.
- − The handwriting is a bit too uniform, bordering on a digital font look.
- − The 'Today's Specials' title is not in the requested elegant cursive style.
Verdict: Imagen 4.0 Ultra is the clear winner as it followed the prompt's complex text requirements perfectly without a single spelling error. While FLUX.1 [schnell] captures a slightly more natural hand-drawn variation, it suffers from significant spelling mistakes and hallucinates incorrect dish names and prices.
The Reversed Rodeo
Text-to-Image“Horse riding astronaut in space — horse on top, not vice versa. Surreal, highly detailed, cinematic.”
FLUX.1 [schnell]
Imagen 4.0 Ultra Generate 001
AI Judge Analysis
FLUX.1 [schnell]
- + Successfully follows the negative constraint with the horse on top of the astronaut
- + Excellent cinematic lighting and atmospheric depth
- + Strong alignment with the surreal requirement
- − Anatomical glitching with two horse heads and overlapping limbs
- − The astronaut's structure is somewhat incoherent beneath the horse
Imagen 4.0 Ultra Generate 001
- + High visual clarity and sharp textures
- + Technically sound composition with zero anatomical errors
- + Creative touches like the horse's space gear and glowing hooves
- − Completely failed the negative constraint; the astronaut is riding the horse
- − Follows a more conventional, less surreal interpretation of the prompt
Verdict: FLUX.1 [schnell] is the only model that successfully adhered to the difficult logic constraint of having the horse on top of the astronaut, though it suffered from anatomical artifacts in the process. Imagen 4.0 Ultra provided a much cleaner and more professional image, but it failed the primary conceptual challenge by showing a standard horse-riding-astronaut arrangement. FLUX.1 [schnell] is preferred for closer prompt adherence despite the visual messy details.
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.1 [schnell]
Imagen 4.0 Ultra Generate 001
AI Judge Analysis
FLUX.1 [schnell]
- + Excellent photographic quality and lighting
- + Captures the bored, non-chalant expression of the passenger perfectly
- + Realistic textures on the capybara's fur
- − The capybara's paws are not both on the wheel as requested
- − The cap and jacket are slightly less detailed
Imagen 4.0 Ultra Generate 001
- + Adheres better to the structural prompt regarding paws on the steering wheel
- + Very clear and crisp text on the taxi cap
- + Excellent interior vehicle lighting and depth of field
- − The passenger's expression looks slightly stressed rather than 'bored/normal'
- − The capybara's paws have digit artifacts that look more like claws than natural paws
- − Slightly less 'photorealistic' and more 'digital 3D' in style
Verdict: Imagen 4.0 follows the specific positioning instructions more accurately, such as having both paws on the steering wheel. However, FLUX.1 [schnell] creates a more believable, cinematic scene with superior facial expressions and lighting that better capture the deadpan humor of the prompt.
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.1 [schnell]
Imagen 4.0 Ultra Generate 001
AI Judge Analysis
FLUX.1 [schnell]
- + Successfully captures a dark parchment and moody aesthetic
- + Features gothic title text and twisted trees as requested
- + Includes all requested elements like bats and a jack-o-lantern
- − Significant text rendering errors and repetition of phrases
- − The event details are cluttered and contain gibberish labels like 'Fate: butistigtion'
- − The border design is very faint and lacks the requested thorns
Imagen 4.0 Ultra Generate 001
- + Perfect text rendering for both the banner and the specific event details
- + Highly detailed and visible border containing both webs and thorns
- + Excellent cinematic lighting with a clear glowing moon and jack-o-lantern
- − The parchment texture is less 'vintage dark parchment' and more of a digital illustration style
- − Trees are somewhat generic in shape
Verdict: FLUX.1 [schnell] creates a moodier atmosphere but fails significantly on text legibility, producing repetitive and nonsensical phrases in the details section. Imagen 4.0 Ultra Generate 001 provides a much cleaner, more professional result with perfect adherence to the text requirements and a more intricate border design.
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.1 [schnell]
Imagen 4.0 Ultra Generate 001
AI Judge Analysis
FLUX.1 [schnell]
- + Excellent high-clarity 3D rendering with clean PBR materials
- + Perfect adherence to the 45-degree isometric perspective
- + Minimalist diorama base and composition
- − Missed the secondary 'SUSHI' text requirement
- − White text on light blue background has poor contrast
Imagen 4.0 Ultra Generate 001
- + Followed all text instructions including 'JAPAN' and 'SUSHI'
- + Includes a diverse and visually appealing variety of sushi pieces
- + Better text contrast and positioning
- − Shadowing and perspective on the 'floating' plate feel slightly less grounded
- − More complex than 'minimal garnish' request
Verdict: Imagen 4.0 Ultra Generate 001 is the winner because it successfully followed all text prompts, including both requested words and the flag icon, while maintaining high visual quality. FLUX.1 [schnell] produced a cleaner 3D render but failed to include the word 'SUSHI' and suffered from poor text legibility.
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.1 [schnell]
Imagen 4.0 Ultra Generate 001
AI Judge Analysis
FLUX.1 [schnell]
- + Warm, cinematic lighting with a soft atmosphere
- + High detail in the fox kit and puppy features
- + Pleasing soft bokeh in the foreground and background
- − Failed to include a rabbit; instead, it generated two cats
- − The animals are mostly static rather than 'tumbling and chasing'
- − The scale of the animals is a bit inconsistent
Imagen 4.0 Ultra Generate 001
- + Successfully included all four requested animals (dog, cat, rabbit, fox)
- + Dynamic posing that captures the 'tumbling' and 'chasing' aspect of the prompt
- + Excellent lighting effects with clear god rays and dew sparkles on the grass
- − The fox's anatomy looks slightly stylized rather than 'hyper-photorealistic'
- − The tabby kitten's paws look a bit unnatural in their pose
- − The image has a slightly more digital/illustrative feel compared to a raw photo
Verdict: Imagen 4.0 Ultra is the clear winner for prompt adherence, as it successfully included all four specific animals while FLUX.1 [schnell] replaced the rabbit with a second cat. Although FLUX.1 [schnell] captures a more naturalistic photographic texture, Imagen 4.0 Ultra better interprets the action and specific environmental details like the 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.”
FLUX.1 [schnell]
Imagen 4.0 Ultra Generate 001
AI Judge Analysis
FLUX.1 [schnell]
- + Clean vector-style emblem
- + Nice use of negative space in the cloche
- − Failed significantly on text accuracy for the name 'Caffè Florian'
- − Incorrect date '7720'
- − Missing the steam element
Imagen 4.0 Ultra Generate 001
- + Perfect text rendering for name and date
- + Accurate inclusion of all requested elements including steam and banner
- + Sophisticated minimalist line work and shading
- − The banner is slightly disconnected from the main text block
- − The background texture is very faint
Verdict: Imagen 4.0 Ultra is the clear winner as it followed every part of the prompt, including complex text rendering for 'Caffè Florian' and 'Est. 1720'. FLUX.1 [schnell] failed on literal text accuracy, hallucinating both the name and the date, and omitted the requested steam detail.
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.1 [schnell]
Imagen 4.0 Ultra Generate 001
AI Judge Analysis
FLUX.1 [schnell]
- + Successfully captures a flat, minimalist vector aesthetic.
- + Uses a clean and readable layout consistent with current infographic design trends.
- + Accurately represents the requested NASA-inspired color palette.
- − Failed to provide 6 distinct steps with clear labels.
- − Text is largely gibberish and doesn't follow the specific requested content.
- − Iconography for the spacecraft is distorted and confusing.
Imagen 4.0 Ultra Generate 001
- + Includes a clear title and a structured list of steps.
- + Features much better text layout and uses a very professional flat-vector iconography style.
- + Excellent adherence to the color palette and NASA aesthetic.
- − Text is still mostly placeholder/gibberish despite having clear headings.
- − The central graphic is somewhat abstract and less representative of flight steps compared to a timeline.
Verdict: Imagen 4.0 Ultra Generate 001 is the clear winner for its superior composition and professional handling of the flat-vector style. While both models struggled to produce readable English text for the specific steps, Imagen 4.0 created a much more believable and balanced infographic layout whereas FLUX.1 [schnell] produced a confusing and sparsely detailed design.
Next steps
Explore each model
Google's Imagen 4.0 Ultra model offering the highest fidelity and resolution for professional-grade image generation