Black Forest Labs' enhanced 12-billion parameter flow transformer with 6x faster generation than FLUX.1 [pro], delivering superior composition, detail, and artistic fidelity
Settled by community votes across 6 shared challenges, with an AI judge weighing in on each.
FLUX1.1 [pro]
18.4
arena score
#50 of 62 in Text-to-Image
Skill signature
· Text-to-Image
Imagen 3.0 Generate 002
21.0
arena score
#36 of 62 in Text-to-Image
Vote tally
Where the votes landed
FLUX1.1 [pro]
0%
win rate
Ties
0%
Imagen 3.0 Generate 002
0%
win rate
Shared challenges
6
Challenge by challenge
The strongest take from each model on every shared challenge, with the AI judge's read.
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.”
FLUX1.1 [pro]
Imagen 3.0 Generate 002
AI Judge Analysis
FLUX1.1 [pro]
- + Excellent presentation for a mockup with realistic silverware and shadow effects.
- + Better text-to-image coherence for specific menu sections like appetizers and 'Pizza'.
- + Cleaner white space usage typical of high-end minimalist menus.
- − Contains floating graphical glitches and 'ghost' text on the side panels.
- − Small, illegible body text.
- − Food photography grid is a bit messy and lacks the geometric precision of the other model.
Imagen 3.0 Generate 002
- + Perfectly adheres to the grid layout request for food photos.
- + Consistently bold and impactful sans-serif typography.
- + High image quality for the individual food photography panels.
- − Repetitive food photos (mostly pizzas) despite prompts for appetizers and mains.
- − The layout is a bit cramped with less white space than requested for a minimalist aesthetic.
- − Text contains more gibberish compared to the other model.
Verdict: FLUX1.1 [pro] provides a more professional restaurant mockup with better use of negative space and logical sectioning, though it suffers from some technical artifacts and illegible small text. Imagen 3.0 Generate 002 follows the grid layout prompt more literally and features vibrant food photography, but the repetitiveness of the pizza imagery despite the multi-section prompt makes it less versatile as a menu. FLUX1.1 [pro] is the likely winner for its superior minimalist composition and realistic presentation style.
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.”
FLUX1.1 [pro]
Imagen 3.0 Generate 002
AI Judge Analysis
FLUX1.1 [pro]
- + Excellent photographic texture on the burger patties and buns.
- + Clear, legible typography for the main title and price.
- + Strong sense of depth with professional lighting and background bokeh.
- − Failed to produce an 'exploded' burger, showing an assembled one instead.
- − Includes redundant text elements that were not requested.
- − Missing the required starburst for the price.
Imagen 3.0 Generate 002
- + Successfully followed the 'exploded' view instruction with suspended components.
- + Included all requested text elements including the starburst for the price.
- + Captured the fiery background and glowing embers more effectively.
- − The price starburst contains garbled and nonsensical placeholder text.
- − The 'glow' on the main title is more metallic than fiery as requested.
- − The tomato slices and lettuce look slightly more like CGI/illustrations than photorealistic.
Verdict: While FLUX1.1 [pro] has superior photorealistic textures, it failed the core compositional requirement of an 'exploded' burger. Imagen 3.0 Generate 002 captured the requested motion, layout, and specific graphical elements like the starburst, making it the more accurate ad despite some garbled text in the secondary fields.
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.”
FLUX1.1 [pro]
Imagen 3.0 Generate 002
AI Judge Analysis
FLUX1.1 [pro]
- + Excellent photographic quality and atmospheric lighting
- + The handwriting style is very consistent and realistic across the whole board
- + Captures the 'cozy café' aesthetic perfectly with the bokeh background
- − Failed the text prompt, splitting the octopus dish into two nonsense lines including '$228'
- − Invented 'Chipkies' and spelling errors in the footer text like 'giluten'
- − The title does not use the specific requested phrase all in one line
Imagen 3.0 Generate 002
- + Better adherence to the chalk texture request with realistic smudges and dusty background
- + Followed the specific header text 'TODAY'S SPECIALS' more accurately
- + Includes the complete date in the requested format
- − Numerous spelling errors including 'Risotttto', 'Octpsuin', and 'Choouip'
- − Redundant lines of text that Repeat items with different misspellings
- − Handwriting looks slightly more like a digital font than natural human variations
Verdict: While FLUX1.1 [pro] produces a more aesthetically pleasing and high-quality image, it fails significantly on the text accuracy, creating bizarre prices and menu items. Imagen 3.0 Generate 002 captures the chalk texture and board layout better but suffers from severe spelling hallucination and repetition. FLUX1.1 [pro] is the likely winner because its handwriting is more believable as actual chalk, despite the typos.
The Reversed Rodeo
Text-to-Image“Horse riding astronaut in space — horse on top, not vice versa. Surreal, highly detailed, cinematic.”
FLUX1.1 [pro]
Imagen 3.0 Generate 002
AI Judge Analysis
FLUX1.1 [pro]
- + Dynamic cinematic composition with dramatic lighting
- + High level of detail in the horse's anatomy and astronaut's suit
- − Completely failed the semantic instruction 'horse on top'
- − Anatomical issues where the horse's front legs merge oddly with the chest
Imagen 3.0 Generate 002
- + Excellent visual clarity and starfield background
- + Clean anatomical lines for both the subject and the animal
- − Completely failed the semantic instruction 'horse on top'
- − Standard, predictable composition rather than 'surreal'
Verdict: Both models completely ignored the difficult spatial instruction 'horse on top, not vice versa', defaulting to a standard astronaut riding a horse. FLUX1.1 [pro] provides a more cinematic and detailed aesthetic, whereas Imagen 3.0 Generate 002 is cleaner but lacks the requested surrealism. Since both failed the primary prompt constraint, FLUX1.1 [pro] is slightly preferred for its superior 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.”
FLUX1.1 [pro]
Imagen 3.0 Generate 002
AI Judge Analysis
FLUX1.1 [pro]
- + Excellent typography with a playful, rounded font that matches the 3D aesthetic.
- + High-quality soft lighting and refined, smooth textures that give it a premium 3D render feel.
- + Vibrant color palette and varied sushi types that create a more interesting scene.
- − Missed the request for a small flag icon.
- − The text is slightly off-center compared to the platform.
Imagen 3.0 Generate 002
- + Perfectly followed all prompt instructions including the small flag icon.
- + True 45° isometric perspective with high geometric clarity.
- + Stronger adherence to the 'small raised diorama base' with visible legs on the platform.
- − The text layout is aligned to the top-left rather than being top-center as requested.
- − The 'fish' textures on the sushi look slightly more artificial/plastic compared to Model A.
Verdict: Imagen 3.0 Generate 002 demonstrated better overall adherence to the prompt's specific details, including the flag icon and the diorama base structure, though it failed the centering instruction for the text. FLUX1.1 [pro] produced a more visually pleasing and artistically cohesive 3D render with superior lighting, but omitted the flag. Imagen 3.0 is preferred for its technical precision and literal prompt compliance.
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.”
FLUX1.1 [pro]
Imagen 3.0 Generate 002
AI Judge Analysis
FLUX1.1 [pro]
- + Excellent use of backlighting and rim light on the fur
- + Expressive and emotive facial expressions on the animals
- + Achieves a magical, high-fantasy aesthetic with the light rays
- − Failed to include the red fox kit mentioned in the prompt
- − Butterflies are overly simplified and look like glowing shapes rather than insects
- − Missing the 'tumbling' action as the animals are mostly sitting
Imagen 3.0 Generate 002
- + Successfully included all four animals: golden retriever, tabby kitten, bunny, and fox kit
- + Better adherence to the 'tumbling together' action with the dynamic poses
- + Detailed and realistic rendering of the butterflies and dew particles
- − The bunny's anatomy is slightly fused with the cat's space in the center
- − Slightly less 'masterpiece' feel to the lighting compared to Model A
- − The fox kit has slightly less expressive eyes than the others
Verdict: FLUX1.1 [pro] created a more aesthetically pleasing image with superior lighting, but failed to include all the requested subjects and the specific action of tumbling. Imagen 3.0 Generate 002 captured the full set of animals and the playful movement requested in the prompt, making it a better match for the complex text requirements.
Next steps
Explore each model
Google's Imagen 3.0 text-to-image generation model, producing high-quality images with improved detail and lighting