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 6 shared challenges, with an AI judge weighing in on each.
FLUX.1 Krea [dev]
18.8
arena score
#48 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
FLUX.1 Krea [dev]
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.”
FLUX.1 Krea [dev]
Imagen 3.0 Generate 002
AI Judge Analysis
FLUX.1 Krea [dev]
- + Excellent typography rendering for headers like 'APPETIZERS' and 'MAINES'.
- + Clean vertical split between text and image grid creates a professional look.
- + Realistic food photography that matches the casual dining vibe.
- − Repeats the 'APPETIZERS' section header twice.
- − Text content becomes garbled and messy in the item descriptions.
Imagen 3.0 Generate 002
- + Highly creative grid layout that integrates text blocks directly into the image sequence.
- + Consistent lighting and high visual quality across all food photos.
- + Stronger adherence to the 'grid' requirement by using a checkerboard style.
- − Text alignment is inconsistent within the various white blocks.
- − The square format is less traditional for a restaurant menu compared to the portrait orientation of the competitor.
Verdict: FLUX.1 Krea produced a more traditional and readable menu layout with clear sectioning, though it suffered from a logical error by repeating the appetizer header. Imagen 3.0 Generate 002 offered a more innovative grid design that was visually striking, but the text placement felt a bit cluttered and less functional as an actual menu. FLUX.1 Krea is the winner for its better font legibility and practical portrait orientation.
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 Krea [dev]
Imagen 3.0 Generate 002
AI Judge Analysis
FLUX.1 Krea [dev]
- + Excellent text legibility and accuracy
- + Effective use of vertical space in the layout
- + Strong photorealistic quality on individual ingredients
- − The burger is not truly 'exploded' as requested, with most layers still touching
- − Failed to place the price within a starburst element
- − Text lacks the requested 'fiery, glowing effect'
Imagen 3.0 Generate 002
- + Perfect 'exploded' execution with all components clearly separated and suspended
- + Includes the price in the requested starburst element
- + Dynamic composition with many flying particles and embers
- − Text rendering is slightly messy inside the starburst
- − The 'Magic Burger' title lacks the requested fiery glow, opting for a gold texture instead
Verdict: FLUX.1 Krea (dev) produces much cleaner and more professional typography, but fails the core creative brief of an 'exploded' view. Imagen 3.0 Generate 002 captures the dynamic motion and exploded structure perfectly, including the starburst requirement, making it the better conceptual match despite slightly weaker text handling.
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 Krea [dev]
Imagen 3.0 Generate 002
AI Judge Analysis
FLUX.1 Krea [dev]
- + Excellent chalk texture and realistic smudge marks on the board.
- + Clean and elegant layout with consistent handwritten style.
- + Successful rendering of the specific date requested.
- − Several spelling errors including 'Gruffle' and 'Lcoman'.
- − Repeats variants of the mushroom and octopus items instead of finishing the list correctly.
Imagen 3.0 Generate 002
- + More legible characters with a distinct chalk outline style for the header.
- + Captures the 'cozy cafe' lighting well on the frame.
- + Identifies the 'gluten free' context in the footer even with spelling wobbles.
- − Numerous spelling errors including 'Risotttto', 'Octpsuin', and 'Choouip'.
- − Repeats lines of text frequently, creating a cluttered look.
- − Misses the 'elegant cursive' requirement for the title header.
Verdict: FLUX.1 Krea (dev) produces a much more realistic chalkboard texture and better visual aesthetic, though it struggles with exact spelling on the menu items. Imagen 3.0 Generate 002 manages some interesting chalk effects but suffers from significant text repetition and very poor spelling. FLUX.1 Krea (dev) is the likely winner for its superior composition and more convincing artistic execution of the 'handwritten' request.
The Reversed Rodeo
Text-to-Image“Horse riding astronaut in space — horse on top, not vice versa. Surreal, highly detailed, cinematic.”
FLUX.1 Krea [dev]
Imagen 3.0 Generate 002
AI Judge Analysis
FLUX.1 Krea [dev]
- + Successfully placed the astronaut underneath the horse as requested by 'horse on top'
- + Strong cinematic lighting with high contrast against the Earth.
- − Anatomical confusion where the astronaut and horse merge into mechanical parts
- − The horse's legs are awkwardly rendered and anatomically incorrect.
Imagen 3.0 Generate 002
- + Excellent visual quality and beautiful nebula background
- + Highly detailed space suit and horse textures.
- − Completely failed the negative constraint to have the horse on top
- − Followed the common trope of an astronaut riding a horse instead of the requested surreal reversal.
Verdict: While Imagen 3.0 produced a much more aesthetically pleasing and high-quality image, it failed the specific spatial logic of the prompt. FLUX.1 Krea Attempted the difficult 'horse on top' instruction, resulting in a surreal (if slightly messy) composition that actually follows the user's creative direction.
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 Krea [dev]
Imagen 3.0 Generate 002
AI Judge Analysis
FLUX.1 Krea [dev]
- + Excellent PBR texturing on the salmon and rice grains.
- + Perfectly centered bold typography with high clarity.
- + Very clean, minimal aesthetic that heightens the miniature feel.
- − The 'small flag icon' is rendered as a physical object rather than part of the UI/text grouping as implied.
- − Includes only a single piece of sushi which feels slightly sparse.
Imagen 3.0 Generate 002
- + Better variety of sushi types that more fully represents the dish.
- + Follows the isometric perspective with high precision across all elements.
- + Text placement and flag icon integration are clean and professional.
- − Textures are slightly more 'plastic' and less 'realistic PBR' than Model A.
- − Shadows are a bit softer and less defined than the requested clear 3D look.
Verdict: FLUX.1 Krea [dev] produces a more visually striking image with superior material rendering, especially on the salmon texture. However, Imagen 3.0 Generate 002 offers a better composition of the dish itself and arguably handles the 'flag icon' instruction more logically by placing it alongside the text rather than as a garnish.
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 Krea [dev]
Imagen 3.0 Generate 002
AI Judge Analysis
FLUX.1 Krea [dev]
- + Excellent depiction of motion with the jumping kitten and running puppy.
- + Large, expressive eyes that perfectly match the 'joyful wholesome' prompt.
- + Strong lighting with clear god rays and backlight on the animals.
- − Failed to include the bunny species requested in the prompt.
- − Duplicates the kitten species, resulting in two cats instead of a diverse group.
Imagen 3.0 Generate 002
- + Followed the prompt perfectly by including all four specific animals: puppy, kitten, bunny, and fox kit.
- + Effective 'tumbling' interaction with the bunny on its back.
- + High-quality fur textures and beautiful dew sparkles on the grass.
- − The kitten's expression is slightly more vacant/startled compared to the others.
- − The puppy's tail has a slightly stiff appearance.
Verdict: While FLUX.1 Krea (dev) has slightly more dynamic lighting and movement, it failed major prompt requirements by omitting the bunny and duplicating the kitten. Imagen 3.0 successfully rendered all four requested species with high fidelity and captured the 'tumbling' aspect of the prompt more effectively.
Next steps
Explore each model
Google's Imagen 3.0 text-to-image generation model, producing high-quality images with improved detail and lighting