Black Forest Labs' 12-billion parameter flow transformer for high-quality text-to-image generation, suitable for personal and commercial use with streaming support
Settled by community votes across 6 shared challenges, with an AI judge weighing in on each.
FLUX.1 [dev]
24.6
arena score
#16 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 [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 [dev]
Imagen 3.0 Generate 002
AI Judge Analysis
FLUX.1 [dev]
- + Clean, professional typographic hierarchy with legible headers.
- + Excellent use of negative space for a modern minimalist look.
- + High-quality, realistic food photography with transparent backgrounds.
- − Failed to incorporate the 'grid' layout for the photos as requested.
- − The pizza category is missing as a distinct section header.
Imagen 3.0 Generate 002
- + Perfectly adhered to the 'grid' layout request for food photos.
- + Included all requested sections: Appetizers, Pizza, and Mains.
- + Bold sans-serif typography matches the 'modern minimalist' aesthetic well.
- − Text legibility in the body sections is poor with significant artifacts.
- − The layout feels slightly repetitive with so many small grid blocks.
Verdict: Imagen 3.0 followed the structural prompt instructions much better, successfully creating a grid-based layout with all the requested categories. However, FLUX.1 [dev] produced a more polished and professional final design with superior photo integration and cleaner typography, even though it missed the grid requirement.
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 [dev]
Imagen 3.0 Generate 002
AI Judge Analysis
FLUX.1 [dev]
- + Features a very clean, high-contrast dark background
- + Good vertical explosion composition that feels organized
- − Failed to include the primary 'MAGIC BURGER' title entirely
- − Missing the requested starburst and fiery glowing effect for text
- − Image looks more like a stack of several burgers rather than one exploded burger
Imagen 3.0 Generate 002
- + Successfully integrated all required text with high accuracy
- + Includes the starburst element and fiery background with embers as requested
- + Excellent dynamic composition with flying ingredients and sauces
- − The text inside the starburst contains some gibberish characters
- − Texture on the buns looks slightly more illustrative than photorealistic
Verdict: Imagen 3.0 Generate 002 is the clear winner as it followed all prompt instructions, including complex text rendering and specific layout elements like the starburst. FLUX.1 [dev] failed to include the most important text element ('MAGIC BURGER') and missed the specific background and atmospheric 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.1 [dev]
Imagen 3.0 Generate 002
AI Judge Analysis
FLUX.1 [dev]
- + Excellent text rendering with near-perfect spelling for the entire prompt.
- + The chalk texture is highly realistic with believable smudging and varied pressure.
- + Great artistic consistency between the cursive and print styles while remaining handwritten.
- − Minor spelling glitches in the supplementary text at the bottom ('drish', 'ufor').
Imagen 3.0 Generate 002
- + Natural-looking chalkboard smudges and eraser marks add to the realism of the medium.
- + Good layout that fills the chalkboard space effectively.
- − Significant spelling errors including 'Risotttto', 'Octpsuin', and 'Choouip'.
- − Repeats menu items unnecessarily, creating a cluttered and confusing list.
- − Fails to render the elegant cursive requested for the title.
Verdict: FLUX.1 [dev] followed the prompt instructions much more accurately, producing legible text and correctly completing the truncated menu item from the prompt. In contrast, Imagen 3.0 Generate 002 suffered from severe spelling hallucinations and awkward repetition of the menu lines, making it less usable.
The Reversed Rodeo
Text-to-Image“Horse riding astronaut in space — horse on top, not vice versa. Surreal, highly detailed, cinematic.”
FLUX.1 [dev]
Imagen 3.0 Generate 002
AI Judge Analysis
FLUX.1 [dev]
- + Features a clean, cinematic lighting style with a nice glow from the planet below.
- + Good interpretation of the astronaut suit details.
- − Failed the specific spatial instruction for the horse to be on top of the astronaut.
- − Significant anatomical errors with five legs visible beneath the horse.
Imagen 3.0 Generate 002
- + High level of intricate detail in the horse's mane and the star-field background.
- + Cleaner composition with better anatomical consistency than the competitor.
- − Failed to follow the contradictory 'horse on top' spatial instruction.
- − The horse's face appears slightly flattened/distorted in profile.
Verdict: Both models failed the specific prompt instruction to place the horse on top of the astronaut, instead defaulting to the more common astronaut riding a horse. FLUX.1 [dev] produced a serious anatomical error with five legs on the horse, while Imagen 3.0 Generate 002 produced a more coherent, detailed, and visually appealing cosmic scene.
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 [dev]
Imagen 3.0 Generate 002
AI Judge Analysis
FLUX.1 [dev]
- + Excellent PBR materials with realistic subsurface scattering on the fish textures.
- + Creative use of miniature foliage to enhance the diorama feel.
- + Beautiful lighting and depth of field that creates a high-end photography look.
- − Text rendering is poor, with 'SUSHI' misspelled as 'SUSH CATON' and extra characters present.
- − The isometric angle is slightly off, leaning more towards a standard perspective shot.
Imagen 3.0 Generate 002
- + Perfect adherence to the isometric perspective and composition requirements.
- + Excellent text rendering and layout for 'JAPAN' and 'SUSHI'.
- + Clean, cartoonish aesthetic that fits the 'miniature 3D cartoon' prompt perfectly.
- − Materials look a bit more like matte plastic than the requested refined/realistic PBR textures.
- − The sushi rice texture is somewhat repetitive and lacks natural variation.
Verdict: Imagen 3.0 Generate 002 is the overall winner because it followed every instruction, including the complex text and layout requirements, perfectly. While FLUX.1 [dev] produced a more visually stunning image with superior lighting and materials, it failed significantly on the text rendering and did not capture the strict isometric style as well as the other model.
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 [dev]
Imagen 3.0 Generate 002
AI Judge Analysis
FLUX.1 [dev]
- + Successfully captures a joyful, wholesome vibe
- + Attractive warm golden sunset lighting
- + Clean, high-resolution rendering with no visible artifacts
- − Failed the photorealistic requirement, appearing as a 3D animation/cartoon style
- − Missed a core prompt element by including two dogs and no kitten
- − Anatomically incorrect paws and ears on the fox-like creatures
Imagen 3.0 Generate 002
- + Excellent adherence to the hyper-photorealistic requirement
- + Accurately includes all four requested animals: puppy, kitten, bunny, and fox kit
- + Beautifully captures the requested 'tumbling' interaction and 'dew sparkles'
- − The fox kit has a slightly awkward paw placement near its chest
- − The bunny's belly fur texture is slightly less detailed than the puppy's fur
Verdict: Imagen 3.0 Generate 002 is the clear winner as it perfectly follows the prompt's instructions for a hyper-photorealistic style and includes all four specific animals, whereas FLUX.1 [dev] produced a cartoonish, 3D-animation style that omitted the kitten entirely. Imagen 3.0 Generate 002 also successfully rendered the 'tumbling' action and 'dew sparkles' which added to the overall 8K masterpiece quality.
Next steps
Explore each model
Google's Imagen 3.0 text-to-image generation model, producing high-quality images with improved detail and lighting