Distilled version of Black Forest Labs' FLUX.2 [dev] outperforming it at a cheaper price. Developed by fal.ai.
Settled by community votes across 6 shared challenges, with an AI judge weighing in on each.
FLUX.2 [dev] Turbo
#3 of 62 in Text-to-Image
Imagen 3.0 Generate 002
#36 of 62 in Text-to-Image
Where the votes landed
FLUX.2 [dev] Turbo
0%
win rate
Ties
0%
Imagen 3.0 Generate 002
0%
win rate
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.”
AI Judge Analysis
FLUX.2 [dev] Turbo
- + Excellent text legibility and font choice.
- + High-quality, realistic food photography.
- + Professional layout with logical sectioning for a single menu page.
- − Nonsensical pricing (e.g., $260 for pizza).
- − The 'Mains' section overlaps awkwardly with the large pizza image.
Imagen 3.0 Generate 002
- + Strict adherence to the grid layout request.
- + Very clean, minimalist aesthetic that feels modern.
- + Good variety of food items shown in the photos.
- − Text is largely illegible/gibberish.
- − The repetitive use of 'Mains' and 'Pizza' headers throughout the grid becomes confusing rather than organized.
- − Photos feel a bit more repetitive/stock-like compared to Model A.
Verdict: FLUX.2 [dev] Turbo produces a much more functional menu with legible titles and descriptions, making it feel like a real design despite the bizarre pricing. Imagen 3.0 Generate 002 creates a more rigid grid that looks great at a distance, but the text is garbled and the organizational logic is repetitive. FLUX.2 is the winner for its superior text rendering and better food quality.
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.”
AI Judge Analysis
FLUX.2 [dev] Turbo
- + Perfect text rendering for all requested strings.
- + Excellent fiery starburst and glow effects that feel integrated.
- + High photorealistic texture on the meat patty and bun.
- − The 'sauce' in the air looks a bit like solid plastic loops.
Imagen 3.0 Generate 002
- + Clean exploded view of the burger components.
- + Good use of color and vibrancy.
- − Failed to render 'LIMITED TIME ONLY' correctly in the secondary message.
- − The starburst includes garbled, nonsensical text above the price.
- − The text lacks the 'fiery, glowing effect' specifically requested for all text elements.
Verdict: FLUX.2 [dev] Turbo followed the prompt instructions perfectly, particularly regarding the text content and the fiery aesthetic. Imagen 3.0 Generate 002 failed on the text accuracy and ignored the specific glowing, fiery requirement for the typography.
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.”
AI Judge Analysis
FLUX.2 [dev] Turbo
- + Excellent text rendering with near-perfect spelling and grammar.
- + Natural chalk textures including smudges and varying stroke opacity.
- + Authentic blackboard appearance with realistic lighting and a believable cafe background.
- − The date is not in cursive as requested in the prompt.
- − The 'Brown Butter' entry gets slightly repetitive with the price label placement.
Imagen 3.0 Generate 002
- + Successfully uses a more cursive-inspired script as requested.
- + Good framing of the chalkboard within a wooden border.
- − Significant spelling errors throughout the menu items such as 'Risottoo' and 'Octpsuin'.
- − Text looks like a digital overlay rather than authentic chalk on a board.
- − The layout is cluttered with repeated words and garbled text at the bottom.
Verdict: FLUX.2 [dev] Turbo significantly outperforms the other model by producing legible, accurately spelled text and a highly realistic chalk texture that feels integrated into the environment. Imagen 3.0 Generate 002 struggles with basic spelling and suffers from a 'digital font' look that violates the prompt's request for a realistic handwritten style.
The Reversed Rodeo
Text-to-Image“Horse riding astronaut in space — horse on top, not vice versa. Surreal, highly detailed, cinematic.”
AI Judge Analysis
FLUX.2 [dev] Turbo
- + Excellent level of detail on the space suit and horse's mane.
- + Dramatic cinematic lighting and high-quality planet rendering.
- + Strong dynamic composition with a sense of motion.
- − Failed the specific spatial instruction for the horse to be 'on top'.
- − Visible anatomy issues where the horse's back leg merges into the foreground clouds/mountain.
Imagen 3.0 Generate 002
- + Clean, ethereal lighting that matches the surreal prompt.
- + Detailed rendering of nebulas and star fields.
- + Realistic textures on the horse and astronaut gear.
- − Failed the specific spatial instruction for the horse to be 'on top'.
- − Composition is a bit static and centered compared to the other model.
Verdict: Both FLUX.2 [dev] Turbo and Imagen 3.0 Generate 002 failed the complex spatial constraint of placing the horse on top of the astronaut, instead defaulting to the common trope of an astronaut riding a horse. FLUX.2 [dev] Turbo creates a more cinematic and visually epic scene, though it contains some clipping artifacts in the lower-left corner.
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.”
AI Judge Analysis
FLUX.2 [dev] Turbo
- + Excellent PBR textures with realistic marbling on the fish and translucent rice grains.
- + Perfectly centered and bold typography that matches the prompt exactly.
- + High-quality lighting and shadow depth that give it a premium 3D render look.
- − The sushi and plate arrangement is slightly off-center compared to the text.
- − Includes a ginger garnish not specifically asked for, though it fits the theme.
Imagen 3.0 Generate 002
- + Stronger adherence to the 'cartoon' aspect of the prompt with soft, rounded modeling.
- + Text is placed top-center as requested.
- + Good isometric perspective and clean display base.
- − The textures are very flat and lack the 'realistic PBR' quality requested in the prompt.
- − The text and flag icon are shifted to the top-left rather than being centered at the top.
- − Lower level of detail in the rice and fish compared to the competition.
Verdict: FLUX.2 [dev] Turbo followed the prompt much more effectively, particularly regarding the 'realistic PBR materials' and 'bold' centered text. While Imagen 3.0 captured the cartoon aesthetic well, it failed to center the typography and lacked the material sophistication seen in the fish and rice of the FLUX image.
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.”
AI Judge Analysis
FLUX.2 [dev] Turbo
- + Excellent adherence to the 'tumbling' and 'chasing' aspect of the prompt with dynamic poses.
- + Stronger representation of god rays and sun backlighting.
- + Highly detailed dew droplets on the grass and flowers that add to the atmosphere.
- − The kitten's facial expression is slightly distorted and unnatural.
- − The golden retriever's paws seem to merge awkwardly into the fox kit.
Imagen 3.0 Generate 002
- + Superior anatomical accuracy and clarity in the facial features of all animals.
- + Beautiful, soft lighting that creates a very clean and wholesome vibe.
- + The fur texture is exceptionally soft and fluffy, matching the 'ultra-detailed' requirement.
- − The scene is more static and lacks the sense of active 'chasing' described in the prompt.
- − Distortion on the rabbit's hind legs/paws where it lies on its back.
Verdict: Both models followed the complex prompt well, but FLUX.2 [dev] Turbo captured the energy and movement of the scene better, highlighting the 'tumbling together' and 'chasing' keywords. However, Imagen 3.0 Generate 002 produced a higher-quality image in terms of clarity and facial rendering, avoiding the slightly creepy expressions found in the other model's kitten.
Explore each model
Google's Imagen 3.0 text-to-image generation model, producing high-quality images with improved detail and lighting