Black Forest Labs' precision image generation model with maximum control, reliable text rendering, and complete creative control supporting up to 4MP output
Settled by community votes across 6 shared challenges, with an AI judge weighing in on each.
FLUX.2 [flex]
25.2
arena score
#13 of 44 in Text-to-Image
Skill signature
Not enough comparable category data
The chart appears once both models have ratings across at least three shared arena categories.
Qwen Image 2512
22.4
arena score
#26 of 44 in Text-to-Image
Vote tally
Where the votes landed
FLUX.2 [flex]
55.6%
win rate
Ties
22.2%
Qwen Image 2512
22.2%
win rate
55.6%
22.2% ties
22.2%
Shared challenges
6
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.2 [flex]
Qwen Image 2512
100% wins
0% ties
0% wins
AI Judge Analysis
FLUX.2 [flex]
- + Excellent adherence to spatial layout and lighting instructions.
- + High visual clarity and clean rendering of the cube and book.
- + Realistic depth of field with the plant correctly positioned behind the glass.
- − The sphere is quite large, pushing the definition of 'small' in the prompt.
Qwen Image 2512
- + Realistic texture on the book cover and wooden table.
- + The scale of the 'small' sphere is more accurate relative to the cube.
- − Confusing glass physics where the back panels look more like mirrors than transparent glass.
- − The plant is significantly less visible through the glass compared to Model A.
Verdict: FLUX.2 [flex] produced a much clearer and more logically coherent image, where the plant is distinctly visible through the transparent glass cube as requested. Qwen Image 2512 struggled with the transparency of the cube, making the internal surfaces look mirrored and obscuring the plant behind it.
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.2 [flex]
Qwen Image 2512
0% wins
0% ties
100% wins
AI Judge Analysis
FLUX.2 [flex]
- + Excellent adherence to the motion blur and candid photography request
- + Realistic skin textures and clothing details
- + Effective use of shallow depth of field and bokeh
- − The anatomy of the bicycle is slightly nonsensical with the rear wheel and pedal arrangement
- − The man is kneeling directly on the wet pavement which looks a bit unnatural
Qwen Image 2512
- + Very realistic facial features and skin texture
- + Strong composition with a focus on the subject's expression
- + Better bicycle anatomy compared to the competitor
- − Missed the 'motion blur from passing cars' instruction; the cars in the background are stagnant
- − The man is posing for the camera rather than 'repairing' the bike as requested
Verdict: FLUX.2 [flex] followed the prompt's technical requirements much better, successfully incorporating the motion blur and the action of repairing the bike, though the bike's structure is flawed. Qwen Image 2512 produced a high-quality portrait, but the subject is stationary and posing, ignoring the specific request for a candid repair scene with motion-blurred cars. FLUX.2 [flex] is the winner for its superior prompt adherence and atmospheric storytelling.
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.2 [flex]
Qwen Image 2512
50% wins
50% ties
0% wins
AI Judge Analysis
FLUX.2 [flex]
- + Excellent text rendering with clear, legible English words.
- + Clean, professional typography using the requested bold sans-serif fonts.
- + Consistent and high-quality food photography that fits the grid layout.
- − The 'Appetizers' section contains photos but no corresponding text menu items.
- − Repeats nearly identical pizza/steak images in the grid.
Qwen Image 2512
- + Dynamic grid layout with a good variety of colorful food images.
- + Bold use of color accents and icons to denote different sections.
- + Includes a larger focal image at the bottom for visual interest.
- − Poor text rendering with many gibberish words and spelling errors.
- − The typography feels cluttered and less professional compared to a real menu.
- − Price formatting is inconsistent and unrealistic.
Verdict: FLUX.2 [flex] produced a much more usable and professional design with legible text and a clean minimalist aesthetic. While Qwen Image 2512 had an interesting layout with more color, its failure to render coherent English text or realistic pricing makes it less effective as a design asset.
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.2 [flex]
Qwen Image 2512
AI Judge Analysis
FLUX.2 [flex]
- + Perfect text rendering and alignment.
- + Ultra-clean minimalist aesthetic exactly matching the prompt.
- + High-quality, soft 3D cartoon textures.
Qwen Image 2512
- + Intricate diorama base with organic details like grass and leaves.
- + Playful custom typography style.
- + High level of detail on the sushi pieces themselves.
- − The flag icon is skewed and placed awkwardly next to the text.
- − Text is not centered perfectly as requested.
- − The diorama base has slight texture inconsistencies for a 'clean' look.
Verdict: FLUX.2 [flex] produced an exceptionally clean and balanced image that adhered perfectly to every technical instruction, including centering and text placement. Qwen Image 2512 offered more creative flair in the diorama base but struggled with the specific layout and icon placement requested in the prompt.
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.2 [flex]
Qwen Image 2512
67% wins
33% ties
0% wins
AI Judge Analysis
FLUX.2 [flex]
- + Excellent depiction of movement and playfulness as requested
- + Includes all four specified animals with distinct, proportional sizes
- + Beautiful environmental lighting with clear god rays and atmospheric depth
- − The fox's front right leg has a slightly unnatural anatomy
- − Some butterflies appear to be floating stamps without much depth
Qwen Image 2512
- + Very high detail in fur texture and facial expressions
- + Strong character interaction with animals huddling together
- + Accurate butterflies and sharp foreground rendering
- − Fails to capture the 'playfully chasing' and 'tumbling' aspect of the prompt
- − The composition feels a bit cramped and posed like a studio portrait
- − The golden retriever's head is disproportionately large compared to the other animals
Verdict: FLUX.2 [flex] is the winner because it successfully captures the dynamic action of the prompt, showing the animals chasing butterflies and tumbling in a wide meadow. While Qwen Image 2512 has slightly sharper textures, it ignored the 'chasing' and 'tumbling' instructions in favor of a static, posed group portrait where the scale of the animals feels inconsistent.
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.2 [flex]
Qwen Image 2512
0% wins
0% ties
100% wins
AI Judge Analysis
FLUX.2 [flex]
- + Perfect adherence to the 'minimalist' and 'vector emblem' descriptors.
- + Clean, professional execution of the typography and icon.
- + Extremely accurate rendering of text and the requested banner element.
- − Steam effect is very subtle and simple compared to the other elements.
- − The banner styling is slightly generic.
Qwen Image 2512
- + Excellent artistic detail and shading on the cloche.
- + Beautiful, dynamic steam interpretation.
- + Strong vintage aesthetic with high-quality cross-hatching textures.
- − Fails the 'minimalist' requirement with its complex shading.
- − Typography is a bit heavy, and the letter 'a' in 'Florian' has some slight structural weirdness.
- − Large, ornate steam clouds might be too busy for a standard logo.
Verdict: FLUX.2 [flex] perfectly captures the 'minimalist vector emblem' request, resulting in a logo that is clean, professional, and ready for use. Qwen Image 2512 produces a much more detailed and visually striking illustration with beautiful textures, but it ignores the 'minimalist' constraint and is less successful as a practical logo design.
Next steps
Explore each model
Improved version of Alibaba's Qwen image model with better text rendering, finer natural textures, and more realistic human generation.