FLUX.2 [max] vs ImagineArt 1.5 (Preview)
Head-to-head across 9 challenges
FLUX.2 [max]
66.7%
win rate
Ties
11.1%
ImagineArt 1.5 (Preview)
22.2%
win rate
Challenge Results
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.”
AI Judge Analysis
FLUX.2 [max]
- + Excellent adherence to depth of field and motion blur requirements.
- + Highly realistic skin texture and clothing details with convincing rain droplets.
- + Superior background bokeh and atmospheric lighting that feels cinematic.
- − The character's hands are slightly merged with the bicycle frame.
- − The bicycle's mechanical structure is a bit simplified/distorted near the front wheel.
ImagineArt 1.5 (Preview)
- + Captures the 'imperfect framing' and 'candid' feel with a close-up, awkward angle.
- + Clearer rendering of raindrops on the bicycle frame.
- − Lacks the requested motion blur on the passing car.
- − The subject's face has a slightly 'plastic' AI sheen compared to Model A.
- − The bicycle's pedal and kickstand geometry is nonsensical and warped.
Verdict: FLUX.2 [max] is the clear winner as it successfully captured the complex technical requirements of the prompt, specifically the 50mm shallow depth of field and the motion blur of the passing cars. While ImagineArt 1.5 (Preview) attempted a more intimate angle, the lighting feels flat and it failed to generate any motion blur, resulting in a less cinematic image.
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 [max]
- + Strictly followed the requested sections for Appetizers, Pizza, and Mains.
- + Excellent text rendering with clear, legible headings and consistent prices.
- + Highly organized grid layout with professional alignment and vibrant color accents.
- − The 'Appetizers' section contains several images of pizza, which is redundant.
- − Small descriptive text below titles is nonsensical filler.
ImagineArt 1.5 (Preview)
- + High-quality, artistic food photography with good color and depth.
- + Captures a sophisticated minimalist aesthetic for a high-end casual dining vibe.
- − Failed to include the specific requested categories (Appetizers/Pizza/Mains).
- − Text is completely illegible and garbled throughout the menu.
- − Visual layout is cluttered and the grid logic is inconsistent.
Verdict: FLUX.2 [max] is the clear winner as it produced a functional, professionally designed menu with clear headings for all requested sections and legible prices. In contrast, ImagineArt 1.5 (Preview) produced illegible text and failed to follow the specific category instructions, despite having high-quality photography.
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.”
AI Judge Analysis
FLUX.2 [max]
- + Perfect adherence to the spatial requirements, placing the book on top of the cube.
- + High realism in light behavior, including reflections and caustics on the tabletop.
- + Excellent texture work on the book cover and wood grain.
- − The glass box has an open or thin-walled design rather than a solid block, though this is a valid interpretation.
ImagineArt 1.5 (Preview)
- + Good photographic quality and Sharpness.
- + Successfully includes all requested elements (sphere, cube, plant, book).
- − Failed the spatial prompt by putting the cube on top of the book.
- − The sphere appears to be hovering or embedded in a solid glass block without clear internal physics.
Verdict: FLUX.2 [max] followed the complex spatial instructions perfectly, accurately placing the book on top of the cube and providing high-quality lighting that feels natural. ImagineArt 1.5 (Preview) produced a sharp image but failed the primary prompt instruction by placing the cube on top of the book instead of the other way around.
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 [max]
- + Perfect text rendering and alignment according to instructions.
- + Very clean isometric composition with a balanced diorama base.
- + Soft, appealing 3D cartoon textures that look professional.
- − The sushi models are slightly more simplified than Model B’s.
ImagineArt 1.5 (Preview)
- + Excellent PBR-style material rendering on the fish and rice grains.
- + Creative interpretation of the isometric text in 3D.
- − Text contains a spelling error ('SUSHN' instead of 'SUSHI').
- − The composition feels slightly cramped with the large text overlapping the scene.
Verdict: FLUX.2 [max] followed the prompt's layout instructions perfectly, providing clean, legible text and a well-centered diorama. While ImagineArt 1.5 (Preview) had more detailed textures on the food itself, it failed on the text spelling and the overall balance of the composition.
Victorian Greenhouse Oasis
Text-to-Image“Hyper-photorealistic interior of a lush Victorian glass greenhouse filled with exotic tropical plants, vibrant blooming orchids, tall ferns, colorful butterflies in flight, sunlight filtering through ornate glass roof creating realistic caustics and dew on leaves, intricate iron framework visible, misty atmosphere, 8K masterpiece.”
AI Judge Analysis
FLUX.2 [max]
- + Excellent depiction of misty atmosphere and light rays
- + Highly intricate and accurate Victorian ironwork
- + Abundant and diverse floral arrangement matching the orchid request
- − Butterflies feel more like flat stickers placed on top of the image
- − The composition feels a bit crowded with two identical benches
ImagineArt 1.5 (Preview)
- + Stronger focus on dew droplets on leaves in the foreground
- + Better sense of spatial depth and architectural scale
- + Superior rendering of light god-rays coming through the entrance
- − One butterfly is significantly oversized and lacks realism
- − The archway structure is slightly asymmetrical and warped in the center
Verdict: Both models captured the prompt's complexity well, but ImagineArt 1.5 (Preview) produced a more dynamic composition with better depth and more realistic dew on the foliage. FLUX.2 [max] excelled at the architectural detail and atmospheric mist, but was let down by the somewhat artificial appearance of the butterflies and a repetitive foreground layout.
Heroic Super Hero Portrait
Text-to-Image“Hyper-photorealistic full-body portrait of a female superhero standing triumphantly on a New York skyscraper rooftop at golden sunset, wearing a classic modest superhero costume with flowing cape, chest emblem, gloves, and boots in red and blue colors, practical design, short hair, strong determined heroic expression looking into the distance, powerful confident stance with hands on hips and cape billowing dramatically in the wind, detailed urban cityscape background, warm natural sunlight with sharp shadows and fabric highlights, ultra-sharp textures on suit, hair, and concrete, 8K masterpiece, empowering family-friendly style.”
AI Judge Analysis
FLUX.2 [max]
- + Excellent low-angle composition that enhances the heroic feel
- + Superior cinematic lighting and atmospheric depth in the cityscape
- + Very realistic fabric textures and high-quality skin rendering
- − The cape physics feel a bit heavy and less 'billowing' than requested
ImagineArt 1.5 (Preview)
- + Direct eye contact and clear heroic expression
- + The cape has a more dramatic, wind-swept motion
- + Detailed cityscape with a clear view of the horizon
- − Lighting feels a bit flat and artificial compared to Model A
- − Anatomical issues where the hands meet the hips/waist
- − Less 'hyper-photorealistic' overall with some digital smoothing on the face
Verdict: FLUX.2 [max] creates a much more cinematic and believable image with professional-grade lighting and a superior low-angle composition that fits the 'triumphant' prompt. While ImagineArt 1.5 (Preview) captures the dramatic cape movement well, it suffers from anatomical inconsistencies and lacks the realistic depth and texture found in FLUX.2 [max].
Intricate Floral Mandala
Text-to-Image“Perfectly symmetrical mandala made entirely of real flowers, petals, leaves, fruits, and seeds in vibrant natural colors, intricate layered patterns with radial symmetry, top-down view on a soft neutral background, hyper-detailed organic textures and subtle shadows, photorealistic, 8K masterpiece.”
AI Judge Analysis
FLUX.2 [max]
- + Excellent adherence to radial symmetry
- + Sophisticated use of lighting and subtle shadows creating depth
- + Very clean and professional composition on a neutral background
- − Individual elements like fruits and petals have a slightly uniform, illustrated texture
- − The 'real fruit' components (orange slices) appear repeated and a bit flat
ImagineArt 1.5 (Preview)
- + Very realistic and diverse organic textures for seeds, fruits, and petals
- + Rich and vibrant color palette with high contrast
- + Great inclusion of small details like seeds and diverse plant species
- − Significant symmetry errors, especially in the outer rings
- − The background is cluttered with rocks and wood, ignoring the 'neutral background' prompt
- − Slightly cropped at the edges, losing the full circular mandala effect
Verdict: FLUX.2 [max] produced a much more successful mandala with near-perfect symmetry and a clean, professional layout that matched the requested 'neutral background.' While ImagineArt 1.5 (Preview) had more realistic individual textures for the seeds and fruits, it failed on the core requirement of 'perfectly symmetrical' and included busy background elements that were not requested.
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.”
AI Judge Analysis
FLUX.2 [max]
- + Perfect text rendering including the accent on 'Caffè'
- + Superior minimalist vector style that feels clean and professional
- + The cloche and steam are illustrated with elegant, simple lines
- − The 'Est. 1720' text is slightly off-center within the banner
ImagineArt 1.5 (Preview)
- + Strong vintage woodcut aesthetic with good contrast
- + Includes all requested elements like the banner and cloche
- − Steam is placed awkwardly below the cloche instead of rising from it
- − Text is slightly cramped within the circular frame
- − Background lacks the requested subtle texture
Verdict: FLUX.2 [max] produced a high-quality, professional-grade logo that perfectly adheres to the minimalist vector request, including accurate accent marks on the text. ImagineArt 1.5 (Preview) has a nice vintage style but fails on the logic of the steam (placing it under the dome) and lacks the subtle paper texture mentioned in the prompt.
Apollo 11: Journey to Tranquility
Text-to-Image“Create a clean, modern vector infographic poster about the Apollo 11 mission. NASA-inspired palette (navy, white, muted red, light gray). Flat-vector style, crisp lines, consistent iconography, subtle gradients only. Steps (stop at landing): 1. Launch (Saturn Vicon) 2. Earth Orbit (Earth + orbit ring icon) 3. Translunar (trajectory arc icon) 4. Lunar Orbit (Moon + orbit ring icon) 5. Descent (lunar module descending icon) 6. Landing (lunar module on the surface icon) Small supporting elements (minimal text): • Crew strip: three silhouette icons with only last names: Armstrong, Aldrin, Collins. • Landing site marker: Moon pin labeled "Tranquility" only. Layout constraints: generous margins, large readable labels, clean background with subtle stars. Vector-only, print-poster look, high resolution.”
AI Judge Analysis
FLUX.2 [max]
- + Excellent text rendering with no spelling errors for main headings and crew names.
- + Very clean, modern vector aesthetic that aligns perfectly with the 'flat-vector' request.
- + Higher logical consistency in icons, accurately representing the stages in separate, organized frames.
- − The sequence of steps is non-linear and confusing (Lunar Orbit is third, then Translunar is fourth).
- − Minor typo in 'Tranquiity'.
ImagineArt 1.5 (Preview)
- + Great use of a continuous trajectory line to show movement through the stages.
- + Strong color palette adherence with a very 'NASA' feel.
- + Good composition with a clear sense of vertical progression.
- − Multiple spelling errors including 'TRANCLUTAL' and 'ALERIN'.
- − Includes five silhouettes for the crew instead of the historical three (Armstrong, Aldrin, Collins).
- − The iconography is less distinct, with several planets/moons looking identical.
Verdict: FLUX.2 [max] is the winner due to its superior image clarity, highly accurate text rendering, and professional vector style that looks like a finished infographic. While ImagineArt 1.5 (Preview) has a more dynamic layout with its red trajectory line, it fails on basic details like the number of crew members and suffers from significant spelling errors.
FLUX.2 [max]
Black Forest Labs' flagship image generation model delivering state-of-the-art quality with exceptional realism, precision, and consistency for both text-to-image and advanced image editing
ImagineArt 1.5 (Preview)
Vyro AI's professional-grade text-to-image model delivering photorealistic output with accurate text rendering and typography precision for commercial workflows