Head to head
Esc

Models · slot A

to navigate to pick

FLUX.1 [dev] Black Forest Labs ImagineArt 1.5 (Preview) Vyro AI

Settled by community votes across 7 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

ImagineArt 1.5 (Preview)

27.1 arena score

#5 of 62 in Text-to-Image

Vote tally

Where the votes landed

FLUX.1 [dev]

0%

win rate

Ties

0%

ImagineArt 1.5 (Preview)

0%

win rate

Shared challenges 7

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.1 [dev]
ImagineArt 1.5 (Preview)

AI Judge Analysis

FLUX.1 [dev]

  • + Extremely clean and modern aesthetic
  • + Realistic soft lighting through the glass edges
  • + Perfectly simple and elegant composition
  • The sphere appears to be floating mid-air inside the cube with no support
  • The plant is positioned more to the side than directly behind

ImagineArt 1.5 (Preview)

  • + Excellent handling of glass refraction and reflections
  • + Very realistic textures on the vintage book and wooden table
  • + Accurately places the plant behind the cube visible through the glass
  • The sphere is partially embedded in the bottom surface of the glass rather than just sitting inside
  • The top of the cube seems surprisingly liquid-like under the book

Verdict: Both models followed the complex spatial instructions well, but Image B (ImagineArt 1.5) captured the refraction of the background plant and the texture of the materials more realistically. While FLUX.1 [dev] produced a cleaner, more minimalist image, ImagineArt 1.5 felt more grounded in reality despite the minor clipping of the blue sphere.

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.1 [dev]
ImagineArt 1.5 (Preview)

AI Judge Analysis

FLUX.1 [dev]

  • + Excellent shallow depth of field and bokeh effects.
  • + Great composition that emphasizes the environment and weather.
  • + Realistic textures on the jacket and wet pavement.
  • The man is just holding the handlebars rather than actively 'repairing' the bike.
  • Lacks the skin detail requested compared to the competitor model.

ImagineArt 1.5 (Preview)

  • + Captures a more active 'repairing' gesture as requested.
  • + Incredible skin texture and detail on the subject's face and hands.
  • + Strong adherence to the 'imperfect framing' prompt with a tight, candid crop.
  • Noticeable anatomical issues with the hands and fingers.
  • The background cars lack the 'motion blur' requested, appearing static.
  • The bicycle's geometry and the way the tools are held are illogical.

Verdict: FLUX.1 [dev] produced a much more cinematic and aesthetically pleasing image with superior lighting and atmosphere, though the subject is not actively repairing the bike. ImagineArt 1.5 (Preview) adhered closer to the literal prompt elements like 'repairing' and 'skin texture' but failed on anatomical correctness and background motion blur. FLUX.1 [dev] is preferred for its overall realism and professional photographic quality.

Fantasy Warrior

Text-to-Image

“Close portrait of a battle-worn paladin in ornate engraved plate armor, hair braided with small beads, faint scars and dirt on the skin, warm torchlight reflecting off metal, shallow depth of field, bokeh sparks, lifelike eyes, highly detailed texture on leather straps and cloth underlayer.”

FLUX.1 [dev]
ImagineArt 1.5 (Preview)

AI Judge Analysis

FLUX.1 [dev]

  • + Excellent skin texture with realistic freckles and pores
  • + Vibrant and aesthetic bokeh sparks
  • + High quality rendering of the eyes
  • Missed the request for beads in the hair braids
  • Minimal visible scarring or 'battle-worn' characteristics
  • Lacks the requested engraved details on the armor plates

ImagineArt 1.5 (Preview)

  • + Successfully included beads in the hair braids and faint scars as requested
  • + Detailed engravings on the plate armor and visible leather strap textures
  • + Strong atmospheric lighting that accurately reflects torchlight on metal
  • The torch flame looks a bit like a 2D asset overlay
  • Chainmail and cloth textures are slightly less sharp than the facial features

Verdict: ImagineArt 1.5 (Preview) followed the prompt much more accurately, including specific details like the beads in the braids, engravings on the armor, and visible scarring to signify a battle-worn state. While FLUX.1 [dev] produced a cleaner and more aesthetically pleasing face, it failed on several key prompt instructions like the hair accessories and armor details.

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]
ImagineArt 1.5 (Preview)

AI Judge Analysis

FLUX.1 [dev]

  • + Excellent typography with clean, legible sans-serif fonts
  • + Professional graphic design layout with good use of white space
  • + High-quality, isolated food photography that matches a modern aesthetic
  • Failed to provide a grid-based food photo layout as requested
  • Text contains some gibberish characters and placeholder-like logic

ImagineArt 1.5 (Preview)

  • + Correctly followed the grid-based food photo layout request
  • + High-quality, appetizing food photography
  • + Diverse range of food visuals representing multiple menu segments
  • Typography is extremely blurry and completely illegible
  • Layout feels cramped with inconsistent font sizes and line weights
  • Text rendering is significantly lower quality than the images

Verdict: FLUX.1 [dev] produces a design that looks like a real professional menu with clean typography and balanced composition, though it missed the specific 'photo grid' instruction. ImagineArt 1.5 followed the grid layout prompt better but failed significantly on the execution of text, which is distorted and unreadable. FLUX.1 [dev] is the better choice for a usable graphic design template.

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]
ImagineArt 1.5 (Preview)

AI Judge Analysis

FLUX.1 [dev]

  • + Excellent soft, clay-like 3D miniature textures
  • + Accurate 45-degree isometric perspective
  • + Clean and minimal diorama base
  • Text includes a misspelling ('SUSH CATON')
  • Sushi variety is repetitive, using only salmon nigiri
  • The diorama base is slightly cut off at the bottom

ImagineArt 1.5 (Preview)

  • + High level of detail and variety in sushi types
  • + Perfect text rendering and alignment
  • + Strong contrast and realistic PBR materials
  • Text is placed in the top-right corner instead of top-center as requested
  • The diorama base includes visible aliasing artifacts along the edges
  • The garnish is more complex than the 'minimal' request

Verdict: FLUX.1 [dev] captures the 'miniature cartoon' aesthetic and isometric perspective much better than the competitor, though it fails on the specific text string requested. ImagineArt 1.5 (Preview) produces much higher quality sushi models and perfect text, but it misses the centering of the text and lacks the specific soft-toy/clay texture implied by the prompt, resulting in a slightly more generic render. Overall, FLUX.1 [dev] is preferred for its better adherence to the composition and stylistic vibe.

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.1 [dev]
ImagineArt 1.5 (Preview)

AI Judge Analysis

FLUX.1 [dev]

  • + Features a clean, minimalist vector aesthetic.
  • + Includes a balanced banner and cloche icon as requested.
  • Significant spelling errors in both the brand name and the word 'restaurant'.
  • Hallucinated random numbers like '11011' and '1941' which were not in the prompt.

ImagineArt 1.5 (Preview)

  • + Perfect text rendering for 'Caffè Florian' and 'Est. 1720'.
  • + Excellent application of subtle texture on the background.
  • + Stronger vector emblem style with professional gradients and composition.
  • The 'Est. 1720' text is placed on a curved shape rather than a traditional ribbon banner.

Verdict: ImagineArt 1.5 (Preview) is the clear winner because it correctly spelled the brand name, whereas FLUX.1 [dev] produced 'Café Flariláan'. ImagineArt 1.5 also exhibited better adherence to the 'subtle texture' and 'classic typography' requirements while avoiding the nonsensical numbers present in the other model's output.

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.”

FLUX.1 [dev]
ImagineArt 1.5 (Preview)

AI Judge Analysis

FLUX.1 [dev]

  • + Elegant layout with a professional aesthetic inspired by mid-century modern design.
  • + Excellently captures a navy-heavy color palette with subtle red accents.
  • + High-quality vector style lines and cohesive iconography.
  • Text rendering is mostly gibberish, failing to spell the specific mission steps correctly.
  • The infographic flow is circular and confusing, making it difficult to follow the logical sequence of the mission.

ImagineArt 1.5 (Preview)

  • + Strong text legibility for headers and mission steps with significant accuracy.
  • + Logic and flow of information are clear, moving sequentially from top to bottom.
  • + Captures the NASA-inspired color palette perfectly while maintaining a clean poster layout.
  • The 'Descent' icon is a satellite-like object rather than a lunar module.
  • Illustration style is slightly less refined compared to the competitor's cleaner minimalist vectors.

Verdict: While FLUX.1 [dev] produced a more sophisticated artistic design, it failed significantly on text legibility and semantic logic. ImagineArt 1.5 followed the prompt's logical steps much more effectively, providing readable and accurate labels for most of the mission phases, making it the superior infographic.

Next steps

Explore each model