Head to head
Esc

Models · slot A

to navigate to pick

FLUX.2 [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.2 [dev]

24.4 arena score

#19 of 48 in Text-to-Image

Skill signature · Text-to-Image

ImagineArt 1.5 (Preview)

27.0 arena score

#6 of 48 in Text-to-Image

Vote tally

Where the votes landed

FLUX.2 [dev]

44.4%

win rate

Ties

0.0%

ImagineArt 1.5 (Preview)

55.6%

win rate

44.4% 0.0% ties 55.6%
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.2 [dev]
ImagineArt 1.5 (Preview)
50% wins 0% ties 50% wins

AI Judge Analysis

FLUX.2 [dev]

  • + Perfect adherence to the complex spatial prompt of sitting on top of the cube.
  • + Excellent photographic lighting with soft window light correctly positioned.
  • + High-quality rendering of glass thickness and internal reflections.
  • The plant is slightly more blurred/abstracted than may be ideal.

ImagineArt 1.5 (Preview)

  • + Sharp textures on the book and wooden table surface.
  • + Vibrant colors and clear visibility of the plant behind the cube.
  • Failed negative spatial prompt; cube is on the book rather than book on the cube.
  • The perspective of the cube is slightly skewed and physically inconsistent.

Verdict: FLUX.2 [dev] followed every instruction perfectly, including the difficult spatial relationship of placing the book on top of the glass cube. ImagineArt 1.5 failed that primary instruction, placing the cube on the book instead, and lacked the sophisticated lighting and glass physics seen in the FLUX image.

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 [dev]
ImagineArt 1.5 (Preview)
50% wins 0% ties 50% wins

AI Judge Analysis

FLUX.2 [dev]

  • + Excellent execution of motion blur from passing cars
  • + Natural, lifelike skin texture and facial expression
  • + Beautiful reflections on the wet pavement that feel realistic
  • The bicycle frame geometry is slightly nonsensical and cluttered near the handlebars
  • The man appears to be sitting on the bicycle frame rather than kneeling beside it

ImagineArt 1.5 (Preview)

  • + Strong 'imperfect framing' choice with a close-up, candid feel
  • + Impressive detail on the rain droplets on the bicycle frame
  • + Action of repairing the chain is more clearly depicted
  • Failed to include the requested motion blur for passing cars
  • Skin texture looks slightly over-sharpened and metallic
  • The background cars are static and in focus despite the 'shallow depth of field' prompt

Verdict: FLUX.2 [dev] followed the technical camera instructions much better, delivering convincing motion blur and a 50mm cinematic aesthetic that feels truly candid. While ImagineArt 1.5 (Preview) had excellent macro details like rain droplets, it missed the key motion blur requirement and produced a less natural skin tone.

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.2 [dev]
ImagineArt 1.5 (Preview)
33% wins 0% ties 67% wins

AI Judge Analysis

FLUX.2 [dev]

  • + Excellent adherence to the 'beads' requirement with intricate detail in the braids.
  • + Superior rendering of the engraved plate armor and leather strap textures.
  • + Very clean, high-resolution facial features and realistic scars.
  • The character's expression and skin appear slightly too clean for a 'battle-worn' paladin.

ImagineArt 1.5 (Preview)

  • + Stronger interpretation of the 'battle-worn' descriptor with visible skin texture, deeper wrinkles, and more dirt.
  • + Effective lighting and atmosphere with a more prominent, realistic torch.
  • + Good use of depth of field and bokeh sparks in the background.
  • The beads in the hair are less prominent and somewhat lost in the dark shadows.
  • The armor engraving is slightly less sharp and the metal texture feels more simplified compared to the other model.

Verdict: FLUX.2 [dev] produces a much cleaner and more intricate image, particularly in the details of the armor engravings and the beads within the braids, though the character looks a bit too young and fresh for the 'battle-worn' prompt. ImagineArt 1.5 (Preview) captures the mood and the 'worn' aesthetic better through realistic skin textures and more dramatic lighting, but lags behind in the fine detail of the materials. FLUX.2 [dev] is the winner for its superior technical execution of the complex prompt requirements.

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 [dev]
ImagineArt 1.5 (Preview)

AI Judge Analysis

FLUX.2 [dev]

  • + Excellent typography with clean, legible sans-serif fonts and bold headings.
  • + The grid layout is professionally structured and adheres perfectly to the requested sections (Appetizers, Pizza, Mains).
  • + Colors are used effectively as accents to separate categories.
  • Nonsense text and some spelling errors in headers (e.g., 'PIZZAU').

ImagineArt 1.5 (Preview)

  • + High-quality food photography with sophisticated plating.
  • + Good use of white space and a clean minimalist aesthetic.
  • Text is almost entirely illegible scribbles rather than fonts.
  • The layout is less structured, with sections feeling disconnected or poorly labeled.
  • Ignored the specific section requirements like 'Pizza' headings.

Verdict: FLUX.2 [dev] is the clear winner because it successfully creates a functional menu layout with the requested categories and a bold, professional design. While the text is mostly placeholder gibberish, it maintains the visual integrity of a real document, whereas ImagineArt 1.5 (Preview) fails to produce readable text or follow the specific structural requirements of the prompt.

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 [dev]
ImagineArt 1.5 (Preview)

AI Judge Analysis

FLUX.2 [dev]

  • + Perfect adherence to text placement and formatting instructions.
  • + Clean, professional 3D isometric execution on a raised diorama base.
  • + High-quality PBR material textures on the sushi and wasabi.
  • The sushi variety is a bit limited compared to typical platters.

ImagineArt 1.5 (Preview)

  • + Excellent variety of sushi types and vibrant colors.
  • + Good glossy reflections on the fish textures.
  • Text is placed in the corner instead of 'top-center'.
  • Japanese flag icon is incorrectly placed and merged with the text block.
  • The plate and diorama base have some clipping/alignment issues at the edges.

Verdict: FLUX.2 [dev] followed every instruction perfectly, specifically the 'top-center' text placement and the clean isometric diorama aesthetic. ImagineArt 1.5 (Preview) produced more visually diverse sushi but failed on the layout requirements, putting the text in the corner and exhibiting minor rendering artifacts.

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 [dev]
ImagineArt 1.5 (Preview)

AI Judge Analysis

FLUX.2 [dev]

  • + Excellent typography including the requested accent mark on 'Caffè'.
  • + Clean vector emblem style with appropriate minimalist illustration.
  • + Strict adherence to the banner and 'Est. 1720' request.
  • The subtle texture on the background is very sparse.

ImagineArt 1.5 (Preview)

  • + Elegant script typography and warm color palette.
  • + Good use of shadows and highlights on the cloche to give it depth.
  • + Pleasant parchment-like texture on the background.
  • Missed the 'Est. 1720' banner, placing the text in a simple line instead.
  • The composition feels slightly crowded within the circular frame.
  • The 'E' in 'Est.' is partially obscured or stylistically thin.

Verdict: FLUX.2 [dev] followed the prompt more accurately, successfully incorporating both the banner and the specific accent mark on 'Caffè'. While ImagineArt 1.5 (Preview) produced an aesthetically pleasing design, it failed to include the requested banner element and had less precise typography.

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.2 [dev]
ImagineArt 1.5 (Preview)

AI Judge Analysis

FLUX.2 [dev]

  • + Stronger vector art style with high-quality illustrations of the Saturn V and Lunar Module.
  • + Good use of the requested NASA color palette.
  • + Includes high-quality crew names in the top right header.
  • The layout is a disorganized grid rather than a sequential process.
  • Icons and text labels are mixed up and do not follow the numerical order of the prompt.
  • Contains significant text rendering errors such as 'UALSIST ORDIT' and 'LTUREST LIAMDIIES'.

ImagineArt 1.5 (Preview)

  • + Excellent composition that follows a logical, connected flow of mission stages.
  • + Much cleaner text rendering for the main titles and labels.
  • + Stronger adherence to the 'infographic poster' concept with a vertical layout and clear connections.
  • The Saturn V rocket illustration is very simplified and slightly inaccurate.
  • Some minor spelling errors like 'LANDAR' and 'ALDERIN'.
  • Icons are less detailed than those in the competing model.

Verdict: ImagineArt 1.5 (Preview) is the winner because it actually functions as an infographic, providing a clear sequential layout and readable text that follows the logic of the mission. FLUX.2 [dev] produced higher quality individual icons and better crew names, but failed completely on the layout, resulting in a confusing grid where the labels and images do not match the stages requested.

Next steps

Explore each model