Head to head
Esc

Models · slot A

to navigate to pick

FLUX.1 [schnell] FP8 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 [schnell] FP8

19.0 arena score

#47 of 62 in Text-to-Image

Skill signature · Text-to-Image

ImagineArt 1.5 (Preview)

27.1 arena score

#6 of 62 in Text-to-Image

Vote tally

Where the votes landed

FLUX.1 [schnell] FP8

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 [schnell] FP8
ImagineArt 1.5 (Preview)

AI Judge Analysis

FLUX.1 [schnell] FP8

  • + Excellent object separation and geometric clarity
  • + Crisp, modern visual style with high resolution
  • + Highly accurate representation of thin glass and refraction
  • The glass object is more of a hollow rectangular prism than a perfect cube
  • The blue sphere appears to be floating on an internal shelf rather than centered inside

ImagineArt 1.5 (Preview)

  • + Realistic texture on the red book and wooden table
  • + Accurately places the plant behind the glass with convincing distortion
  • + Captures a warmer, more natural photographic aesthetic
  • The 'cube' has very thick, distorted walls and an irregular top edge
  • Optical physics of the sphere inside the glass are slightly muddled

Verdict: FLUX.1 [schnell] FP8 wins on composition and clarity, providing an exceptionally clean image that follows every prompt instruction with high fidelity. While ImagineArt 1.5 (Preview) offers more realistic textures—especially on the book's binding—the structural integrity of the glass cube and the overall lighting are superior in the FLUX.1 generation.

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 [schnell] FP8
ImagineArt 1.5 (Preview)

AI Judge Analysis

FLUX.1 [schnell] FP8

  • + Excellent cinematic lighting and bokeh.
  • + Captures the 'motion blur' request for passing cars effectively.
  • + Strong composition that feels like a professional street photograph.
  • The subject appears less clearly Japanese and more ethnically ambiguous.
  • The man is leaning on the bike rather than actively 'repairing' it as requested.
  • Lacks visible rain drops, relying only on wet surfaces.

ImagineArt 1.5 (Preview)

  • + Excellent skin texture and realistic portrayal of an elderly Japanese man.
  • + Highly accurate to the 'repairing' part of the prompt with specific hand tasks.
  • + Captures the 'imperfect framing' and 'shallow depth of field' very naturally.
  • Missing the 'motion blur from passing cars' as the background vehicles appear stagnant.
  • The red bicycle frame has some structural inconsistencies near the rear wheel.
  • Rain is subtly visible on the bike, but missing the general atmosphere of 'light rain' in the air.

Verdict: While FLUX.1 [schnell] FP8 produces a more aesthetically pleasing, cinematic image with great motion blur, ImagineArt 1.5 (Preview) is the winner due to its superior adherence to the 'repairing' action and its much more realistic, high-detail rendering of skin and ethnic features. ImagineArt 1.5 feels like a genuine candid snapshot, whereas FLUX.1 feels more like a generic movie still.

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 [schnell] FP8
ImagineArt 1.5 (Preview)

AI Judge Analysis

FLUX.1 [schnell] FP8

  • + Extremely high skin and hair texture detail
  • + Stunning cinematic lighting and color contrast
  • + Sharp focus on the eyes creates an intense portrait
  • Missed the request for braided hair
  • The 'ornate engraved plate' is partially obscured by the tight framing
  • Lighting feels slightly more artificial compared to Model B

ImagineArt 1.5 (Preview)

  • + Perfect adherence to specific details like braided hair and beads
  • + Excellent rendering of chainmail and engraved plate textures
  • + Captures the 'bokeh sparks' and 'warm torchlight' atmosphere more naturally
  • Slightly lower resolution on facial skin textures compared to model A
  • The torch is a bit distracting and positioned at the very edge of the frame

Verdict: While FLUX.1 [schnell] FP8 produced a more visually striking and sharper portrait, it failed to include the requested braids. ImagineArt 1.5 (Preview) adhered much better to all prompt instructions, including the intricate hair details, visible scars, and complex layers of armor and cloth, making it the more accurate and functional image for this specific request.

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 [schnell] FP8
ImagineArt 1.5 (Preview)

AI Judge Analysis

FLUX.1 [schnell] FP8

  • + Excellent text legibility and alignment
  • + Perfectly followed the 'white background' requirement
  • + Clean, professional layout that looks like a real menu mockup
  • Nonsense words in headers (e.g., 'Orceters', 'Seccer')
  • The 'pizza' section images are not all pizza

ImagineArt 1.5 (Preview)

  • + High-quality, realistic food photography
  • + Balanced distribution of images and text
  • + Sophisticated aesthetic suitable for upscale casual dining
  • Failed the 'white background' requirement by using heavy shadows and dark table backgrounds
  • Text is completely illegible and garbled
  • Layout feels more like a magazine spread than a functional menu

Verdict: FLUX.1 [schnell] FP8 is the clear winner for design utility as it produced a highly legible, clean, and professional layout that strictly adhered to the white background and minimalist prompt. ImagineArt 1.5 (Preview) produced beautiful photography, but it failed on several prompt constraints and the text was entirely unreadable.

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 [schnell] FP8
ImagineArt 1.5 (Preview)

AI Judge Analysis

FLUX.1 [schnell] FP8

  • + Excellent soft 3D cartoon aesthetic with gentle lighting.
  • + Clean isometric composition on a clear diorama base.
  • + High-quality PBR-like textures on the food items.
  • Failed the text generation significantly, repeating 'JAPAN' incorrectly.
  • Did not include the specific 'SUSHI' text requested.
  • Miniature scale feels slightly less detailed.

ImagineArt 1.5 (Preview)

  • + Correctly followed all text prompts including 'JAPAN' and 'SUSHI'.
  • + Accurate inclusion of the flag icon in a logical layout.
  • + Beautiful rendering of realistic textures and lighting for the sushi.
  • The text is placed in the corner rather than top-center as requested.
  • The '45° top-down' angle is slightly shallower than a standard isometric view.
  • Text styling (striped/outlined) differs from the 'bold' request.

Verdict: While FLUX.1 [schnell] FP8 captured the '3D cartoon' and 'isometric' aesthetic more accurately, its total failure to render the requested text makes it less useful. ImagineArt 1.5 (Preview) produced a higher detail image with successfully rendered text and a clear flag icon, fulfilling the complex prompt requirements more comprehensively.

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 [schnell] FP8
ImagineArt 1.5 (Preview)

AI Judge Analysis

FLUX.1 [schnell] FP8

  • + Strong minimalist vector aesthetic
  • + Includes all requested elements like the banner and steam swirls
  • + Good use of the specified warm brown and cream color palette
  • Significant spelling errors in the brand name ('AFe FLAMILAN')
  • The cloche is rendered more like an architectural dome
  • Uneven and messy typography layout

ImagineArt 1.5 (Preview)

  • + Perfect text rendering for 'Caffè Florian'
  • + Professional logo composition with a clear cloche icon
  • + Smooth gradients and high-quality vector-style execution
  • Missed the 'banner' requirement for the Est. 1720 text
  • Less 'minimalist' than requested due to the use of gradients and highlights

Verdict: ImagineArt 1.5 (Preview) is the clear winner because it correctly spelled the brand name 'Caffè Florian' and produced a professional, balanced logo. While FLUX.1 [schnell] FP8 captured the 'minimalist' and 'banner' aspects of the prompt better, its failure to spell the primary text correctly makes it unusable as a logo.

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 [schnell] FP8
ImagineArt 1.5 (Preview)

AI Judge Analysis

FLUX.1 [schnell] FP8

  • + Excellent adherence to the navy, white, and muted red color palette.
  • + Superior typography rendering for the main header.
  • Failed to provide distinct icons for each step, repeating basic circles and spheres.
  • Composition is disjointed with large amounts of empty space and confusing layout logic.

ImagineArt 1.5 (Preview)

  • + Strong iconography that follows the requested steps (Saturn V, orbit rings, lunar module).
  • + Excellent vertical infographic composition that feels like a real poster.
  • + Good integration of the crew names and landing site marker details.
  • Included a mock poster frame and wall background which was not requested.
  • Slight spelling errors in body text ('Aldrin' as 'Alderin', 'Landar Orbit').

Verdict: ImagineArt 1.5 (Preview) is the clear winner for its superior understanding of infographic structure and iconography. While FLUX.1 [schnell] FP8 followed the color palette well, it failed to produce the specific requested icons (like the Saturn V) and had a confusing layout, whereas ImagineArt 1.5 successfully mapped out the entire mission flow in a professional vector style.

Next steps

Explore each model