Black Forest Labs' ultra-high resolution image generation model, an enhanced version of FLUX1.1 [pro] optimized for premium quality output
Settled by community votes across 7 shared challenges, with an AI judge weighing in on each.
FLUX1.1 [pro] Ultra
#51 of 62 in Text-to-Image
ImagineArt 1.5 (Preview)
#6 of 62 in Text-to-Image
Where the votes landed
FLUX1.1 [pro] Ultra
0%
win rate
Ties
0%
ImagineArt 1.5 (Preview)
0%
win rate
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.”
AI Judge Analysis
FLUX1.1 [pro] Ultra
- + Excellent adherence to the glass cube geometry with sharp, realistic edges.
- + Perfectly captures the 'blue sphere' inside, even though it appears to be levitating.
- + High-quality textures on the red book and the wooden table.
- − The blue sphere is levitating rather than resting, which may look slightly surreal.
- − The plant visibility through the glass is a bit hazy and less defined than the rest of the scene.
ImagineArt 1.5 (Preview)
- + Features a more realistic, heavy glass material with complex refractions.
- + The blue sphere has a beautiful translucency that matches the lighting.
- + The textures and lighting on the wooden table are very warm and detailed.
- − The glass object is not a perfect cube, appearing more like a notched rectangular block.
- − Perspective issues where the book seems to be floating slightly above the glass surfaces.
- − The plant is mostly above/behind the cube rather than visible through the glass panels.
Verdict: FLUX1.1 [pro] Ultra followed the geometric requirements of the prompt much better, providing a clear and well-defined glass cube with a red book on top. While ImagineArt 1.5 (Preview) produced a more artistically interesting glass material with realistic caustic light effects, it failed to create a proper cube shape and had minor perspective errors with the red book.
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
FLUX1.1 [pro] Ultra
- + Excellent execution of long-exposure motion blur on passing traffic
- + Strong cinematic composition with beautiful reflections on the wet pavement
- + High overall image clarity and realistic lighting
- − The man isn't actually repairing the bicycle; he is just standing by it
- − The skin texture on the face is a bit smoothed over compared to the requested 'natural' look
ImagineArt 1.5 (Preview)
- + Superb adherence to the 'repairing' action and 'natural skin texture' prompt
- + Perfectly captures the 'imperfect framing' and 'candid' feel requested
- + Excellent fine details in the hands, wrinkles, and bicycle mechanics
- − Fails to include the 'motion blur from passing cars' entirely
- − The wet pavement is visible but lacks the cinematic reflections seen in Model A
Verdict: FLUX1.1 [pro] Ultra created a more aesthetically pleasing, cinematic image with great motion blur, but it failed to show the man actually repairing the bike. ImagineArt 1.5 (Preview) followed the specific details of the 'repairing' action and skin texture much better, capturing a more authentic candid moment despite missing the motion blur requirement. ImagineArt 1.5 feels more like a real street photograph, while FLUX1.1 feels like a high-budget 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.”
AI Judge Analysis
FLUX1.1 [pro] Ultra
- − Image failed to load or is a solid black frame.
- − Provided no visual information for evaluation.
ImagineArt 1.5 (Preview)
- + Excellent adherence to all prompt details including braided hair with beads, scars, and ornate engraving.
- + High-quality texture work on the leather straps and chainmail underlayer.
- + Effective use of warm torchlight and bokeh sparks for atmospheric depth.
- − The torch flame looks slightly disconnected from the wood texture.
Verdict: FLUX1.1 [pro] Ultra failed to generate a visible image, resulting in a black frame. ImagineArt 1.5 (Preview) produced a highly successful image that captured every element of the complex prompt, specifically the intricate texture of the paladin's gear and the specific hairstyle requested.
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
FLUX1.1 [pro] Ultra
- + Excellent typography with legible, relevant headings like 'Appetizers' and 'Mains'.
- + Professional mockup presentation with realistic shadows and paper texture.
- + Followed the grid layout and vibrant accent request perfectly.
- − Minor spelling errors in smaller text and subheadings.
- − The food photos are slightly repetitive, showing many similar pizzas.
ImagineArt 1.5 (Preview)
- + Good variety of food photography representing different courses.
- + Clean, structured grid that maximizes image usage.
- − Text is completely illegible and gibberish.
- − The layout lacks the 'bold sans-serif' and 'vibrant accents' requested in the prompt.
- − Low resolution on internal menu text making it look blurry and poorly generated.
Verdict: FLUX1.1 [pro] Ultra is the clear winner as it produced a highly professional and usable design mockup with legible headings and a clean, modern aesthetic. While ImagineArt 1.5 (Preview) provided better variety in the food photos, the text was entirely unreadable and it failed to incorporate the bold sans-serif styling requested in 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.”
AI Judge Analysis
FLUX1.1 [pro] Ultra
- + Excellent adherence to the 'cartoon scene' and 'miniature 3D' stylistic instructions
- + Perfectly clean typography and layout that feels like a professional 3D render
- + Superior lighting and texture quality that matches the 'soft refined' request
- − Includes a small bug-like detail on the board that was not requested
- − Slightly less variety in the sushi types compared to the other model
ImagineArt 1.5 (Preview)
- + Features a wider variety of realistic-looking sushi pieces
- + Followed the text and flag icon requirements clearly
- + Accurate isometric perspective on the diorama base
- − Text is forced into the top right corner instead of the requested top-center
- − Materials look a bit too oily/glossy, missing the 'soft refined' aesthetic
- − Text rendering is slightly messy with overlapping lines
Verdict: FLUX1.1 [pro] Ultra created a much more cohesive and aesthetically pleasing 3D miniature scene that felt intentional and high-quality. While ImagineArt 1.5 (Preview) provided more sushi variety, it failed to center the text and the overall lighting was somewhat harsh and less refined.
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
FLUX1.1 [pro] Ultra
- + Excellent vector emblem style with clean lines
- + High contrast and strong visual balance
- + Accurate interpretation of the vintage minimalist style
- − Misspelled the main text as 'Caffé Framilian'
- − The 'Est. 1720' is not on a banner as requested
ImagineArt 1.5 (Preview)
- + Perfect text rendering for 'Caffè Florian'
- + Includes subtle paper texture on the background as requested
- + Elegant script typography fits the cafe theme
- − The gradients on the cloche deviate from the 'minimalist vector' request
- − The 'Est. 1720' text is very small and lacks a prominent banner
Verdict: ImagineArt 1.5 (Preview) is the winner because it correctly spelled the name of the establishment, whereas FLUX1.1 [pro] Ultra introduced significant spelling errors ('Framilian'). While FLUX1.1 [pro] Ultra produced a cleaner vector aesthetic, ImagineArt 1.5 (Preview) followed the specific text requirements and texture details more reliably.
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
FLUX1.1 [pro] Ultra
- + Features a large, visually appealing composition with a moon-horizon base
- + Includes some legible headings like LAUNCH and EARTH ORBIT
- + Matches the NASA-inspired color palette perfectly
- − Step numbering is chaotic and non-sequential
- − Text block content is complete gibberish (e.g., THE ABOUT FING IF)
- − Iconography is inconsistent and contains significant artifacts
ImagineArt 1.5 (Preview)
- + Strict adherence to the 6-step logical flow requested
- + Significantly better text legibility including names of astronauts
- + Very clean flat-vector style with crisp lines
- − Minor spelling errors in labels (e.g., TRANSLACDIC, LANDAR)
- − The Saturn V rocket design is a bit simplified/stylized compared to real proportions
Verdict: ImagineArt 1.5 (Preview) is the clear winner as it successfully follows the logical sequence of the mission steps and maintains a clean, professional infographic layout. FLUX1.1 [pro] Ultra produces a larger image, but the content is disorganized, the numbering is nonsensical, and the text is mostly unreadable jargon.
Explore each model
Vyro AI's professional-grade text-to-image model delivering photorealistic output with accurate text rendering and typography precision for commercial workflows