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 13 shared challenges, with an AI judge weighing in on each.
FLUX1.1 [pro] Ultra
#49 of 62 in Text-to-Image
Qwen Image 2512
#30 of 62 in Text-to-Image
Where the votes landed
FLUX1.1 [pro] Ultra
0.0%
win rate
Ties
0.0%
Qwen Image 2512
100.0%
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 lighting instructions with a clear left-side window light source.
- + Photorealistic glass texture with accurate edge refraction and transparency.
- + Crisp text rendering on the book spine.
- − The blue sphere is levitating rather than resting on the bottom of the cube.
- − The sphere placement feels a bit centered and lacks some natural shadow interaction.
Qwen Image 2512
- + Realistic physics with the blue sphere resting on the base of the cube.
- + Effective use of reflections on the glass and the table surface.
- + High-quality wooden texture on the table.
- − The glass has a heavy teal tint that wasn't requested.
- − The plant in the background is less distinct through the glass compared to Model A.
- − The glass cube edges look more like a mirror box than a transparent glass cube in certain areas.
Verdict: FLUX1.1 [pro] Ultra produced a more aesthetically pleasing image with superior clarity and lighting, though the sphere was strangely levitating. Qwen Image 2512 managed the physics better by placing the sphere on the floor of the cube, but the glass was overly tinted and the overall composition felt darker. FLUX1.1 [pro] Ultra is the winner for its impressive photorealism and accurate response to the lighting prompt.
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 vehicles.
- + Sophisticated composition with realistic street reflections.
- + High mechanical accuracy in the bicycle's structure.
- − The character looks slightly more generic and less gritty than requested.
- − The man is standing rather than performing an active repair.
Qwen Image 2512
- + Outstanding natural skin texture and facial detail capturing an authentic 'candid' feel.
- + The character is actively crouching/working, fitting the 'repairing' prompt better.
- + Captured the 'imperfect framing' and 'shallow depth of field' very effectively.
- − Failed to include motion blur for the passing cars.
- − Anatomical issues with the man's hands/fingers upon closer inspection.
Verdict: FLUX1.1 [pro] Ultra produced a technically superior image with impressive motion blur and clean composition, but it felt a bit like a stock photo. Qwen Image 2512 captured the requested 'candid' essence and authentic Japanese street aesthetic much better, despite missing the motion blur requirement and having some hand artifacts. Qwen is preferred for its superior character detail and adherence to the 'no stylization' and 'candid' atmosphere.
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
- + Excellent adherence to the 'battle-worn' descriptor with realistic wounds and grime.
- + Superior lighting and depth of field, with beautiful bokeh and torchlight reflections.
- + Incredible texture detail on the leather straps and the fabric underlayer.
- − The hair braids are relatively simple compared to the other model.
Qwen Image 2512
- + Intricate hair braiding with clearly visible colored beads.
- + Highly detailed engraving on the gorget and plate armor.
- − Lighting feels slightly flatter and less cinematic than the competitor.
- − The 'battle-worn' elements like scars look a bit more like surface marks rather than integrated texture.
Verdict: FLUX1.1 [pro] Ultra is the winner due to its superior lighting, mood, and material textures, particularly the leather and cloth which look photorealistic. While Qwen Image 2512 does a great job with the specific detail of the beads in the hair and the armor engravings, it lacks the cinematic depth and convincing grit present in the FLUX output.
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 typographic hierarchy with clear section headers.
- + Professional and clean layout with realistic food photography.
- + Accurate rendering of the 'Pizza' and 'Mains' sections as requested.
- − Includes some gibberish text in the smaller descriptions.
- − The placement of some photos overlaps text slightly.
Qwen Image 2512
- + Strong grid layout for the food photos.
- + Vibrant color accents that align with the brand identity prompt.
- + Good overall balance between images and text blocks.
- − Significant spelling errors in every single header (e.g., 'Ressagrent', 'Piesmanets').
- − The font is stylized but lacks the professional 'bold sans-serif' clarity requested in the prompt.
Verdict: FLUX1.1 [pro] Ultra is the clear winner for its superior professional execution and legible typography, which are essential for a menu design. While Qwen Image 2512 followed the grid layout instructions well, it failed significantly on text rendering, producing garbled words for all major headers.
Magic Burger Explosion: Fiery Photorealism Challenge
Text-to-Image“Ad for 'Magic Burger'. Dynamic, exploded burger with all components (bun, patty, cheese, lettuce, tomato, sauce) suspended in mid-air. Emphasize photorealistic detail and a sense of motion. Dark, fiery background with glowing embers. Integrate text: 'MAGIC BURGER' as a prominent title, 'LIMITED TIME ONLY' as a secondary message, and '€6.99' in a starburst, all rendered with a fiery, glowing effect.”
AI Judge Analysis
FLUX1.1 [pro] Ultra
- + Crisp and clear text rendering throughout the image.
- + Excellent photorealistic textures on the burger buns and ingredients.
- + Strong lighting contrast between the glowing elements and the dark background.
- − Missed the starburst element for the price tag.
- − The burger composition is vertically repetitive with multiple stacked patties and lettuce layers.
- − Included unnecessary hallucinated text/watermarks at the bottom.
Qwen Image 2512
- + Included all requested design elements, including the starburst price tag.
- + Applied a more cohesive fiery, glowing effect to the typography.
- + The 'exploded' burger composition feels more dynamic and natural.
- − Missed the word 'TIME' in the 'LIMITED TIME ONLY' phrase.
- − The texture on the burger patty looks slightly less realistic compared to the other model.
Verdict: Qwen Image 2512 is the superior choice because it followed all layout instructions, including the specific starburst for the price and the fiery font style, while maintaining a very dynamic composition. FLUX1.1 [pro] Ultra produced a high-quality image with excellent clarity but failed on specific prompt details like the starburst and included undesirable text artifacts.
Chalkboard Menu
Text-to-Image“Handwritten-style chalkboard menu in a cozy café, all text rendered in the exact same realistic chalk handwriting style with natural variations in letter size, slight slant, and chalk texture — no printed or digital fonts anywhere on the board. Title at the top in elegant cursive chalk handwriting: ‘TODAY’S SPECIALS – APRIL 30, 2026’. Below it, three menu items also in the same handwritten chalk style: ‘Truffle Mushroom Risotto – $24’, ‘Grilled Octopus with Lemon & Herbs – $28’, ‘Brown Butter Chocolate Chip Cookies – $9’. At the very bottom, smaller text in the identical handwritten chalk style (slightly smaller but still clearly legible with the same handwriting characteristics): ‘All items made fresh daily • Ask about our gluten-free options’. Warm ambient café lighting, visible chalk dust and smudges, realistic handwriting imperfections, no clean printed text anywhere.”
AI Judge Analysis
FLUX1.1 [pro] Ultra
- + Excellent chalk texture on the board surface.
- + Realistic frame and lighting for a cafe setting.
- − Significant text errors and gibberish repetitions in the body text.
- − Failed to use the requested elegant cursive for the header.
- − Visible digital artifacting in the handwritten lines.
Qwen Image 2512
- + Perfect adherence to the elegant cursive requirement for the title.
- + High spelling accuracy and legibility for all menu items.
- + Consistent artistic style across all text elements.
- − Minor misspelling of 'Risotto' as 'Risitto'.
- − The text looks slightly overlayed rather than physically drawn with chalk in some areas.
Verdict: Qwen Image 2512 followed the complex text and styling instructions much better, delivering the requested cursive title and all menu items with minimal errors. FLUX1.1 [pro] Ultra struggled significantly with the text content, creating repetitive phrases and incoherent strings of letters despite having a more realistic chalk smudge texture.
The Reversed Rodeo
Text-to-Image“Horse riding astronaut in space — horse on top, not vice versa. Surreal, highly detailed, cinematic.”
AI Judge Analysis
FLUX1.1 [pro] Ultra
- + Excellent cinematic lighting and atmospheric perspective
- + Highly detailed background containing multiple celestial bodies and spacecraft
- + Dramatic dynamic pose of the horse
- − Failed the spatial reasoning instruction to put the horse on top of the astronaut
Qwen Image 2512
- + Strong clarity on the astronaut's face and suit details
- + Good texture on the horse's coat
- + Properly rendered horse tack and saddle
- − Failed the spatial reasoning instruction to put the horse on top of the astronaut
- − Less creative composition compared to the other model
Verdict: Both FLUX1.1 [pro] Ultra and Qwen Image 2512 failed to follow the specific surreal instruction of placing the horse on top of the astronaut, instead opting for the standard 'astronaut riding a horse' trope. FLUX1.1 [pro] Ultra is the better overall image due to its superior cinematic scale, better use of the background, and more more dynamic lighting.
The Capybara Taxi Driver
Text-to-Image“Photorealistic scene inside a yellow New York taxi at night. A capybara is driving, wearing a yellow taxi driver cap and a dark jacket. It has a calm, professional expression and both front paws on the steering wheel. In the back seat sits a human businesswoman in a coat, looking at her phone with a completely normal, bored expression (as if this is just another normal ride). Through the windows you can see the streets of Manhattan at night with blurred lights. Realistic taxi interior, photorealistic, detailed fur and fabric, 35mm lens, night lighting with reflections, shallow depth of field.”
AI Judge Analysis
FLUX1.1 [pro] Ultra
- + Excellent photographic lighting and depth of field
- + Highly detailed fur texture on the capybara
- + Clean and aesthetic composition through the side window
- − Failed the spatial logic of the prompt by placing the passenger in the front seat
- − Capybara's paws are not visible on the steering wheel
Qwen Image 2512
- + Strict adherence to spatial prompt instructions with the passenger in the back seat
- + Correctly depicted the capybara with paws on the steering wheel
- + Captures the requested 'bored' expression of the businesswoman well
- − Human-like hands/fingers on the capybara are slightly uncanny
- − The capybara's face looks a bit more digitally smoothed compared to Image A
Verdict: FLUX1.1 [pro] Ultra produces a more visually stunning, high-definition image, but it fails significantly on prompt instruction by placing the guest in the front seat and omitting the paws on the wheel. Qwen Image 2512 followed every specific detail of the prompt, including character placement and composition, making it the more accurate representation despite the slightly creepy anthropomorphic hands.
The Halloween Invitation
Text-to-Image“Vintage gothic Halloween party invitation. Dark parchment poster, spooky border with webs and thorns, central glowing jack-o-lantern, bats, twisted trees, moody night sky. Add elegant gothic title text saying "Halloween Party Invitation", a small scroll banner saying "You are invited to a night of frights", and event details at the bottom: Date: 30.10.2026 Time: 7pm Location: The Arches, NYC Spooky but polished, cinematic lighting, square format.”
AI Judge Analysis
FLUX1.1 [pro] Ultra
- + Excellent layout with a clear scroll parchment effect.
- + Accurate rendering of the event details and main title text.
- + Detailed thorny border and background atmosphere.
- − Includes redundant and misspelled text ('a noickt or a night of frights') below the scroll.
- − Missed the word 'Party' in the main title.
Qwen Image 2512
- + Atmospheric cinematic lighting with high visual quality.
- + Correctly includes the thorny border and spider web corners.
- + Follows the 'twisted trees' and 'moody sky' prompt instructions very well.
- − Glaring spelling error in the primary title ('Hallowern').
- − Layout feels a bit more cramped compared to the poster-style layout of the other model.
Verdict: FLUX1.1 [pro] Ultra provides a more functional invitation layout with better text legibility, though it suffers from redundant text hallucinations in the center. Qwen Image 2512 has superior artistic detail and lighting, but the significant spelling error in the main title ('Hallowern') makes it less usable for its intended purpose.
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 typography with a clean, modern aesthetic
- + Superior textural details on the salmon and rice grains
- + Minimalist and professional diorama presentation
- − Includes some unnecessary elements like the potted plant and steam
- − Text layout is slightly arched rather than straightforwardly bold
Qwen Image 2512
- + Highly accurate interpretation of the diorama base requested
- + Excellent text placement and bold font style
- + Colors are vibrant and follow the cartoon/miniature requirement well
- − The sushi toppings look slightly like plastic or clay rather than refined PBR materials
- − The flag icon is a bit large relative to the text
Verdict: Both models followed the complex prompt with high accuracy. FLUX1.1 [pro] Ultra produced a more refined, professional-looking image with superior lighting and textures, though it added a few extra scene elements. Qwen Image 2512 captured the 'miniature diorama' concept more literally but with slightly lower material fidelity; FLUX1.1 [pro] Ultra is the winner for its overall aesthetic quality and realistic PBR textures.
Adorable Baby Animals in Sunny Meadow
Text-to-Image“Hyper-photorealistic scene of fluffy baby animals—a golden retriever puppy, tabby kitten, baby bunny, and red fox kit—with big expressive eyes and ultra-detailed soft fur, playfully chasing butterflies and tumbling together in a lush wildflower meadow, warm golden sunrise light with god rays and dew sparkles, joyful wholesome vibe, 8K masterpiece.”
AI Judge Analysis
FLUX1.1 [pro] Ultra
- + Excellent soft lighting and bokeh effect
- + Whimsical, cohesive art style that fits the 'joyful vibe'
- + Distinct species representation that matches the 'baby' description well
- − Lean more towards a digital illustration style than 'hyper-photorealistic'
- − The paws and anatomy of the kitten and bunny are slightly simplified
- − Animals are sitting still rather than 'tumbling together'
Qwen Image 2512
- + Achieves a much higher level of photorealism in fur texture and lighting
- + Strong adherence to all species requested including the specific tabby markings
- + Very clear 'god rays' and dew sparkles as requested in the prompt
- − The fox looks more like a sub-adult than a 'baby kit'
- − The composition is a bit crowded with animals overlapping awkwardly
- − One butterfly appears to be floating unnaturally close to the kitten's head
Verdict: Qwen Image 2512 wins this challenge as it adheres much closer to the 'hyper-photorealistic' part of the prompt, delivering lifelike fur textures and realistic anatomy. FLUX1.1 [pro] Ultra produces a beautiful, charming image, but it feels more like a 3D animated film render than a masterpiece of photography.
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 that feels like a cohesive logo
- + Strong balance and clean circular composition
- + Accurately represents the warm brown and cream tones requested
- − Misspelled the primary brand name as 'Caffé Framilian'
- − The steam effect is very minimal compared to the other model
Qwen Image 2512
- + Perfect text rendering of 'Caffè Florian'
- + Detailed vintage engraving style on the cloche dome
- + Excellent interpretation of the steam and banner elements
- − Less like a 'logo' and more like an illustration
- − Shadowing under the cloche feels slightly detached from the text section
Verdict: While FLUX1.1 [pro] Ultra produced a more professional emblem layout, it failed significantly on the text by misspelling the brand name as 'Framilian'. Qwen Image 2512 followed all text instructions perfectly and provided a beautiful vintage aesthetic, making it the superior choice for this specific 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
FLUX1.1 [pro] Ultra
- + Excellent adherence to the NASA-inspired color palette.
- + Crisp, thin-line vector aesthetic that feels modern and professional.
- + Clean layout with a high-end infographic feel.
- − Text is largely illegible or nonsensical gibberish.
- − The numbered steps are disorganized and do not follow the requested chronological order.
- − Includes strange, unrelated icons like a profile silhouette and multiple conflicting rockets.
Qwen Image 2512
- + Successfully followed the specific numbered sequence of steps requested in the prompt.
- + Included a highly accurate Saturn V and Lunar Module illustration.
- + Very legible main headers and supporting names for the crew.
- − Several typos in secondary labels seperti 'Desceeint' and 'Translaurtcoit'.
- − The layout is somewhat cluttered with redundant numbering.
- − The style is a bit more illustrative and less like a 'flat vector' infographic compared to the other model.
Verdict: FLUX1.1 [pro] Ultra created a more visually stunning and stylistically accurate 'flat-vector' poster, but it failed significantly on information architecture and legibility. Qwen Image 2512 followed the complex instructions much better, correctly identifying the sequence of mission steps and providing recognizable lunar mission hardware, making it the more functional infographic despite some spelling errors.
Explore each model
Improved version of Alibaba's Qwen image model with better text rendering, finer natural textures, and more realistic human generation.