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
#53 of 62 in Text-to-Image
Qwen Image 2.0
#34 of 62 in Text-to-Image
Where the votes landed
FLUX1.1 [pro] Ultra
0%
win rate
Ties
0%
Qwen Image 2.0
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 photorealism and high texture detail on the book and glass edges.
- + Perfect adherence to spatial prompts, including object placement and visibility through glass.
- + Natural and soft window lighting that creates a realistic atmosphere.
- − The sphere is floating unnaturally in the center without any clear support.
Qwen Image 2.0
- + Strong materiality with realistic wood grain and high-quality glass reflections.
- + Good adherence to the requested color palette and object arrangement.
- − The sphere appears duplicated or reflected incorrectly on the side panels in a confusing way.
- − The plant visibility through the glass is slightly muddy compared to the background.
Verdict: FLUX1.1 [pro] Ultra is the winner due to its superior clarity and flawless execution of the request, particularly in how the plant is refracted through the glass cube. While both models struggled with the physics of the sphere (making it float), FLUX1.1 [pro] Ultra produced a cleaner, more professional-looking photograph with better lighting and texture.
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 the passing vehicle.
- + Strong cinematic lighting and high-quality wet pavement reflections.
- + Accurately represents the 50mm lens feel with a balanced composition.
- − The man's posture is more of 'holding' than 'repairing' the bike.
- − The man's feet and the bike frame appear slightly disconnected from the ground plane.
Qwen Image 2.0
- + Superb interpretation of 'candid' street photography with a realistic, unposed feel.
- + Exceptional skin texture and facial details that feel natural and non-AI-generated.
- + Accurate 'imperfect framing' that mimics a real photographer's snapshot.
- − Missed the 'motion blur' requirement for the passing cars.
- − The hands and bike chain area have some minor structural clipping/clutter.
Verdict: FLUX1.1 [pro] Ultra produces a more visually striking, cinematic image with high-quality effects like motion blur and reflections. However, Qwen Image 2.0 captures the spirit of the prompt's 'candid' and 'no stylization' requirements much better, providing a photo that looks like a genuine documentary shot despite missing the motion blur instruction.
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 photographic quality and skin texture realism
- + Subtle and sophisticated use of bokeh sparks and warm lighting
- + High-fidelity rendering of the braided hair and small beads
- − The 'battle-worn' scars are extremely faint and hard to see
- − The image has a slightly generic 'high-fantasy' stock photo aesthetic
Qwen Image 2.0
- + Character design feels more hardened and battle-worn
- + Bold use of color in the beads and eyes adds character
- + Compositional use of flame provides a strong thematic background
- − Texture on the leather pauldrons looks a bit muddy and low-detail
- − Historical/ornate accuracy is lower compared to Model A
- − Hand anatomy on the sword hilt is slightly awkward and lacks fine detail
Verdict: FLUX1.1 [pro] Ultra produced a superior technical image with incredibly lifelike skin textures and clean lighting that perfectly followed the technical aspects of the prompt. While Qwen Image 2.0 did a great job capturing the 'battle-worn' mood with more visible scars and fire, its overall rendering quality was slightly coarser, particularly on the armor and hand 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.”
AI Judge Analysis
FLUX1.1 [pro] Ultra
- + Excellent presentation of the menu as a physical mockup with realistic shadows
- + Clean, professional layout that looks like a real restaurant brochure
- + Clear, bold sans-serif header typography
- − Text in the body is nonsensical gibberish
- − The food images are cluttered and some are cut off awkwardly
Qwen Image 2.0
- + Perfect adherence to the 3x4 grid layout request
- + High-quality, distinct food photography for each section
- + Logical organization of sections with clear headers
- − The text below the images contains significant rendering artifacts and illegible characters
- − The design is very flat and lacks the realistic mockup feel of the competitor
Verdict: FLUX1.1 [pro] Ultra produces a more convincing real-world mockup that captures the 'casual dining' vibe, but Qwen Image 2.0 followed the specific grid layout and section instructions much more accurately. While Qwen's text rendering is poor, its composition makes it a better template for a menu design.
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
- + Excellent photorealistic rendering of food textures.
- + Clean and highly legible primary text.
- + Strong composition with a sense of scale and detail.
- − Missed the starburst requirement for the price tag.
- − Included unnecessary hallucinated text at the bottom of the image.
Qwen Image 2.0
- + Successfully included all requested text elements, including the starburst price tag.
- + Excellent fiery text effect that matches the prompt perfectly.
- + Good sense of motion with steam and flying sparks.
- − The burger is less 'exploded' than Model A, looking more like a standard stack.
- − The burger photography looks slightly more artificial/CG compared to Model A.
Verdict: FLUX1.1 [pro] Ultra produces a more visually stunning and realistic burger, but it fails to follow the specific layout instructions regarding the price starburst. Qwen Image 2.0 follows every detail of the prompt, including complex text requirements like the starburst and the fiery glow, making it the more accurate advertisement despite slightly lower food realism.
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
- + Very realistic chalk texture that includes dust on the board edges.
- + High image clarity and resolution.
- − Numerous spelling and repetition errors (e.g., 'mushroomm', 'fresh fresh').
- − Failed to render the title in an elegant cursive style.
- − The handwriting looks more like a digital marker than actual chalk.
Qwen Image 2.0
- + Perfect text accuracy and spelling for all menu items.
- + Captures the 'elegant cursive' style for the header as requested.
- + Authentic chalk-smudged background texture that looks like a real cafe board.
- − The slant of the text is slightly inconsistent toward the bottom.
Verdict: Qwen Image 2.0 followed the prompt instructions perfectly, correctly spelling all menu items and providing the requested cursive header. In contrast, FLUX1.1 [pro] Ultra suffered from significant text hallucinations and repetition, failing to maintain the requested phrasing or formatting.
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 high-resolution detail on the planet's surface and atmosphere
- + Cinematic composition with a wide-angle perspective
- + Sharp rendering of the astronaut suit and horse's fur
- − Failed the negative constraint; the astronaut is riding the horse instead of the horse on top
Qwen Image 2.0
- + Strong surreal elements such as the scales on the horse and floating liquid droplets
- + Good lighting and contrast between the subjects and the starfield
- + Intricate detail on the horse's mane and tack
- − Failed the negative constraint; the astronaut is riding the horse instead of the horse on top
- − Aesthetic is slightly more illustrated than cinematic
Verdict: Both FLUX1.1 [pro] Ultra and Qwen Image 2.0 failed the specific logic constraint of placing the horse on top of the astronaut, instead opting for the traditional interpretation. FLUX1.1 [pro] Ultra is the preferred choice as it produced a much more cinematic and technically superior image with a breathtaking planetary backdrop.
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 quality and lighting.
- + The businesswoman is clearly positioned in the passenger area with a realistic expression.
- + Detailed cap and jacket on the capybara.
- − The capybara is on the right side of the vehicle, suggesting a right-hand drive car which is incorrect for NYC.
- − Composition is slightly cluttered with the steering wheel overlapping the woman.
Qwen Image 2.0
- + Follows the spatial logic of a New York left-hand drive taxi correctly.
- + Shows both paws on the steering wheel as requested.
- + The businesswoman is clearly in a separate back seat row.
- − The paws look somewhat distorted and more like primate hands than capybara paws.
- − The lighting and overall image sharpness are slightly lower than the competitor.
Verdict: FLUX1.1 [pro] Ultra produces a more aesthetically pleasing and high-resolution image, but it fails the logic of a New York taxi by placing the driver on the right and the passenger in the front seat. Qwen Image 2.0 captures the specific prompt details like the two paws on the wheel and the correct seating arrangement for a taxi, making it the better choice for prompt adherence despite slightly lower visual fidelity.
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 typography style and layout.
- + Includes complex border details as requested.
- + Very high resolution and sharp details.
- − Includes redundant and misspelled text ('noickt').
- − The title is missing the word 'Party'
Qwen Image 2.0
- + Includes all specific text from the prompt correctly.
- + Excellent cinematic lighting on the pumpkin and environment.
- + Clean and legible composition without text repetition.
- − The 'webs' in the border are a bit simplistic.
- − The parchment effect is slightly less 'vintage' than the other model.
Verdict: While FLUX1.1 [pro] Ultra has a more intricate border and artistic parchment texture, it fails significantly on text accuracy by repeating the invite line with misspellings and omitting a core word from the title. Qwen Image 2.0 followed all text instructions perfectly and provided much better atmosphere and lighting, making it the superior invitation.
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' and 'isometric miniature' aesthetic.
- + Sophisticated soft lighting and material textures.
- + Very clean typography integrated into the 3D scene design.
- − Included a strange bug-like artifact on the wooden board.
- − The sushi pieces themselves are slightly more abstracted compared to the realistic request.
Qwen Image 2.0
- + Strong text readability and clear flag icon.
- + Realistic rendering of the sushi ingredients.
- + Followed the minimal garnish and solid background instructions well.
- − Failed to capture the 'cartoon' or 'miniature' diorama aesthetic, looking like a standard photo.
- − Shadows are somewhat harsh and less refined compared to the PBR request.
- − The angle is a standard top-down rather than the requested 45° isometric perspective.
Verdict: FLUX1.1 [pro] Ultra significantly outperformed Qwen Image 2.0 by accurately capturing the requested isometric miniature 3D cartoon style. While Qwen produced a more realistic-looking photo of sushi, it lacked the creative diorama execution and specific perspective requested in the prompt. FLUX1.1 [pro] Ultra's lighting and material quality feel more premium and intentional despite a minor artifact on the board.
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 consistent artistic style
- + All animals have a unified 'cute' aesthetic with high-quality fur texture
- + Vibrant colors that enhance the joyful vibe
- − Has a distinct digital/CGI illustrative feel rather than 'hyper-photorealistic'
- − The animals are mostly sitting still rather than 'chasing' or 'tumbling'
Qwen Image 2.0
- + Successfully captures the 'tumbling' and 'playful' action requested in the prompt
- + Much higher degree of photorealism in both animal anatomy and environment
- + Includes clear 'god rays' and dew-like lighting as specified
- − The fox kit has a slightly distorted facial expression while on its back
- − Texture on the kitten's forehead is slightly muddy compared to the puppy
Verdict: While FLUX1.1 [pro] Ultra produces a beautiful, charming illustration, it fails the 'hyper-photorealistic' and 'tumbling' aspects of the prompt. Qwen Image 2.0 provides a much more convincing photorealistic scene with dynamic posing and accurate lighting effects like god rays, making it the superior choice for this specific prompt.
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 unavailable for this challenge.
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 vector art style with high graphical complexity.
- + Strong adherence to the NASA-inspired color palette.
- + Crisp, modern typography for the main title.
- − Nonsensical text and labels for the body copy.
- − Poor information hierarchy with redundant icons and confusing layout flows.
- − Fails to accurately count or sequence the steps requested in the prompt.
Qwen Image 2.0
- + Perfectly follows all 6 steps in the correct order.
- + Legible, correctly spelled labels that align with the required stages.
- + Accurate iconography for the Saturn V and Lunar Module.
- − Typography is a bit generic and feels like a default font.
- − The composition is a bit cramped towards the bottom where the landing occurs.
- − A typo exists in 'Translunjar'.
Verdict: While FLUX1.1 [pro] Ultra produces a more aesthetically pleasing 'vector art' look, Qwen Image 2.0 is vastly superior as an infographic because it actually follows the requested sequence of events with legible text. Qwen Image 2.0 captures the specific technical requirements of the Saturn V and Lunar Module, whereas FLUX1.1 [pro] Ultra generates gibberish and loses the logical flow of the mission steps.
Explore each model
Alibaba's Qwen Image 2.0 model with enhanced text rendering, supporting both Chinese and English prompts with up to 6 images per request