OpenAI's legacy image generation model supporting generations, edits with masks (inpainting), and variations
Settled by community votes across 13 shared challenges, with an AI judge weighing in on each.
DALL-E 2
15.8
arena score
#59 of 62 in Text-to-Image
Skill signature
· Text-to-Image
FLUX1.1 [pro] Ultra
18.5
arena score
#49 of 62 in Text-to-Image
Vote tally
Where the votes landed
DALL-E 2
0%
win rate
Ties
0%
FLUX1.1 [pro] Ultra
0%
win rate
Shared challenges
13
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.”
DALL-E 2
FLUX1.1 [pro] Ultra
AI Judge Analysis
DALL-E 2
- + Features a wooden table base
- + Shows a green plant in the background
- − Failed almost all spatial instructions
- − The blue item is a giant vase, not a small sphere inside the cube
- − The cube contains a red shape instead of having a book on top
- − Low photographic realism compared to modern models
FLUX1.1 [pro] Ultra
- + Perfect adherence to all spatial prompts including object placement
- + High visual fidelity with realistic textures on the book and glass
- + Accurately renders lighting and transparency effects
- − The blue sphere is levitating rather than resting on the bottom of the cube
- − Artificial-looking text on the book spine
Verdict: FLUX1.1 [pro] Ultra followed every instruction perfectly, placing the sphere inside the cube and the book on top with remarkable clarity and realism. DALL-E 2 struggled significantly with the spatial logic, turning the 'small blue sphere' into a large background vase and failing to place the red book correctly.
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.”
DALL-E 2
FLUX1.1 [pro] Ultra
AI Judge Analysis
DALL-E 2
- + Successfully captures the requested 'imperfect framing' and candid feel.
- + High-quality reflections on the wet pavement.
- − Extreme depth of field makes the subject nearly unrecognizable.
- − Fails to show an elderly Japanese man or natural skin texture effectively due to blur.
- − Image quality/resolution appears low and dated.
FLUX1.1 [pro] Ultra
- + Excellent adherence to nearly all prompt keywords including motion blur, skin texture, and rain.
- + Highly realistic rendering of the red bicycle and wet street reflections.
- + Clear portrayal of the requested elderly Japanese man.
- − The framing is quite central and balanced, missing the 'imperfect framing' request.
- − Minor anatomical oddity where the man's left hand meets the bicycle handlebars.
Verdict: DALL-E 2 produced an abstract composition that follows the 'imperfect framing' and 'shallow depth of field' prompts but fails to render a visible subject or high-quality details. FLUX1.1 [pro] Ultra created a stunning, high-fidelity image that successfully integrates complex elements like motion blur from passing cars while maintaining a clear, realistic subject.
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.”
DALL-E 2
FLUX1.1 [pro] Ultra
AI Judge Analysis
DALL-E 2
- + Successfully rendered metallic textures and a warm bokeh effect
- + Matches the grim, battle-worn mood of the prompt
- − Image is extremely blurry and lacks clear fine detail
- − Anatomical features are messy and lack the 'lifelike eyes' requested
- − Resolution is very low with significant artifacts
FLUX1.1 [pro] Ultra
- − The image is a complete failure, providing only a black screen
Verdict: DALL-E 2 provided a recognizable attempt at the prompt, showing armor and lighting, though the image quality is poor and lacks detail. FLUX1.1 [pro] Ultra failed to generate an image entirely, resulting in a black output. DALL-E 2 wins by default as it produced a visual response that adheres to some aspects of the prompt.
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.”
DALL-E 2
FLUX1.1 [pro] Ultra
AI Judge Analysis
DALL-E 2
- + Strong bold sans-serif typography on the right page
- + Abstract grid-like composition
- − Text is nonsensical and includes artifacts
- − Food photos are distorted and lack appetizing quality
- − Fails to create distinct sections for appetizers, pizza, and mains
FLUX1.1 [pro] Ultra
- + Implements clear sections for Appetizers, Pizzas, and Mains as requested
- + High-quality, vibrant food photography in a realistic grid layout
- + Excellent professional typesetting and clean minimalist layout
- − Includes minor spelling errors in headings like 'Pizzzans'
- − The text below headings is placeholder-like rather than coherent English
Verdict: FLUX1.1 [pro] Ultra significantly outperformed DALL-E 2 by providing a clear, professional menu structure that followed every part of the prompt, including the specific sections requested. DALL-E 2 produced a more abstract, less functional design with distorted imagery that does not resemble a usable menu.
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.”
DALL-E 2
FLUX1.1 [pro] Ultra
AI Judge Analysis
DALL-E 2
- + Successfully captures a dynamic, painterly sense of fire and motion.
- + Follows the request for a fiery, glowing background effect.
- − Text is largely illegible and contains numerous spelling errors like 'MARGIC' and 'BAGUEC'.
- − The burger components lack photorealistic detail and look messy or smeared.
- − Failed to include the price starburst and secondary messaging.
FLUX1.1 [pro] Ultra
- + Excellent text rendering with perfect spelling for 'MAGIC BURGER' and 'LIMITED TIME ONLY'.
- + High photorealistic detail in the burger components, particularly the texture of the meat and bun.
- + Clear and organized composition that effectively showcases an 'exploded' view.
- − The price '€6.99' is not contained within a starburst as requested.
- − The 'exploded' burger is actually multiple burgers stacked, which makes the layout feel slightly cluttered.
Verdict: FLUX1.1 [pro] Ultra is the clear winner as it produces professionally legible text and highly detailed, appetizing food photography that aligns with modern advertising standards. DALL-E 2 struggles significantly with both text generation and visual clarity, resulting in an image that looks like a blurry digital painting rather than a photorealistic advertisement.
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.”
DALL-E 2
FLUX1.1 [pro] Ultra
AI Judge Analysis
DALL-E 2
- + The chalk texture looks authentic and dusty.
- − The text is completely illegible gibberish.
- − It failed to follow any of the specific menu item instructions.
- − The image quality is low and blurry.
FLUX1.1 [pro] Ultra
- + Successfully rendered the complex text and dates requested.
- + The handwriting looks realistic with variations in letter size and slant as requested.
- + High visual quality and clear composition within a café setting.
- − Includes some repetitive words (fresh fresh, chocolate chocolate).
- − The 'Truffle Mushroom Risotto' has some spelling artifacts (mushroomm ris).
Verdict: FLUX1.1 [pro] Ultra significantly outperforms DALL-E 2 by providing legible, accurate text that follows the prompt's specific menu items and date. DALL-E 2 produced an illegible scramble of letters that failed all prompt requirements related to content. While FLUX1.1 [pro] Ultra has minor repetitive word errors, the overall presentation and adherence to the handwriting style are excellent.
The Reversed Rodeo
Text-to-Image“Horse riding astronaut in space — horse on top, not vice versa. Surreal, highly detailed, cinematic.”
DALL-E 2
FLUX1.1 [pro] Ultra
AI Judge Analysis
DALL-E 2
- + Attempts a painterly, textured aesthetic.
- + Composition provides a sense of a lunar landscape.
- − Fails the specific negative constraint by placing the astronaut on top of the horse.
- − Low resolution with significant noise and muddy details.
- − Anatomy of both the horse and astronaut is distorted and unclear.
FLUX1.1 [pro] Ultra
- + High visual clarity and extremely sharp details across the entire frame.
- + Dynamic composition with a professional, cinematic lighting style.
- + Correctly interprets the space setting and surreal atmosphere.
- − Fails the specific logic puzzle by placing the astronaut on top, ignoring the 'horse on top' instruction.
- − Minor anatomical awkwardness where the astronaut's leg meets the horse.
Verdict: Both models failed the difficult logical constraint to place the horse on top of the astronaut, instead defaulting to the common trope of an astronaut riding a horse. FLUX1.1 [pro] Ultra is the clear winner due to its vastly superior image quality, modern rendering, and detailed cinematic composition, whereas DALL-E 2 produced a blurry, low-quality image with poor anatomy.
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.”
DALL-E 2
FLUX1.1 [pro] Ultra
AI Judge Analysis
DALL-E 2
- + Attempts to show the creature and human in their respective positions
- − Extreme anatomical distortions and nightmare-like facial artifacts
- − Fails to render a recognizable capybara, showing a strange golden figure instead
- − The passenger's expression is shocked rather than bored, and her face is severely malformed
FLUX1.1 [pro] Ultra
- + High photographic realism with excellent lighting and texture
- + Perfect adherence to all prompt details including the capybara's hat and calm expression
- + Clean composition with accurate depth of field for the Manhattan background
- − The passenger appears to be sitting in the front passenger seat rather than the back seat
- − The steering wheel is positioned strangely between the driver and passenger
Verdict: DALL-E 2 produced a low-quality, distorted image that fails to clearly depict a capybara or a realistic human. FLUX1.1 [pro] Ultra generated a stunning, highly detailed image that captures the requested mood and textures perfectly, though it struggled slightly with the spatial arrangement of the car's interior.
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.”
DALL-E 2
FLUX1.1 [pro] Ultra
AI Judge Analysis
DALL-E 2
- + Successfully captures a weathered, vintage parchment aesthetic
- + The border has a hand-carved, organic feel
- − Text is largely illegible and contains numerous misspellings
- − Fails to include key visual elements like the central glowing jack-o-lantern and bats
- − Overall image quality is blurry and lacks fine detail
FLUX1.1 [pro] Ultra
- + Excellent text rendering, with almost all requested details spelled correctly
- + Includes all requested visual motifs: jack-o-lantern, bats, thorns, and twisted trees
- + High resolution with clean, professional composition and cinematic lighting
- − Repeats the 'invited to a night of frights' sentence twice, once with a typo ('noickt')
- − The illustrative style is more modern digital art than a truly 'vintage' gothic artifact
Verdict: FLUX1.1 [pro] Ultra is the clear winner as it follows the complex text-based instructions with high accuracy and includes every requested visual element in a polished layout. DALL-E 2 fails significantly on text legibility and omits several core components of the prompt, resulting in a much lower-quality output.
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.”
DALL-E 2
FLUX1.1 [pro] Ultra
AI Judge Analysis
DALL-E 2
- + Successfully used a light blue background
- + Maintained sharp, 3D shadows for the text and objects
- − Failed to include 'JAPAN' text and misspelled 'SUSHI' as 'Sush'
- − The 3D models are very primitive and don't resemble high-quality sushi
- − Floating cube and fragment artifacts appear on the plate
FLUX1.1 [pro] Ultra
- + Exemplary text rendering for both 'JAPAN' and 'SUSHI' with the requested flag icon
- + Excellent miniature 3D cartoon aesthetic with soft PBR materials
- + Perfectly followed the diorama base and isometric perspective instructions
- − The garnish includes a slightly strange ladybug-like artifact on the wooden board
- − Added steam to cold sushi, which is a minor logical inconsistency
Verdict: FLUX1.1 [pro] Ultra followed every instruction perfectly, producing a professional-grade 3D icon style with accurate text and a beautiful diorama composition. DALL-E 2 struggled significantly, failing to render the full text, misspelling what it did produce, and generating very low-quality 3D assets.
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.”
DALL-E 2
FLUX1.1 [pro] Ultra
AI Judge Analysis
DALL-E 2
- + Stronger sense of action/movement in the pose of the animals.
- − Several severe anatomical distortions and artifacts, particularly on the kitten and bunny.
- − Poor image clarity and resolution, looking muddy and unrefined.
- − Distorted, non-realistic butterfly shapes and fragmented lighting.
FLUX1.1 [pro] Ultra
- + Exceptional visual quality with clear, sharp details in fur and eyes.
- + Perfectly captures the lighting request including golden hour glow and god rays.
- + Features all requested animals with high aesthetic appeal and cute expressions.
- − The style and expressions lean more towards 'Disney-style' cute than true photorealistic.
- − The animals are sitting rather than 'tumbling', missing some of the requested kinetic energy.
Verdict: FLUX1.1 [pro] Ultra produced a high-quality masterpiece that perfectly adheres to the lighting and character requirements, whereas DALL-E 2 struggled with significant anatomical artifacts and low resolution. While FLUX1.1 took a more stylized approach to 'expressive eyes', the overall coherence and beauty of the image far exceed the fragmented and distorted output from DALL-E 2.
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.”
DALL-E 2
FLUX1.1 [pro] Ultra
AI Judge Analysis
DALL-E 2
- + Matches the requested minimalist vector style and color palette.
- + Employs an asymmetrical texture that fits the vintage aesthetic.
- − Text consists entirely of illegible, garbled characters.
- − The cloche handle is poorly formed and lacks the requested steam element.
- − Composition feels scattered and unrefined.
FLUX1.1 [pro] Ultra
- + Excellent layout with a balanced emblem structure.
- + Includes almost all prompt details like the steam, banner, and date.
- + Clean, high-quality vector rendering with subtle paper texture.
- − Misspelled the name of the establishment as 'Caffé Framilian'.
- − The cloche design is quite detailed, bordering on decorative rather than minimalist.
Verdict: DALL-E 2 failed significantly on text legibility and basic prompt details like the steam and date banner. FLUX1.1 [pro] Ultra produced a professional, cohesive logo with high visual appeal, and although it misspelled the restaurant name, it is the superior choice for its adherence to complex structural requirements.
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.”
DALL-E 2
FLUX1.1 [pro] Ultra
AI Judge Analysis
DALL-E 2
- + Follows the requested color palette well.
- + Captures an abstract technical aesthetic.
- − Fails to follow the specific 6-step infographic structure.
- − Text is completely illegible and nonsensical.
- − Composition is cluttered and chaotic rather than a clean infographic.
FLUX1.1 [pro] Ultra
- + Excellent adherence to the 6-step structural prompt.
- + Clean, modern flat-vector aesthetic with a logical layout.
- + High-quality text rendering and professional iconography.
- − Text content includes several spelling errors and nonsensical phrases.
- − The numbering system for the steps is inconsistent.
Verdict: FLUX1.1 [pro] Ultra is the clear winner as it successfully interpreted the request for a structured infographic with specific steps and icons. While the text contains errors, it is legible and clearly organized, whereas DALL-E 2 produced a chaotic mess of abstract lines and symbols that failed to follow any of the step-by-step instructions.
Next steps
Explore each model
Black Forest Labs' ultra-high resolution image generation model, an enhanced version of FLUX1.1 [pro] optimized for premium quality output