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]
18.4
arena score
#50 of 62 in Text-to-Image
Vote tally
Where the votes landed
DALL-E 2
0%
win rate
Ties
0%
FLUX1.1 [pro]
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]
AI Judge Analysis
DALL-E 2
- + The lighting matches the requested soft window light vibe.
- + Interesting reflections on the wooden surface.
- − Completely failed to follow the spatial instructions, merging the red book into the cube and omitting the blue sphere.
- − The plant is in a giant blue pot rather than being behind the glass cube.
- − Low resolution and blurry details.
FLUX1.1 [pro]
- + Perfect adherence to all prompt elements including the blue sphere inside and red book on top.
- + Exceptional photorealism with clear textures on the book and glass reflections.
- + Accurately represents the depth of the plant behind the glass cube.
- − The glass container is more of a rectangular prism than a perfect cube.
- − The blue sphere appears to be magically floating rather than resting.
Verdict: FLUX1.1 [pro] followed every specific detail of the prompt, including complex spatial relationships like objects inside and on top of one another. DALL-E 2 completely failed the prompt adherence, missing key objects and confusing the colors of the subjects. FLUX1.1 [pro] is the clear winner due to its superior realism and logic.
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]
AI Judge Analysis
DALL-E 2
- + Successfully captures reflections on wet pavement
- + Follows the 'imperfect framing' and 'shallow depth of field' prompts effectively
- − The subject is completely out of focus and unrecognizable as an elderly Japanese man
- − Image quality is low with significant blur and noise
- − Lack of clear subject matter and detail
FLUX1.1 [pro]
- + Excellent adherence to multiple prompt details including the subject, bicycle color, and wet pavement
- + High visual quality with realistic skin textures and cinematic lighting
- + Effective use of shallow depth of field and bokeh
- − Failed to include 'motion blur from passing cars' as cars in background are static light sources
- − Anatomical/mechanical glitch with a small wheel-like object appearing beneath the man's feet
Verdict: DALL-E 2 produced an abstract, low-quality image where the requested subject is unrecognizable due to extreme focus issues. FLUX1.1 [pro] followed almost every prompt instruction with high fidelity, creating a realistic, cinematic photograph with a clear central subject, despite a small artifact near the subject's feet.
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]
AI Judge Analysis
DALL-E 2
- + Captures a strong weathered texture on the metal armor
- + Follows the request for warm lighting bokeh
- − Low resolution and lacks clarity
- − Fails to render lifelike eyes or a recognizable human face
- − Composition is messy and lacks a clear focal point
FLUX1.1 [pro]
- + Exquisite detail on skin texture, scars, and individual hair strands
- + Perfectly captures all prompt elements including braids with beads and bokeh sparks
- + Cinematic lighting and high-quality photorealistic rendering
- − The 'faint' scars and dirt appear quite prominent/heavy compared to the prompt
Verdict: FLUX1.1 [pro] significantly outperforms DALL-E 2 by providing a clear, high-resolution portrait that adheres to every specific detail of the prompt, including the braided hair and lifelike eyes. DALL-E 2 produced a blurry, distorted image where the face and armor details are largely unintelligible.
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]
AI Judge Analysis
DALL-E 2
- + Bold, high-impact sans-serif typography
- + Creative geometric approach to food imagery
- − Nonsensical text rendering
- − Doesn't resemble a functional menu layout
- − The food images are distorted and unrecognizable
FLUX1.1 [pro]
- + Excellent grid layout with clear food photography
- + Includes specific requested sections like Appetizers and Pizza
- + Highly professional and realistic menu presentation
- − Fine print text is garbled upon close inspection
- − Small scale makes reading specific menu items difficult
Verdict: FLUX1.1 [pro] significantly outperforms DALL-E 2 by providing a functional, professional menu design that follows all prompt instructions, including specific category headers and a clean grid of high-quality food photos. DALL-E 2 fails the layout requirement, producing an abstract book-like image with distorted food and gibberish text.
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]
AI Judge Analysis
DALL-E 2
- + Successfully captures a dynamic, exploded mid-air effect
- + Matches the fiery orange and red color palette well
- − Poor typography with significant misspellings
- − Lower resolution with blurry, indistinct ingredients
- − Fails to include the price and starburst mentioned in the prompt
FLUX1.1 [pro]
- + Excellent photorealistic detail on the burger ingredients
- + Perfectly rendered text for the title, secondary message, and price
- + Strong composition with a professional advertising layout
- − The burger is mostly assembled rather than 'exploded' with individual components suspended in air
- − Missing the starburst specifically requested for the price
- − Text has a blue neon glow instead of the requested fiery glowing effect
Verdict: FLUX1.1 [pro] significantly outperforms DALL-E 2 in terms of visual fidelity, legibility, and modern aesthetic, despite failing to fully 'explode' the burger components. While DALL-E 2 captured the requested motion better, its failure to generate readable text and high-quality textures makes it less effective for an advertisement. FLUX1.1 [pro] is the clear winner for its superior rendering and professional execution.
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]
AI Judge Analysis
DALL-E 2
- + Captures a rough, authentic chalk-on-board texture.
- − Text consists entirely of illegible gibberish.
- − Completely fails the prompt criteria for specific menu items and dates.
- − Extremely low resolution and lacks any environmental context.
FLUX1.1 [pro]
- + High adherence to specific menu text including the exact date and items.
- + Excellent visual quality with a realistic cafe atmosphere and lighting.
- + Strong composition with elegant, legible cursive and script chalk effects.
- − Minor text errors such as 'Chipkies' instead of 'Chip' and 'Herbss'.
- − Pricing logic is inconsistent with 'Grilled Octopus' listed twice at differing high prices.
Verdict: FLUX1.1 [pro] is the clear winner as it successfully rendered most of the complex handwritten text and instructions, whereas DALL-E 2 produced completely illegible scribbles that did not follow the prompt's content. FLUX1.1 [pro] also provided a beautifully composed scene with a realistic cafe background, while DALL-E 2 only generated a low-quality crop of a board.
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]
AI Judge Analysis
DALL-E 2
- + Successfully captures a cinematic sense of scale with a planet in the background.
- + Follows the general theme of a space-faring horse riding scenario.
- − Failed the spatial reasoning constraint of having the horse on top of the astronaut.
- − Low visual fidelity with significant compression artifacts and muddy textures.
- − Anatomical issues with the horse's legs and the astronaut's rendering.
FLUX1.1 [pro]
- + High resolution with exceptional detail in the spacesuit and horse's mane.
- + Dynamic composition with dramatic cinematic lighting.
- + Clean execution and vibrant colors.
- − Failed the specific spatial instruction to have the horse on top of the astronaut.
- − The horse's anatomy is slightly confused at the rear where it meets the ground/clouds.
Verdict: Both models failed the specific logical constraint to place the 'horse on top' of the astronaut, providing standard 'astronaut on horse' interpretations instead. However, FLUX1.1 [pro] is the clear winner due to its vast superiority in image quality, detail, and lighting compared to the low-resolution and artifact-heavy output from DALL-E 2.
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]
AI Judge Analysis
DALL-E 2
- + Attempts to show the front-facing viewpoint from the passenger seat.
- − Extreme anatomical distortions on the hand, face, and capybara.
- − Significant artifacts and incoherent composition with floating objects.
- − Fails to place the woman in the back seat as requested.
FLUX1.1 [pro]
- + Excellent photorealism and professional lighting.
- + Accurate adherence to almost all prompt details, including the capybara's hat and jacket.
- + High visual quality with realistic textures on fur and clothing.
- − The capybara and woman appear to be sitting side-by-side in the front rather than the woman being in the back seat.
- − The capybara's 'front paws' are floating near its chest rather than on a steering wheel.
Verdict: FLUX1.1 [pro] produces a high-quality, professional image that closely follows the aesthetic and narrative elements of the prompt, despite some spatial confusion regarding the car seats. DALL-E 2 fails significantly with severe anatomical glitches, poor resolution, and a complete lack of photorealism.
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]
AI Judge Analysis
DALL-E 2
- + Strong vintage aesthetic
- + Gothic border feels hand-carved and intricate
- − Text is largely unintelligible and misspelled
- − Artifacts and smearing throughout the image
- − Missing the requested jack-o-lantern
FLUX1.1 [pro]
- + Excellent text rendering including difficult date and address details
- + High-quality cinematic lighting with a clear subject
- + Follows almost all prompt instructions including the moon, bats, and trees
- − Redundant text layout at the bottom
- − A minor typo in 'invivted' in the small banner
Verdict: FLUX1.1 [pro] significantly outperforms DALL-E 2 by providing readable, accurate text according to the prompt and a clear, high-resolution composition. While DALL-E 2 captures a nice 'old-world' texture, it fails to generate the actual requested objects like the jack-o-lantern and produces nonsensical text.
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]
AI Judge Analysis
DALL-E 2
- + Matches the diagonal top-down perspective fairly well.
- + Uses a high-contrast color palette.
- − Fails to include the required 'JAPAN' text.
- − Trunkated 'Sush' text with poor rendering.
- − Sushi models are deformed and lack the requested '3D cartoon' aesthetic.
FLUX1.1 [pro]
- + Perfectly follows all text instructions including 'JAPAN' and 'SUSHI'.
- + Excellent miniature 3D cartoon style with soft refined textures.
- + Clean isometric diorama composition on a solid background.
- − Missing the specific small flag icon mentioned in the prompt.
Verdict: FLUX1.1 [pro] followed almost every instruction including complex text rendering, material style, and the diorama base requirement, resulting in a professional-looking asset. DALL-E 2 failed significantly on the text elements, clarity, and overall aesthetic quality, producing a distorted image with misspelled words.
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]
AI Judge Analysis
DALL-E 2
- + Attempts to include all four requested animals
- + Shows dynamic interactions with butterflies
- − Extremely poor image quality with heavy artifacts
- − Anatomically incorrect and distorted animals
- − Butterfly shapes are mangled and nonsensical
FLUX1.1 [pro]
- + Stunning photorealistic lighting and fur detail
- + Perfectly captures the 'expressive eyes' and 'wholesome vibe' from the prompt
- + Excellent composition and professional 8K aesthetic
- − Missing the red fox kit mentioned in the prompt
- − Animals are looking at butterflies rather than tumbling together
Verdict: FLUX1.1 [pro] significantly outclasses DALL-E 2 in terms of visual fidelity, lighting, and detail, creating a masterpiece-quality image even though it missed one of the four animals. DALL-E 2 struggled with the complex scene, resulting in distorted, nightmare-like figures and low-resolution textures that fail the 'hyper-photorealistic' requirement.
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]
AI Judge Analysis
DALL-E 2
- + Successfully captures warm brown and cream tones.
- + Minimalist approach to the cloche icon.
- − Text is nonsensical gibberish and does not follow the prompt.
- − Lacks the requested banner and steam details.
- − Vector shapes are poorly defined with messy edges.
FLUX1.1 [pro]
- + Excellent vintage aesthetic with professional-grade vector illustration.
- + Accurately includes steam, the banner, and the correct established date.
- + Superb paper texture and framing details that feel authentic.
- − Minor misspelling in the name (Cailfeé FRATILIAN instead of Caffè Florian).
- − Complexity leans more towards illustrative than minimalist.
Verdict: DALL-E 2 failed significantly on text rendering and prompt adherence, providing garbled characters and a very basic composition. FLUX1.1 [pro] produced a high-quality, professional logo that followed almost every stylistic instruction perfectly, including the specific date and icon, despite a slight misspelling of the restaurant name.
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]
AI Judge Analysis
DALL-E 2
- + Adheres well to the requested color palette
- + Captures a complex, technical diagram aesthetic
- − Text is nonsensical and poorly rendered
- − The layout is cluttered and does not clearly show the 6-step progression requested
- − Graphic elements are messy and lack crisp vector lines
FLUX1.1 [pro]
- + Excellent adherence to the chronological steps requested
- + Legible main title and clean, modern vector aesthetic
- + Effective use of negative space and iconography
- − Some small-scale text is still slightly garbled
- − Numerical layout for steps 1-5 is a bit repetitive/confusing on the left side
Verdict: FLUX1.1 [pro] significantly outperforms DALL-E 2 by providing a clear, logical infographic that follows the specific 6-step sequence requested in the prompt. While DALL-E 2 produced a chaotic mess of gibberish text and abstract lines, FLUX1.1 [pro] delivered a clean, professional layout with recognizable iconography and a readable title.
Next steps
Explore each model
Black Forest Labs' enhanced 12-billion parameter flow transformer with 6x faster generation than FLUX.1 [pro], delivering superior composition, detail, and artistic fidelity