Black Forest Labs' 12-billion parameter flow transformer for high-quality text-to-image generation, suitable for personal and commercial use with streaming support
Settled by community votes across 9 shared challenges, with an AI judge weighing in on each.
FLUX.1 [dev]
#16 of 62 in Text-to-Image
Qwen Image 2.0 Pro
#31 of 62 in Text-to-Image
Where the votes landed
FLUX.1 [dev]
50.0%
win rate
Ties
0.0%
Qwen Image 2.0 Pro
50.0%
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
FLUX.1 [dev]
- + Excellent surface textures, especially on the book's leather cover.
- + High-quality lighting with realistic caustic reflections from the glass and sphere.
- + Clear adherence to the prompt with a vibrant blue sphere.
- − The glass structure appears more like a frame than a solid cube.
Qwen Image 2.0 Pro
- + Successfully renders the plant visible through the glass panels as requested.
- + The cube geometry and perspective are highly accurate.
- + Maintains a realistic matte texture for the blue sphere.
- − The sphere appears to be floating unnaturally in the center with no point of contact or support.
- − Lighting is a bit flatter compared to the other model.
Verdict: Both models followed the complex spatial instructions perfectly. FLUX.1 [dev] produced a more aesthetically pleasing image with superior lighting and textures, while Qwen Image 2.0 Pro did a better job of showing the plant behind and through the glass panels.
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
FLUX.1 [dev]
- + Excellent photorealistic lighting on the food ingredients
- + Vertical stack composition feels magical and balanced
- − Completely failed to include the primary 'MAGIC BURGER' text
- − Missing the requested starburst element for the price
- − No sense of motion; the burger feels static
Qwen Image 2.0 Pro
- + Followed all text instructions perfectly including title, subtitle, and starburst
- + Excellent fiery, glowing text effects as requested
- + Strong sense of motion with flying embers and steam
- − The starburst graphic is a bit simple/clip-art like compared to the burger
- − The burger ingredients are a bit standard and less 'exploded' than the prompt suggests
Verdict: Qwen Image 2.0 Pro is the clear winner as it successfully integrated all requested text and visual elements, whereas FLUX.1 [dev] completely omitted the main title and the starburst requirement. Qwen Image 2.0 Pro also captured the 'fiery' atmosphere and 'sense of motion' much more effectively than the static composition of FLUX.1 [dev].
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
FLUX.1 [dev]
- + Excellent typography rendering with almost no spelling errors.
- + The text style captures a very clean, aesthetic chalk handwriting look.
- + High-quality framing and wooden texture on the board.
- − The chalk texture looks a bit too 'clean', bordering on digital marker rather than dusty chalk.
- − The handwriting for the main items is slightly less natural than a human hand would produce.
Qwen Image 2.0 Pro
- + Features a very realistic chalk texture with smudges and varying pressure.
- + The perspective and lighting in the cafe setting feel more organic and less like a studio product shot.
- + Accurately captured the 'slight slant' requested in the prompt.
- − Slight spelling artifact in 'April' (the 'A' is slightly malformed).
- − The cursive requested for the title is more of a print-style block letter set compared to Model A.
Verdict: Both models performed exceptionally well on a difficult text rendering task. FLUX.1 [dev] produced near-perfect spelling and a very clean layout, but Qwen Image 2.0 Pro felt more authentic to the request for 'chalk texture' and 'natural variations,' looking like a real chalkboard in a real environment. FLUX.1 [dev] is slightly preferred for its impeccable legibility and spelling accuracy.
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
FLUX.1 [dev]
- + Excellent photographic depth of field and bokeh effect
- + High aesthetic quality with clean lighting
- + Text on the cap is clear and relevant
- − The passenger is seated in the front seat instead of the back seat as requested
- − The woman's expression is more focused/melancholic than 'bored' or 'normal'
Qwen Image 2.0 Pro
- + Follows the composition prompt perfectly with the passenger in the back seat
- + Captures the 'bored' expression and 'businesswoman in a coat' look precisely
- + Highly realistic taxi interior details including the TLC license sticker and dashboard electronics
- − The capybara's hands/paws look slightly anthropomorphic and uncanny
- − The exterior street details are a bit more cluttered compared to the clean background of Model A
Verdict: While FLUX.1 [dev] produced a more visually striking and cinematic image, it failed on a key spatial instruction by placing the passenger in the front seat. Qwen Image 2.0 Pro followed every detail of the prompt, including the passenger's placement and the specific bored expression, while adding realistic touches like the TLC license.
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
FLUX.1 [dev]
- + Strong illustrative style with bold colors
- + Clear jack-o-lantern and thorn border elements
- + Composition is balanced with the central moon
- − Major text errors including 'Lalloween Ranty' and 'You Tre'
- − Duplicate '7pm, 7pm' in event details
- − Lacks the requested spider webs in the border
Qwen Image 2.0 Pro
- + Perfect text rendering for all requested strings
- + Includes all requested elements: webs, thorns, bats, trees, and glowing pumpkin
- + Captures the 'gothic parchment' aesthetic very effectively
- − The green glow on the pumpkin is slightly less traditional than orange
- − Lighting on the bats is a bit flat compared to the pumpkin
Verdict: Qwen Image 2.0 Pro is the clear winner as it followed every instruction perfectly, specifically the complex text requirements which it rendered without a single typo. FLUX.1 [dev] produced a visually striking image but failed significantly on the text prompts, yielding gibberish and typos throughout the 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
FLUX.1 [dev]
- + Excellent PBR texturing on the salmon
- + Beautiful depth of field and soft lighting
- + Sophisticated miniature aesthetic
- − Failed the text prompt with 'SUSH CATON'
- − Text placement and size do not match 'large bold' request
- − Inclusion of extra cherry blossom elements not requested
Qwen Image 2.0 Pro
- + Perfect adherence to text content and styling
- + Excellent isometric projection
- + Clean, high-clarity rendering that matches the 'cartoon' request
- − Lighting is slightly flat compared to Model A
- − Sushi models are quite simple
Verdict: While FLUX.1 [dev] produced a more visually artistic image with superior lighting and materials, it failed significantly on the text rendering. Qwen Image 2.0 Pro followed every instruction perfectly, including the specific text hierarchy, placement, and the flag icon, making it the better choice for this specific design-oriented prompt.
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
FLUX.1 [dev]
- + Bright and colorful lighting that suits a joyful vibe.
- + Clean and consistent character designs.
- − Failed to follow the prompt's request for hyper-photorealism, resulting in an illustrated/3D animation style.
- − Failed to include a tabby kitten, instead generating two dogs and two fox/rabbit hybrids.
Qwen Image 2.0 Pro
- + Excellent adherence to the hyper-photorealistic style requested.
- + Followed all subject requirements, including the golden retriever, tabby kitten, bunny, and fox kit.
- + Superb interaction and composition with realistic 'tumbling' behavior and god rays.
- − One butterfly in the background has a slightly unnatural wing alignment.
Verdict: Qwen Image 2.0 Pro is the clear winner as it successfully delivered a hyper-photorealistic image containing all four specific animals requested, whereas FLUX.1 [dev] produced a non-realistic 3D-cartoon style and failed to include the kitten. Qwen Image 2.0 Pro also perfectly captured the environmental details like god rays and dew sparkles mentioned in the 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
FLUX.1 [dev]
- + Features a balanced emblem-style composition
- + Includes all requested prompt elements including the banner and steam
- + Good texture on the background
- − Has spelling errors in both the restaurant name ('Flariláan') and the word 'RESEAURANT'
- − Contains random, nonsensical numbers '11011' and '1941'
Qwen Image 2.0 Pro
- + Spells the core name almost correctly despite a double 'i'
- + Strong vector illustration style with clean gradients
- + Excellent adherence to the color palette and minimalist aesthetic
- − Places the steam graphic in front of the cloche rather than emerging from it
- − Slight typo in the main name ('Floriian')
Verdict: Both models struggled with the exact spelling of the restaurant name, but Qwen Image 2.0 Pro was much closer than FLUX.1 [dev], which hallucinated random numbers and additional spelling errors. While FLUX.1 [dev] captured the layout of a traditional logo better, the overall clean vector quality and better text accuracy of Qwen Image 2.0 Pro make it the superior choice.
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
FLUX.1 [dev]
- + Features a balanced, symmetrical composition with a professional layout.
- + Excellent use of negative space and clean lines consistent with vector art.
- + Adheres strictly to the requested NASA-inspired muted color palette.
- − Text rendering is mostly nonsensical gibberish.
- − The iconography is confusing and doesn't clearly represent the specific mission steps requested.
Qwen Image 2.0 Pro
- + Excellent text rendering, correctly labeling every specific step and the crew names.
- + Closely follows the requested progression from launch to landing with clear, identifiable icons.
- + Highly logical layout that functions effectively as a readable infographic.
- − The 'Descent' icon includes some realistic rendering/shading that leans away from the 'flat-vector' request.
- − Composition feels a bit vertically cramped compared to the other model.
Verdict: While FLUX.1 [dev] produces a more aesthetically pleasing 'poster' with better balance and color harmony, Qwen Image 2.0 Pro is the superior functional infographic. Qwen correctly labels every requested mission step with legible text and follows the logical sequence of the Apollo 11 mission perfectly.
Explore each model
Alibaba's Qwen Image 2.0 Pro model offering higher quality image generation with enhanced detail and accuracy