Distilled version of Black Forest Labs' FLUX.2 [dev] outperforming it at a cheaper price. Developed by fal.ai.
Settled by community votes across 13 shared challenges, with an AI judge weighing in on each.
FLUX.2 [dev] Turbo
#4 of 62 in Text-to-Image
Qwen Image
#35 of 62 in Text-to-Image
Where the votes landed
FLUX.2 [dev] Turbo
100.0%
win rate
Ties
0.0%
Qwen Image
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
FLUX.2 [dev] Turbo
- + Excellent photorealism with realistic dusty/smudged glass textures.
- + Complex and accurate reflections and refractions of the plant through the glass.
- + Great depth of field and natural-looking window light.
- − The blue sphere has a slight transparency that might be interpreted as a marble rather than a solid sphere.
Qwen Image
- + Successfully follows all spatial prompts including the red book on top and blue sphere inside.
- + Clean, minimalist composition with vibrant colors.
- + Accurately represents the 'soft window light' from the left.
- − The glass cube appears more like a solid block of acrylic or mirror-based item than a hollow glass container.
- − The plant is heavily blurred, reducing the effectiveness of the 'partially visible through the glass' instruction.
Verdict: FLUX.2 [dev] Turbo produces a much more realistic and detailed image, with sophisticated light play and glass textures that make the scene feel authentic. Qwen Image provides a clean and accurate layout but suffers from a more artificial, CG-like appearance with less impressive refraction effects.
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
FLUX.2 [dev] Turbo
- + Excellent realism with highly detailed skin textures and lifelike hands.
- + Superior background integration with convincing motion blur and atmospheric rain effects.
- + The bicycle mechanics and tools on the ground add a high degree of authenticity to the scene.
- − The front wheel of the bicycle is slightly cut off at the bottom and merged oddly with the wet ground.
- − The framing feels a bit tight, though this could be argued as fitting the 'imperfect framing' prompt.
Qwen Image
- + Good adherence to the 'imperfect framing' prompt with a wider, slightly offset composition.
- + Clear reflections on the wet pavement that enhance the rainy atmosphere.
- + Captures the 'man repairing a bicycle' action well with a natural posture.
- − The bicycle lacks a chain and has nonsensical floating pedals/kickstand parts.
- − The image has a slightly painterly, smoothed texture that contradicts the 'no stylization' request.
- − The background car has a strange warped geometry.
Verdict: FLUX.2 [dev] Turbo is the clear winner due to its exceptional realism and attention to detail, particularly in the rendering of the man's skin and the complex mechanical parts of the bicycle. While Qwen Image captures a nice cinematic mood and composition, it fails significantly on technical accuracy, producing a bicycle with missing and floating parts and a more stylized, less photographic finish.
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
FLUX.2 [dev] Turbo
- + Excellent photorealistic skin texture with subtle fine-grained detail.
- + Highly intricate engraving on the plate armor with realistic metal weathering.
- + Very natural-looking hair and bead integration.
- − The torch in the background is slightly blurry due to the depth of field, though this was requested.
Qwen Image
- + Strong composition with dramatic lighting and high contrast.
- + Good adherence to the 'bokeh sparks' request with visible starburst effects.
- + Solid texture on the leather straps and mail.
- − The facial scars look a bit painted on rather than recessed in the skin.
- − Overall look is more digital/painterly rather than the requested 'lifelike' photo quality.
- − The beads in the hair look slightly less grounded in the physics of the braids.
Verdict: FLUX.2 [dev] Turbo produces a far more realistic image with superior skin textures, more naturalistic scarring, and authentic metal engraving that feels physical rather than drawn. While Qwen Image captures the dramatic lighting and specific 'bokeh' request well, it has a noticeably digital and less lifelike appearance compared to FLUX.2.
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
FLUX.2 [dev] Turbo
- + Excellent typography with clean, legible sans-serif fonts
- + Organized layout with distinct sections for Appetizers, Pizza, and Mains
- + Professional, high-quality food photography that fits the casual dining theme
- − Prices are unrealistically high ($160-$300 for a pizza) while being inconsistent in the 'Mains' section
- − Text includes some minor Latin-style gibberish in descriptions
Qwen Image
- + Strong minimalist aesthetic with vibrant colored square backgrounds
- + Creative use of a grid layout for food photography
- + Includes a more realistic pricing scale
- − Poor typography with significant 'AI gibberish' characters and strange spelling like 'Pizzaurant'
- − Combined 'Pizza/mains' section fails to follow the prompt's request for separate sections
- − Visual quality of food images is lower and more artificial-looking
Verdict: FLUX.2 [dev] Turbo produced a far more professional and usable design that strictly adhered to the separate section requirements and featured much cleaner typography. While Qwen Image had a creative color-block aesthetic, its text was largely unreadable and it failed to separate the categories as requested.
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.2 [dev] Turbo
- + Excellent text integration with a consistent fiery texture across all elements.
- + Highly photorealistic textures on the lettuce, patty, and bun.
- + Clean, professional composition that looks like a high-end food advertisement.
- − The 'exploded' effect is a bit conservative with components still largely clumped together.
Qwen Image
- + More dynamic 'exploded' movement with many scattered ingredients.
- + Strong use of glow and neon-like lighting for the title.
- − The 'LIMITED TIME ONLY' text lacks the requested fiery/glowing effect, appearing as flat white font.
- − The starburst and price tag look like a plastic 3D asset rather than a glowing effect.
- − Overall visual style is more illustrative/CG than photorealistic.
Verdict: FLUX.2 [dev] Turbo produced a far more cohesive and professional advertisement, successfully applying the fiery, glowing effect to all text elements as requested. While Qwen Image offered a more energetic movement of ingredients, its failure to stylize the secondary text and the less realistic rendering of the price starburst make it the weaker option.
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.2 [dev] Turbo
- + Excellent adherence to the chalk texture requirement, showing realistic grain and smudging.
- + Flawless spelling and punctuation for all requested menu items.
- + Very realistic environment with natural lighting and depth of field in the cafe background.
- − The handwriting leans more towards a casual print/script mix rather than the 'elegant cursive' specifically requested for the title.
Qwen Image
- + Clear, legible text that is well-centered on the board.
- + Warm, inviting cafe atmosphere with good composition.
- − Included a significant typo in the year, rendering it as '20026' instead of '2026'.
- − Text lacks realistic chalk texture, appearing more like a digital font or a smooth marker.
- − Misspelled 'Risotto' as 'Risoto'.
Verdict: FLUX.2 [dev] Turbo is the clear winner as it successfully rendered all text with the specific chalk texture requested and maintained perfect spelling throughout the image. Qwen Image failed on both the texture requirement and the accuracy of the text, including a major hallucination in the date and a spelling error in the menu items.
The Reversed Rodeo
Text-to-Image“Horse riding astronaut in space — horse on top, not vice versa. Surreal, highly detailed, cinematic.”
AI Judge Analysis
FLUX.2 [dev] Turbo
- + Excellent surface textures on the spacesuit and horse fur.
- + High level of background detail with multiple celestial bodies and nebulae.
- + Strong cinematic lighting with lens flare effects.
- − Failed to follow the specific spatial instruction 'horse on top'.
- − The馬's tail appears to be melting into clouds/dust in a slightly messy way.
Qwen Image
- + Clean, clear composition with a nice contrast against the planet.
- + Generally correct human and horse proportions.
- − Failed to follow the specific spatial instruction 'horse on top'.
- − The horse has five legs, with clear anatomical errors in the lower back region.
- − Lower level of detail and flatter lighting compared to Model A.
Verdict: Both FLUX.2 [dev] Turbo and Qwen Image failed the 'reverse positioning' trick in the prompt (horse on top of the astronaut). However, FLUX.2 [dev] Turbo is the superior image due to its significantly higher level of detail, better lighting, and anatomical correctness, whereas Qwen Image produced a horse with an extra leg.
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.2 [dev] Turbo
- + Excellent photorealism with detailed textures on the fur and leather
- + Superior prompt adherence for character placement
- + Natural environmental lighting and weather-grime details on the glass
- − The passenger is sitting in the front seat instead of the back seat as requested
- − The capybara's paws look more like primate hands than rodent paws
Qwen Image
- + Successfully placed the passenger in the back seat as requested
- + Creative use of uniform details like the name tag
- + Good depth of field with the city lights
- − The word on the taxi sign is misspelled as 'YOXI'
- − The interior layout is confusing, with the steering wheel appearing disconnected from the dashboard
- − Lighting on the capybara's fur is a bit flat compared to the realism in the other model
Verdict: FLUX.2 [dev] Turbo produces a much more convincing and cinematic photorealistic image, though it failed the spatial instruction of placing the passenger in the back seat. Qwen Image correctly followed the back seat instruction and passenger expression, but suffered from odd interior geometry and a text misspelling on the taxi light. FLUX.2 [dev] Turbo is the preferred winner due to significantly higher visual quality and believable textures despite the seat placement error.
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.2 [dev] Turbo
- + Perfect text rendering for all requested strings.
- + Excellent gothic composition with complex thorn and web borders.
- + High visual quality with detailed textures on the parchment and trees.
- − The jack-o-lantern stem is slightly detached from the body.
Qwen Image
- + Good atmospheric lighting behind the pumpkin.
- + Includes all requested elements like bats and twisted trees.
- − Several spelling errors in the title text including 'Halle Party'.
- − The text on the scroll banner is split awkwardly across two lines and features a font mismatch.
- − The 'thorn' border looks like simple triangular spikes rather than realistic vines.
Verdict: FLUX.2 [dev] Turbo followed the prompt perfectly, delivering flawless text rendering and a sophisticated vintage aesthetic. Qwen Image struggled with the text accuracy and produced a less detailed border, resulting in a less professional-looking 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.2 [dev] Turbo
- + Excellent PBR texturing on the salmon, wood grain, and rice.
- + Perfect typography and layout of the requested text.
- + High clarity and realistic lighting while maintaining the miniature aesthetic.
- − The salmon texture looks slightly more realistic than 'cartoon scene' as requested.
Qwen Image
- + Captures the 'cartoon' style very effectively with soft, rounded shapes.
- + Good use of isometric perspective and the diorama base.
- + Accurate text rendering and placement.
- − The textures are a bit too flat and lack the requested 'refined PBR' qualities.
- − Chopsticks feel a bit more cluttered than the 'minimal' request.
Verdict: FLUX.2 [dev] Turbo succeeded significantly better at the 'PBR materials' and 'high-clarity' requirements, producing an image that looks like a high-end 3D render. While Qwen Image nailed the cartoonish charm, it lacked the material complexity and refined textures present in FLUX.2.
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.2 [dev] Turbo
- + Excellent depiction of dew sparkles and fine fur detail.
- + Dynamic and playful composition with expressive animal faces.
- + Captures all four requested animal species clearly and distinctively.
- − The fox kit has a slightly awkward anatomy near its front paws.
- − The kitten's tail looks somewhat unnatural in its connection to the body.
Qwen Image
- + Beautiful global lighting with strong, cinematic god rays.
- + Soft, pleasing aesthetic that emphasizes the 'wholesome vibe'.
- + Very clean composition with the puppy centered.
- − The fox kit has dark, almost bear-like paws that lack realism.
- − The fur texture is slightly smoothed out compared to Model A's sharper detail.
- − The kitten's facial structure is less feline than in Model A.
Verdict: FLUX.2 [dev] Turbo provided a more detailed and anatomically accurate set of animals, particularly with the kitten and the overall fur texture. While Qwen Image had superior lighting and god rays, it struggled with the fine details of the paws and facial features, making FLUX.2 [dev] Turbo the winner for its superior realism and adherence to the 'ultra-detailed' 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.2 [dev] Turbo
- + Perfect text rendering for both the main name and the banner details.
- + Superior aesthetic with a realistic vintage paper texture and hatching details.
- + Clean vector emblem style with professional composition and balance.
- − The accent on 'Caffè' is slightly stylized as a grave but looks a bit like a comma above the E.
Qwen Image
- + Follows the color scheme and general icon requirements of the cloche and banner.
- + The steam effect is clear and minimalist.
- − Severe typography errors with overlapping and garbled letters in 'Florian'.
- − Flat, cartoonish style lacks the 'vintage' and 'classic' feel requested in the prompt.
- − Poor composition with the text 'Caffé' placed awkwardly inside the larger letters.
Verdict: FLUX.2 [dev] Turbo significantly outperformed Qwen Image by delivering a professional, commercially viable logo with perfect spelling and elegant vintage styling. Qwen Image struggled with the typography, resulting in illegible overlapping text and a much simpler, less sophisticated visual style.
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.2 [dev] Turbo
- + Excellent text rendering and spelling for labels like 'Translunar' and 'Descent'.
- + Rich details including mission crew silhouettes and accurate NASA-inspired color palette.
- + Good use of space with clear iconographic representations for each step.
- − Layout is a bit cluttered with redundant elements like dual 'Translunar' and 'Landing' icons.
- − The Saturn V rocket illustration includes extra boosters not present on the actual rocket.
Qwen Image
- + Clean, minimalist flat-vector style that adheres strictly to the 'modern vector' prompt.
- + Effective use of the requested color palette with clear, chunky icons.
- − Poor spelling and text logical flow (e.g., 'Tranar Orbit', 'Aldin', and 'Stop at landing' being part of the title).
- − The numbering sequence skips steps and is logically confusing (2, 3, 4, 6).
- − The lunar surface at the bottom is very simplistic compared to the rest of the image.
Verdict: FLUX.2 [dev] Turbo produced a much more professional and comprehensive infographic with near-perfect text and relevant supporting details like the crew names. While Qwen Image captured the 'flat-vector' aesthetic well, it failed significantly on text accuracy and logical sequencing of the mission steps.
Explore each model
Alibaba's Qwen image model