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
#3 of 62 in Text-to-Image
Qwen Image 2.0
#34 of 62 in Text-to-Image
Where the votes landed
FLUX.2 [dev] Turbo
100.0%
win rate
Ties
0.0%
Qwen Image 2.0
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 photorealistic texture on the glass and wooden table.
- + Perfectly captures the lighting direction from the left as requested.
- + Realistic material interactions, including dust on the glass and accurate reflections.
- − The sphere is slightly off-center, though this arguably adds to the realism.
Qwen Image 2.0
- + Accurately includes all requested elements in a clean composition.
- + Strong color saturation on the blue sphere and red book.
- − The blue sphere appears to be floating unnaturally without supporting physics.
- − The glass cube has strange internal reflections that look like extra spheres.
- − The texture of the wooden table is somewhat flat and less detailed than Model A.
Verdict: FLUX.2 [dev] Turbo produced a highly photorealistic image with convincing lighting, textures, and physics. While Qwen Image 2.0 followed the prompt accurately, its output suffered from a floating sphere and confusing internal reflections that broke the realism of the scene. FLUX.2 is the clear winner for its superior visual quality and atmospheric lighting.
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 adherence to technical prompts like motion blur from passing cars and light rain effects
- + Highly detailed environment with realistic reflections and wet ground textures
- + Convincing cinematic composition that balances the subject with the urban background
- − The anatomy of the bicycle is slightly messy, with the rear kickstand appearing to go through the frame
Qwen Image 2.0
- + Strong 'imperfect framing' and 'candid' feel with a more intimate perspective
- + Excellent skin texture and realistic, aged Japanese facial features
- + Clean, realistic bokeh in the background cars
- − Missed the 'motion blur from passing cars' requirement, as the background vehicle is quite static
- − The man's right hand has some minor anatomical distortion near the pedal
Verdict: FLUX.2 [dev] Turbo followed the complex technical prompt requirements more closely, particularly the motion blur and environmental details of the rain. Qwen Image 2.0 captured a more grounded, naturalistic portrait of the man, but failed to include the requested motion blur and felt less atmospheric overall.
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 texture on the engraved armor and weathered leather straps.
- + Masterful use of lighting with the torchlight casting realistic glows on the face.
- + Precisely followed the request for hair braided with small beads and faint scars.
- − The torch in the background is a bit blurry/simple compared to the foreground detail.
Qwen Image 2.0
- + Strong 'battle-worn' character design with prominent scarring.
- + Good use of color contrast between the red tunic and silver plate armor.
- + Interesting interpretation of the hair braids with larger, ornate beads.
- − Anatomical issues with the hand resting on the sword, featuring unnatural finger lengths.
- − The background fire is slightly overexposed, losing the 'warm torchlight' subtlety of the prompt.
- − The eyes look somewhat glassy and less lifelike than the other model.
Verdict: FLUX.2 [dev] Turbo provided a much higher level of technical execution, particularly in the rendering of textures and realistic skin details. While Qwen Image 2.0 captured the character's weariness well, it suffered from noticeable anatomical errors in the hand and less refined lighting. FLUX.2 adhered more closely to the 'lifelike eyes' and 'heavy texture' requirements.
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, readable sans-serif fonts
- + Professional layout that mimics a real-world document with hierarchies
- + Vibrant color accents that add to the modern aesthetic
- − Sectioning is a bit cluttered with images and text overlapping incorrectly in the 'Mains' area
- − Highly repetitive pizza images in the grid section
Qwen Image 2.0
- + Perfectly balanced 3x3/3x4 grid structure
- + Clear categorization of food types matching the prompt sections
- + High-quality, distinct food photography for every item
- − Text rendering is distorted and illegible (gibberish characters)
- − Lacks the 'design' elements like descriptions and price variety seen in Model A
Verdict: FLUX.2 [dev] Turbo produces a much more realistic menu design with professional typographic hierarchy and layout elements, though its image grid is somewhat messy. Qwen Image 2.0 follows the grid request more strictly and provides better variety in food photos, but fails significantly on text legibility. FLUX.2 [dev] Turbo is the preferred choice for a design-focused task due to its superior handling of fonts and composition.
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 fiery effects on all elements.
- + Perfectly follows the 'exploded' instruction with clear gaps between every layer.
- + High-quality rendering of individual food textures like the patty and lettuce.
- − The sauce droplets look slightly detached and artificial.
Qwen Image 2.0
- + Strong 'fiery' atmosphere with good use of smoke and embers.
- + Crisp text rendering for the main title and price.
- + Appetizing food photography style with realistic lighting on the cheese.
- − Failed the 'exploded' instruction as the core ingredients (cheese, patty, tomato) are still stacked.
- − The 'Limited Time Only' text is small and lacks the requested fiery/glowing effect.
Verdict: FLUX.2 [dev] Turbo clearly wins this comparison as it followed the 'exploded burger' requirement much better than Qwen Image 2.0, which produced a mostly assembled burger. Additionally, FLUX.2 applied the requested fiery effect to all text elements, whereas Qwen left the secondary text in a plain font.
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 chalk texture with realistic dusty smudges and varying opacity.
- + Near-perfect spelling of long, complex menu items.
- + Highly consistent and realistic handwriting style across all text elements.
- − Repeat text artifacts on the price lines (e.g., '9' and then '$9').
- − The Title text is not quite 'elegant cursive' as requested, leaning more towards a stylized print.
Qwen Image 2.0
- + Strong adherence to the layout on a green chalkboard with good background atmosphere.
- + Legible text with clear spacing between items.
- + Successfully interpreted the 'Brown But...' prompt fragment into a complete item.
- − Text lacks the realistic powdery chalk texture, appearing somewhat flat like a thin marker.
- − Some letters have unnatural digital-looking artifacts or inconsistent strokes.
- − The title font is a simple print rather than the requested elegant cursive.
Verdict: FLUX.2 [dev] Turbo produces a much more convincing chalk texture and a consistent handwriting style that truly feels handwritten rather than generated. While Qwen Image 2.0 provides a clean and legible layout, it lacks the specific textural details and realistic smear effects found in the FLUX.2 image.
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 anatomical detail on the horse and space suit
- + Cinematic lighting with a realistic atmospheric glow over the Earth
- + High resolution texture work on the leather tack and space equipment
- − The prompt requested 'horse on top', implying a subversion of the typical 'astronaut on horse' image, which was missed
Qwen Image 2.0
- + Vibrant, colorful space background with varied nebulae
- + Dynamic pose of the horse creates a sense of movement in zero-G
- + The reflection in the visor adds a nice level of detail
- − Failed to follow the 'horse on top' spatial instruction
- − Slightly less realistic rendering compared to Model A, appearing more like a digital painting
Verdict: Both FLUX.2 [dev] Turbo and Qwen Image 2.0 failed the specific spatial logic of the prompt ('horse on top'), instead providing the common 'astronaut riding a horse' interpretation. FLUX.2 [dev] Turbo is the winner due to superior technical execution, featuring more sophisticated lighting, realistic textures, and better composition.
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 in the textures of the capybara's fur and the taxi's exterior.
- + Accurate composition with the passenger in the back seat as requested.
- + The lighting on the character faces and steering wheel feels very natural for a city night.
- − The passenger is sitting in the front passenger seat rather than the back seat.
Qwen Image 2.0
- + Dynamic angle that captures the interior of the car and the driver's perspective well.
- + Good rendering of the capybara's professional expression and clothing.
- − The human passenger is seated in the front passenger seat instead of the back seat.
- − The hands/paws on the steering wheel have anatomical issues and look distorted.
- − The overall image quality has a slightly more artificial, high-contrast digital look compared to the other model.
Verdict: Both models failed to place the human passenger in the back seat, instead placing her in the front passenger seat. However, FLUX.2 [dev] Turbo produced a much more convincing and photorealistic image with better lighting and surface textures. Qwen Image 2.0 struggled with the rendering of the paws and had a more over-processed aesthetic.
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 including fine details.
- + Integrated composition where the border, background, and center object blend naturally.
- + Consistent gothic art style across all elements including the background texture.
- − The scroll banner is somewhat small and less prominent compared to the main title.
- − The overall image is slightly darker, making the thorn details less crisp.
Qwen Image 2.0
- + Excellent cinematic lighting on the jack-o-lantern and surrounding environment.
- + Higher contrast and sharper detail on the thorn border and twisted trees.
- + Clearer distinction between the foreground parchment and backgroud scene.
- − Minor text error: 'time' has a stray artifact on the letter 'T'.
- − The composition feels slightly more like a collage than a single cohesive piece of parchment.
Verdict: Both models followed the prompt exceptionally well, rendering all text accurately and capturing the gothic aesthetic. FLUX.2 [dev] Turbo offers a more cohesive and authentic vintage feel with its integrated parchment texture, while Qwen Image 2.0 provides more dramatic cinematic lighting and sharper visual clarity. FLUX.2 is slightly preferred for its flawless typography and better compositional balance.
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 miniature aesthetic with highly realistic PBR material textures for the wood and fish.
- + Superior typography integration and flag placement following the prompt instructions.
- + Very clean rendering with soft, appealing lighting.
- − The 45-degree isometric angle is slightly off, appearing more like a standard perspective view.
Qwen Image 2.0
- + Stronger variety of sushi types presented on the plate.
- + Good adherence to the flat light blue background and layout requirements.
- − The text 'JAPAN' is not at the top-center relative to the flag, and the flag icon is overly large.
- − The visual quality looks more like a standard photo than the requested 'miniature 3D cartoon scene'.
- − Material textures are less refined and look slightly generic compared to Model A.
Verdict: FLUX.2 [dev] Turbo followed the stylistic cues and typography requirements much better, producing a sophisticated 3D miniature look with excellent materials. Qwen Image 2.0 provided more variety in the subject matter but failed to capture the 'refined 3D cartoon' aesthetic, looking more like a basic composite image.
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 atmospheric god rays.
- + Captures all four requested animals with distinct, expressive facial features.
- + Superior dynamic interaction between the animals conveying a 'playful' vibe.
- − The fox's ear structure is slightly unusual.
- − The butterfly on the far right has slightly simplified wings.
Qwen Image 2.0
- + Beautiful warm lighting and soft backlighting on the fur.
- + Accurate species identification for all four baby animals.
- + High level of detail in the surrounding wildflowers.
- − The fox looks significantly smaller and is partially flattened under the cat.
- − Noticeable anatomy error where the cat's paw overlaps with the dog's paw in a muddled way.
- − The butterfly on the right has an anatomically incorrect body attached directly to the wing edge.
Verdict: FLUX.2 [dev] Turbo produces a more cohesive and joyful scene with better animal anatomy and a more magical atmosphere through the use of dew sparkles. While Qwen Image 2.0 has lovely lighting, it suffers from several anatomical merging issues where the animals touch and the butterfly rendering is less refined.
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 execution of the vintage texture and light background requested in the prompt.
- + Excellent typography with accurate accents and a high-quality vector style.
- + Balanced composition with a classic emblem layout.
- − The steam is a bit thin and simple compared to the rest of the logo.
Qwen Image 2.0
- + Clean, legible typography.
- + Good use of the requested warm brown and cream color palette.
- − The 'Est. 1720' text is placed outside the main banner element rather than inside it.
- − The steam appears as if it is inside the solid cloche rather than coming off it.
- − Lacks the subtle texture requested for the background and logo.
Verdict: FLUX.2 [dev] Turbo followed the prompt much more effectively, delivering a cohesive 'vintage minimalist' aesthetic with the text correctly placed inside the banner. Qwen Image 2.0 struggled with the spatial logic of the steam and banner, and failed to incorporate the requested texture.
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 typography and nearly perfect spelling of names and stages.
- + Highly detailed illustrations of the Saturn V and Lunar Module.
- + Effective use of the requested NASA-inspired color palette.
- − The layout is cluttered and repetitive, with 'Translunar' and 'Tranquility' appearing twice.
- − Failed to follow the logical sequential order of the infographic, scattering icons across the canvas.
Qwen Image 2.0
- + Strong linear composition that follows the mission steps chronologically from top to bottom.
- + Clean, minimalist flat-vector aesthetic that adheres well to the style request.
- + Includes all requested steps in a clear, easy-to-read hierarchy.
- − Minor typo in 'Translunjar'.
- − Icon styles are slightly inconsistent, with the lunar module being more detailed than the minimalist ship in the launch phase.
Verdict: While FLUX.2 [dev] Turbo provides much higher detail in its individual illustrations and better text rendering, it fails as an infographic because the layout is chaotic and repetitive. Qwen Image 2.0 captures the spirit of a vector infographic much better, presenting a clear, logical progression of the mission steps despite a single typo.
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