Head to head
Esc

Models · slot A

to navigate to pick

FLUX.1 [schnell] Black Forest Labs Vidu Q2 ShengShu Technology

Settled by community votes across 13 shared challenges, with an AI judge weighing in on each.

FLUX.1 [schnell]

19.2 arena score

#44 of 62 in Text-to-Image

Skill signature · Text-to-Image

Vidu Q2

19.8 arena score

#42 of 62 in Text-to-Image

Vote tally

Where the votes landed

FLUX.1 [schnell]

100.0%

win rate

Ties

0.0%

Vidu Q2

0.0%

win rate

100.0% 0.0% ties 0.0%
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.”

FLUX.1 [schnell]
Vidu Q2
100% wins 0% ties 0% wins

AI Judge Analysis

FLUX.1 [schnell]

  • + Excellent photorealistic rendering of the Monstera plant foliage.
  • + Very clean and modern aesthetic with smooth lighting.
  • + Interesting artistic choice to have the blue sphere floating.
  • Failed the spatial prompt by adding an extra blue sphere on top of the book.
  • The sphere inside the cube is quite large, contradicting the 'small' descriptor.
  • The plant is mostly above rather than behind the cube.

Vidu Q2

  • + Perfect adherence to the spatial arrangement described in the prompt.
  • + Superior glass refractive effects showing the plant through the cube walls.
  • + Excellent lighting and shadow work that matches the 'left window light' request.
  • The glass cube has slightly thick, green-tinted edges that might be less desirable for some users.
  • The shadow of the plant on the table is a bit harsh compared to Model A's soft light.

Verdict: Vidu Q2 produced a much more accurate result by following every spatial instruction, specifically placing the sphere inside and the book on top without adding extra elements. FLUX.1 [schnell] struggled with the logic of the scene, adding a second sphere on top of the book and making the internal sphere too large, though it had a very pleasing soft-focus aesthetic.

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.”

FLUX.1 [schnell]
Vidu Q2

AI Judge Analysis

FLUX.1 [schnell]

  • + Natural skin texture and realistic color palette.
  • + Excellent street atmosphere with accurate reflections.
  • Lack of motion blur on passing vehicles as requested.
  • The bicycle geometry is slightly stylized and clean.

Vidu Q2

  • + Stronger adherence to the imperfect framing and candid request.
  • + Good depiction of the mechanical repair action.
  • Anatomical issues with hand and face merging with bicycle parts.
  • Missing the motion blur for passing cars.

Verdict: FLUX.1 [schnell] creates a more cohesive and visually pleasing image with high anatomical accuracy and a professional cinematic look. Vidu Q2 captures the candid framing and grit of the prompt better but suffers from significant biological and mechanical glitches.

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.”

FLUX.1 [schnell]
Vidu Q2

AI Judge Analysis

FLUX.1 [schnell]

  • + Extremely high-detail skin texture and pores
  • + Intense, lifelike eye rendering
  • + Strong adherence to the shallow depth of field request
  • Crop is too tight, obscuring most of the armor and clothing details requested
  • Braid beads are less distinct compared to the other model

Vidu Q2

  • + Excellent depiction of ornate engraved plate armor and leather straps
  • + Clear inclusion of beads in the braids
  • + Beautiful bokeh sparks and lighting balance
  • Skin texture is slightly smoother and less realistic than its competitor
  • Slightly less 'close' than a traditional close portrait, though better for showing armor

Verdict: While FLUX.1 [schnell] captures incredible facial detail and a more intimate expression, Vidu Q2 is the superior overall image as it successfully integrates all elements of the prompt, including the engraved armor and detailed leather straps which are mostly cut out of the first image. Vidu Q2 also excels at lighting, creating a more cinematic scene with visible sparks and well-defined hair accessories.

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.”

FLUX.1 [schnell]
Vidu Q2

AI Judge Analysis

FLUX.1 [schnell]

  • + Excellent typography rendering with readable header text.
  • + Balanced white space and clean minimalist layout.
  • + Accurate adherence to requested menu sections.
  • Internal food photos are repetitive and look slightly generic.
  • Body text under the headers is gibberish upon close inspection.

Vidu Q2

  • + Successfully uses vibrant color accents as requested.
  • + High quality and varied food photography.
  • + Dynamic layout that feels modern and professional.
  • Poor text rendering with numerous spelling errors in headers (e.g., 'Apecizen').
  • Layout feels a bit cluttered compared to the minimalist request.
  • Inconsistent font styles and sizes create visual noise.

Verdict: FLUX.1 [schnell] creates a much more functional and aesthetically pleasing minimalist design, effectively balancing white space and legible typography. While Vidu Q2 captures the 'vibrant' and 'modern' aspects well with its photography and accents, its failure to render coherent text and its cluttered layout make it less effective as a professional menu design.

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.”

FLUX.1 [schnell]
Vidu Q2

AI Judge Analysis

FLUX.1 [schnell]

  • + Excellent photorealistic texture on the meat and bun
  • + Clean, professional lighting setup
  • + Artistic ember and smoke effects in the background
  • Failed to render the full text correctly ('AGIC BURGER')
  • Did not follow the 'exploded' instruction, keeping the burger mostly intact
  • Confusion in price rendering with multiple conflicting numbers

Vidu Q2

  • + Successfully rendered the 'exploded' structure with suspended components
  • + Text is fully accurate and features the requested fiery glow
  • + Better adherence to the 'starburst' and 'fiery background' requests
  • The currency symbol is distorted and does not clearly look like the Euro sign
  • Visual quality is slightly more 'digital' and less photorealistic than its competitor

Verdict: While FLUX.1 [schnell] has superior textures and realism, it failed significantly on the layout and text accuracy. Vidu Q2 followed the complex instructions for an 'exploded' view and rendered all text strings correctly with the requested effects, making it the better advertisement overall.

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.”

FLUX.1 [schnell]
Vidu Q2

AI Judge Analysis

FLUX.1 [schnell]

  • + Clean layout with clear spacing
  • + Excellent legibility of shorter words
  • + Captures the chalkboard frame and café background effectively
  • Major spelling errors in key menu items (e.g., 'Taffle Mushmnctionm')
  • Missing 'April' in the date (rendered as 'Pril')
  • Handwriting lacks the 'elegant cursive' style requested for the title

Vidu Q2

  • + Successfully renders 'APRIL' correctly in the date
  • + Includes realistic chalk smudging and dust texture on the board
  • + Attempts the elegant cursive and stylized handwriting requested
  • Numerous spelling errors consistent with AI hallucinations (e.g., 'Browd Botter')
  • Visual overlapping of letters makes some lines difficult to read
  • Incorrect price for the first item ($34 instead of $24)

Verdict: Both models struggled with the complex spelling of the menu items, though FLUX.1 [schnell] produced a cleaner, more legible layout despite significant word distortions. Vidu Q2 captured the 'chalk texture' and 'elegant cursive' aesthetics much more accurately than FLUX.1 [schnell], but its tendency to overlap text and hallucinate spellings made it less functional as a menu.

The Reversed Rodeo

Text-to-Image

“Horse riding astronaut in space — horse on top, not vice versa. Surreal, highly detailed, cinematic.”

FLUX.1 [schnell]
Vidu Q2

AI Judge Analysis

FLUX.1 [schnell]

  • + Followed the specific instruction to place the horse on top of the astronaut.
  • + Excellent cinematic lighting and high-quality textures on the space suit and horse hide.
  • + Successfully captured the surreal nature of the prompt.
  • The horse has a chaotic anatomy with two heads.
  • The astronaut's body structure is somewhat confusing and disjointed.

Vidu Q2

  • + Vibrant and colorful cosmic aesthetic with a nebular horse texture.
  • + Clear, well-defined astronaut suit and anatomical horse structure.
  • Completely failed the negative constraint to put the horse on top.
  • Generic 'astronaut on horse' interpretation which ignores the specific surreal instruction.

Verdict: FLUX.1 [schnell] followed the difficult spatial instruction to have the horse riding the astronaut, whereas Vidu Q2 defaulted to the standard trope of an astronaut riding a horse. Despite FLUX.1 [schnell] generating a two-headed horse, its adherence to the surreal prompt makes it the more successful image for this specific challenge.

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.”

FLUX.1 [schnell]
Vidu Q2

AI Judge Analysis

FLUX.1 [schnell]

  • + Excellent fur texture rendering
  • + Cinematic lighting consistent with a cab interior at night
  • + High text legibility on the cap
  • The capybara's anatomy is slightly distorted to fit the seat
  • Only one paw is clearly on the steering wheel, failing that prompt detail

Vidu Q2

  • + Perfectly adheres to the 'both front paws on the steering wheel' instruction
  • + Realistic taxi driver cap design with a badge
  • + Clearer composition showing the distance between the driver and passenger
  • The capybara's hands look more like human/monkey hands than capybara paws
  • Lower resolution/clarity in the passenger's facial features

Verdict: FLUX.1 [schnell] produced a more visually striking and atmospheric image with superior textures, but it failed to place both paws on the steering wheel. Vidu Q2 followed the anatomical instructions more closely and provided a better spatial perspective of the taxi interior, though the hands look unnervingly primate-like.

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.”

FLUX.1 [schnell]
Vidu Q2

AI Judge Analysis

FLUX.1 [schnell]

  • + Strong composition with a polished, modern vector art feel.
  • + Includes most required text fields accurately despite layout redundancy.
  • + Captures the moody night sky and twisted trees effectively.
  • Repeated and garbled text elements at the bottom of the poster.
  • The 'parchment' texture is missing, opting for a clean digital background instead.

Vidu Q2

  • + Excellent adherence to the 'dark parchment' and vintage gothic aesthetic.
  • + Superior intricate border work with detailed spider webs and thorns.
  • + High-quality, realistic lighting and textures on the jack-o-lantern.
  • Several spelling errors in the title and banner text.
  • The date provided (30.70.2025) is incorrect/invalid.

Verdict: Vidu Q2 better captures the requested aesthetic with a beautiful vintage parchment texture and detailed gothic borders, though it struggles with exact spelling. FLUX.1 [schnell] is much more accurate with its legible text, but it fails to deliver the 'parchment' style and creates a cluttered, redundant layout for the event details. Vidu Q2 is preferred for its superior visual atmosphere which fits the 'vintage gothic' prompt more authentically.

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.”

FLUX.1 [schnell]
Vidu Q2

AI Judge Analysis

FLUX.1 [schnell]

  • + Excellent clean isometric composition
  • + Sharp rendering of the diorama base and materials
  • + Very clean, professional aesthetic
  • Failed to include the word 'SUSHI' in text
  • Texture on the sushi is a bit flat compared to the base

Vidu Q2

  • + Followed all text instructions including 'JAPAN' and 'SUSHI'
  • + Vibrant colors and a more varied selection of sushi
  • + High-quality 3D clay-like textures
  • The 'flag' is oddly attached to the letter 'N'
  • The text is slightly off-center and the flag is not a standard icon format

Verdict: Vidu Q2 is the winner because it followed all text requirements, whereas FLUX.1 [schnell] missed the word 'SUSHI' entirely. While FLUX.1 [schnell] produced a cleaner, more minimalist render that felt more like a professional UI element, Vidu Q2 capture the 'cartoon' and 'miniature' aspect of the prompt with better adherence to the specific content requested.

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.”

FLUX.1 [schnell]
Vidu Q2

AI Judge Analysis

FLUX.1 [schnell]

  • + Very high detail on the fur textures of the puppy and kit.
  • + Effective use of warm golden hour lighting and bokeh.
  • + Clear, high-quality rendering of the characters in the foreground.
  • Failed to include a rabbit in the scene.
  • The animal in the middle appears to be a kitten/bunny hybrid with confusing anatomy.
  • Lacks the sense of dynamic movement and 'tumbling' requested.

Vidu Q2

  • + Excellent adherence to the prompt, including all four specific animals.
  • + Dynamic composition that captures the 'playfully chasing' and 'tumbling' action better.
  • + Successfully incorporates the requested 'god rays' and dew sparkles in the meadow.
  • The fox kit's face is slightly less detailed and looks more like a toy.
  • Overall image has a slightly more saturated, 'AI-illustrated' look compared to a photograph.

Verdict: Vidu Q2 is the clear winner because it actually included all the animals requested in the prompt, including the baby bunny and the tabby kitten which FLUX.1 [schnell] missed or merged. Vidu Q2 also captured the action of chasing and tumbling, whereas FLUX.1 [schnell] produced a more static, posed portrait.

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.”

FLUX.1 [schnell]
Vidu Q2

AI Judge Analysis

FLUX.1 [schnell]

  • + Strong vector emblem style consistency
  • + Clean and professional graphic layout
  • + Excellent color palette adhering to the 'warm brown and cream' request
  • Significant spelling error ('FRAMILAN' instead of 'Florian')
  • Incorrect year in the date ('7720' instead of '1720')
  • Missing the 'steam' element requested in the prompt

Vidu Q2

  • + Includes the steam element inside the cloche
  • + Subtle texture on the background matches the prompt well
  • + Successfully hit the requested year '1720'
  • Nonsensical text and multiple spelling errors ('FARMIIN', 'Esttt', 'FOPLi20')
  • Inconsistent and messy typography with overlapping characters
  • The cloche handle is poorly rendered with artifacts

Verdict: Both models failed significantly on typography and spelling, which is critical for a logo prompt. FLUX.1 [schnell] produced a much cleaner, professionally balanced vector design, despite the spelling and date errors. Vidu Q2 followed the prompt's details better (including the steam) but the technical execution of the text and graphic elements was cluttered and messy.

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.”

FLUX.1 [schnell]
Vidu Q2

AI Judge Analysis

FLUX.1 [schnell]

  • + Strong aesthetic composition with a professional, navy-based color palette.
  • + Excellent flat vector style that feels like a modern infographic.
  • + High visual clarity and balance in the layout.
  • Text is largely gibberish and illegible.
  • Failed to clearly represent the specific 6-step sequence requested in the prompt.

Vidu Q2

  • + Successfully captured most of the requested icons including the landing sequence.
  • + Follows the step-by-step layout instruction much more closely.
  • + Text is larger and more legible, even if heavily misspelled.
  • Composition is cluttered and less artistic than Model A.
  • Includes extraneous elements like a red map pin and half-numbered steps.
  • The flat vector style is slightly less refined with inconsistent line weights.

Verdict: FLUX.1 [schnell] produced a much more visually appealing and professional-looking poster that perfectly matches the requested NASA color palette, but it failed to follow the logical structure of the mission steps. Vidu Q2 followed the prompt's structural requirements for the six specific steps and icons much more accurately, despite having a more cluttered layout and numerous spelling errors. Vidu Q2 is the winner for better prompt adherence to the complex list of requirements.

Next steps

Explore each model