Head to head
Esc

Models · slot A

to navigate to pick

FLUX.1 Krea [dev] 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 Krea [dev]

19.1 arena score

#47 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 Krea [dev]

0%

win rate

Ties

0%

Vidu Q2

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.”

FLUX.1 Krea [dev]
Vidu Q2

AI Judge Analysis

FLUX.1 Krea [dev]

  • + Excellent adherence to lighting instructions with realistic soft window light from the left.
  • + Highly realistic textures on the glass, wooden table, and leather book.
  • + Sophisticated color palette and realistic depth of field.
  • The plant in the background is quite dark and blurry, making it less distinct.
  • The sphere has a heavy reflection that slightly confuses its form.

Vidu Q2

  • + Perfect adherence to all spatial requirements, including plant visibility through the glass.
  • + Crisp details on the fern and the wooden table grain.
  • + Clear representation of all requested objects with vibrant colors.
  • The lighting feels more like direct sunlight from the right/top rather than 'soft window light from the left'.
  • The glass cube edges appear slightly glowing and neon, which looks less realistic.

Verdict: FLUX.1 Krea [dev] produces a much more cinematic and photographic image that perfectly captures the requested lighting mood, though the plant is very subtle. Vidu Q2 is more successful at showing the plant through the glass as requested, but it fails the specific lighting direction prompt and has a less realistic 'digital' look. FLUX.1 Krea [dev] is the winner for its superior aesthetic quality and lighting accuracy.

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 Krea [dev]
Vidu Q2

AI Judge Analysis

FLUX.1 Krea [dev]

  • + Excellent street photography composition that captures the environment
  • + Realistic rain effects and convincing pavement reflections
  • + Follows the motion blur request for background vehicles
  • The man is holding the bike rather than actively repairing it
  • The bicycle design is a bit simplified and generic

Vidu Q2

  • + Successfully captures the specific action of repairing the bike chain
  • + Excellent natural skin texture and fine detail on the hands
  • + Strong adherence to the 'imperfect framing' and 'shallow depth of field' prompts
  • The hands and bike chain have moderate AI artifacts and anatomical warping
  • Lack of background motion blur for the car
  • The bicycle frame geometry is slightly broken near the seat post

Verdict: FLUX.1 Krea (dev) produces a more aesthetically pleasing 'candid street' photo with great environment work, but it misses the 'repairing' action. Vidu Q2 captures the repair task much more accurately and with more realistic skin texture, despite some technical artifacts in the complex areas of the chain and hands. Vidu Q2 is preferred for following the specific narrative of the prompt while maintaining a more realistic, less 'digitally smooth' feel.

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 Krea [dev]
Vidu Q2

AI Judge Analysis

FLUX.1 Krea [dev]

  • + Expertly rendered cinematic lighting with realistic bokeh sparks.
  • + Superior engraving detail on the plate armor.
  • + Excellent skin texture and subtle battle-worn details that look lifelike.
  • The beads in the hair are less prominent than those in Model B.
  • The portrait is slightly more centered and static compared to Model B.

Vidu Q2

  • + Dynamic character posing and hair braiding with clear bead details.
  • + High-contrast lighting that emphasizes the metallic surfaces and leather straps.
  • + Crisp texture on the cloth underlayer and leather buckles.
  • The skin has a slightly more 'digital' or smoothed appearance compared to Model A.
  • The bokeh sparks are less convincing and feel more like generic light spots.

Verdict: FLUX.1 Krea (dev) produces a much more realistic and cinematic portrait with superior skin textures and sophisticated lighting that truly feels 'battle-worn'. Vidu Q2 offers excellent detail on the equipment, particularly the leather and buckles, but it lacks the organic lifelike quality found in the eyes and skin of the FLUX image.

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 Krea [dev]
Vidu Q2

AI Judge Analysis

FLUX.1 Krea [dev]

  • + Excellent professional layout following the grid request
  • + Cleaner typography that feels more realistic to a design template
  • + Consistent orange accents that provide a cohesive visual identity
  • Repetitive category headers (Appetizers listed twice)
  • Text characters become garbled and illegible in the smaller descriptions

Vidu Q2

  • + Stronger use of vibrant color accents through the whole composition
  • + Better categorization including the requested 'Pizza' section
  • + High-quality, distinct food photography for each item
  • Layout is a bit cluttered and lacks the professional whitespace of a minimalist design
  • Significant text distortion and spelling errors in the headers
  • Inconsistent font weights and styles produce a messy look

Verdict: FLUX.1 Krea [dev] produces a much more realistic and professional design layout that correctly interprets 'minimalist', though it fails to include all specific requested sections like 'pizza'. Vidu Q2 includes more variety in the food and categories but suffers from a cluttered composition and more significant text artifacts. FLUX.1 Krea is the preferred model for a design-centric task where layout hierarchy and cleanliness are key.

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 Krea [dev]
Vidu Q2

AI Judge Analysis

FLUX.1 Krea [dev]

  • + Excellent photorealistic texture on the bun and meat patty
  • + Crisp, clean typography that is easy to read
  • + Atmospheric lighting with embers in the foreground
  • Failed to render the fiery/glowing effect on the text
  • The €6.99 is not in a starburst as requested
  • Minor AI hallucinations in the small secondary text at the bottom

Vidu Q2

  • + Adhered strongly to the 'fiery, glowing' text requirement
  • + Included the price within a starburst graphic
  • + Highly dynamic composition with sauce droplets and intense fire
  • Incorrectly rendered the currency symbol (looks like a hash or double-barred E)
  • The lettuce and sauce look somewhat plastic compared to the other model

Verdict: FLUX.1 Krea (dev) produces a higher quality, more realistic image with professional typography, though it missed several specific styling cues from the prompt like the starburst and glowing text. Vidu Q2 followed the prompt's creative instructions for fiery text and starburst placement much better but struggled with the specific currency symbol and overall realism. FLUX.1 Krea (dev) is the likely winner for its superior visual polish and legible text.

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 Krea [dev]
Vidu Q2

AI Judge Analysis

FLUX.1 Krea [dev]

  • + Excellent text legibility and clean formatting.
  • + Very aesthetically pleasing wooden frame and realistic shadowing.
  • + Consistent cursive style for the menu items.
  • Hallucinates multiple menu items instead of following the list precisely.
  • Text feels a bit too clean and uniform, lacking a gritty chalk texture.
  • Several words become garbled towards the end of the menu items.

Vidu Q2

  • + Superior chalk texture with realistic dusty strokes and tapered lines.
  • + Better adherence to the requested cozy café background setting.
  • + Captured the 'natural variations' in letter size and spacing very well.
  • Significant spelling errors throughout the menu items.
  • The cursive is less elegant than requested for the title.
  • Price for the first item is incorrect based on the prompt.

Verdict: FLUX.1 Krea (dev) produces a much cleaner and more professional-looking image with high legibility, though it deviates from the prompt by adding extra menu items. Vidu Q2 captures the requested chalk texture and 'handwritten' feel much more accurately, but it suffers from poor spelling and messy legibility. FLUX.1 Krea is preferred for overall quality, while Vidu Q2 is better for specific texture adherence.

The Reversed Rodeo

Text-to-Image

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

FLUX.1 Krea [dev]
Vidu Q2

AI Judge Analysis

FLUX.1 Krea [dev]

  • + Successfully followed the difficult logic of 'horse on top' of the astronaut.
  • + High cinematic realism with believable lighting from the planet below.
  • + Clever integration of space-tech gear on the horse's torso.
  • The horse's hind legs are somewhat awkwardly merged with the astronaut's lower body.
  • The background is very sparse compared to the subject detail.

Vidu Q2

  • + Beautiful, vibrant color palette with ethereal nebula effects.
  • + High level of detail on the astronaut's suit and the horse's cosmic coat.
  • + Excellent composition and dynamic posing.
  • Completely failed the negative constraint/positional instruction; showing the astronaut on top.
  • The horse's front-right leg has an anatomical distortion at the joint.

Verdict: This challenge was a test of prompt adherence regarding spatial relationships. FLUX.1 Krea [dev] is the clear winner as it successfully depicted the 'horse on top' of the astronaut as requested, whereas Vidu Q2 completely ignored that specific instruction and produced a standard 'astronaut riding a horse' image. While Vidu Q2 had more vibrant colors, it failed the core requirement of the prompt.

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 Krea [dev]
Vidu Q2

AI Judge Analysis

FLUX.1 Krea [dev]

  • + Excellent fur texture and lighting integration
  • + Captures a very calm and natural 'professional' expression on the capybara
  • + High photographic realism in the car's exterior paint and lighting
  • Includes an extra person in the front passenger seat which was not requested
  • The capybara's paws are somewhat fused with the steering wheel
  • The perspective makes the car interior feel a bit cramped and illogical

Vidu Q2

  • + Perfect adherence to the single passenger and capybara driver layout
  • + Captures the bored expression of the businesswoman very well
  • + Better rendering of the capybara's hands/paws on the wheel
  • The capybara head looks slightly 'photoshopped' onto a human body/jacket
  • The background/street scene looks a bit more like a stage set than a real city night
  • The lighting inside the car is a bit too bright and flat for a night scene

Verdict: Vidu Q2 followed the prompt instructions more accurately by including only one passenger and clearly showing the Bored businesswoman on her phone. While FLUX.1 Krea had superior texture and more realistic automotive lighting, it hallucinated a second passenger and failed to clearly separate the driver's front paws.

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 Krea [dev]
Vidu Q2

AI Judge Analysis

FLUX.1 Krea [dev]

  • + Excellent atmospheric lighting and clean, spooky aesthetic
  • + Higher visual quality in terms of illustration style and borders
  • + Captures the moody night sky more effectively
  • Several typos in the text including 'Pasty Halloween' and 'nights frights'
  • Formatting of the details is messy and repetitive

Vidu Q2

  • + Layout follows the parchment poster request more literally
  • + Better inclusion of the 'thorns' element in the border
  • + Text is generally more readable even with spelling errors
  • Multiple spelling errors in the main title and subtext
  • Date is incorrect (30.70.2025)
  • The overall image feels a bit more cluttered and less cohesive

Verdict: FLUX.1 Krea [dev] produces a much more polished and professional-looking illustration with superior lighting, although it fails significantly on the main title text. Vidu Q2 follows the 'parchment' and 'thorns' prompt more closely but suffers from messy typography and a non-existent date. FLUX.1 Krea [dev] is the likely winner for its artistic quality despite the text issues.

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 Krea [dev]
Vidu Q2

AI Judge Analysis

FLUX.1 Krea [dev]

  • + Excellent adherence to the 'minimal' request with a single, high-quality sushi piece.
  • + Clean, modern typography that integrates well with the 3D scene.
  • + Superior lighting and shadowing that creates a professional 3D render feel.
  • The salmon texture looks slightly plastic-like, though it fits the cartoon aesthetic.

Vidu Q2

  • + Includes a variety of sushi types which fills the scene well.
  • + Good color contrast between the dark text and the light blue background.
  • The flag is floating awkwardly above the text instead of being a small icon within the scene.
  • The 'diorama base' has strange, blob-like artifacts on the corners.
  • The isometric perspective is slightly inconsistent compared to the perfectly calculated angle in Model A.

Verdict: FLUX.1 Krea [dev] followed the prompt more accurately, particularly regarding the 'minimal' aesthetic and clean layout. While Vidu Q2 provided more variety in the food items, it suffered from strange artifacts on the base and a less cohesive integration of the text and flag. FLUX.1 Krea [dev] produced a much more professional and polished 3D diorama look.

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 Krea [dev]
Vidu Q2

AI Judge Analysis

FLUX.1 Krea [dev]

  • + Excellent high-detail fur texture and lighting.
  • + Clean composition with a beautiful bokeh effect.
  • + Accurate and expressive animal features.
  • Missed the baby bunny entirely, providing two kittens instead.
  • Butterflies feel slightly static compared to the movement in the scene.

Vidu Q2

  • + Successfully included all four requested animals (dog, cat, bunny, fox).
  • + High level of dynamic movement and 'tumbling' action.
  • + Vibrant lighting with many distinct butterflies and wildflowers.
  • Noticeable anatomical issues with the second puppy's rear legs.
  • The facial features of the animals are less refined and looks more like CGI than hyper-photorealism.
  • The composition feels a bit cluttered with too many overlapping elements.

Verdict: FLUX.1 Krea produced a much more realistic and aesthetically pleasing image with superior fur rendering and lighting, but it failed to follow the prompt's count of animals. Vidu Q2 followed the prompt's list of subjects perfectly but suffered from anatomical artifacts and a less realistic, more illustrative style. FLUX.1 Krea is the winner for visual quality, even with the missing bunny.

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 Krea [dev]
Vidu Q2

AI Judge Analysis

FLUX.1 Krea [dev]

  • + Excellent vintage engraving style with high-quality cross-hatching.
  • + Strong adherence to the 'cloche dome with steam' request.
  • + Superior layout and balanced composition for an emblem.
  • Misspelled the name as 'Café Flanelín' instead of 'Caffè Florian'.
  • Added extra nonsensical text at the bottom.

Vidu Q2

  • + Clean vector-style execution.
  • + Good use of warm brown and cream tones.
  • + Closer to the request for a minimalist aesthetic.
  • Numerous severe spelling errors ('Esttt', 'Farmiin', 'Caffce').
  • Included redundant, poorly rendered text at the bottom.
  • The cloche handle is poorly integrated with the steam.

Verdict: While both models failed to spell the brand name correctly, FLUX.1 Krea produced a much more professional and aesthetically pleasing design that perfectly captured the requested vintage texture and line-art style. Vidu Q2 followed the minimalism prompt better but suffered from significant typographic glitches and a less coordinated composition.

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 Krea [dev]
Vidu Q2

AI Judge Analysis

FLUX.1 Krea [dev]

  • + Excellent large-scale typography for the main title.
  • + High-contrast color palette consistent with the NASA-inspired theme.
  • + Clean, modern flat vector aesthetic across the layout.
  • Nonsensical iconography including Saturn (not Earth) with red rings and mysterious groups of four figures.
  • Steps do not correspond to the requested logic (e.g., jumping from Earth to spacesuits).
  • Text beneath icons is garbled and unreadable.

Vidu Q2

  • + Better icon relevance, including a rocket, lunar modules, and planetary bodies.
  • + Well-balanced grid layout typical of a modern infographic.
  • + Consistently clean vector style with pleasant subtle gradients.
  • Severe spelling hallucinations, failing to correctly spell 'Apollo' or the step labels.
  • Icon for Earth and Moon are very similar in style, leading to visual confusion.
  • The step numbering is inconsistent (1, 1, 2, then jumping to 1, 4, 5).

Verdict: Both models struggled with the complex logic of the six-step sequence and text rendering. FLUX.1 Krea produced a more visually striking poster with strong title text, but the actual infographic content was nonsensical. Vidu Q2 followed the iconography requirements more closely and captured the modern infographic layout better, despite significant spelling errors.

Next steps

Explore each model