Black Forest Labs' enhanced 12-billion parameter flow transformer with 6x faster generation than FLUX.1 [pro], delivering superior composition, detail, and artistic fidelity
Settled by community votes across 13 shared challenges, with an AI judge weighing in on each.
FLUX1.1 [pro]
#49 of 62 in Text-to-Image
Vidu Q2
#42 of 62 in Text-to-Image
Where the votes landed
FLUX1.1 [pro]
0%
win rate
Ties
0%
Vidu Q2
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
FLUX1.1 [pro]
- + Excellent optical realism with reflections on the glass and sphere
- + Clear adherence to the 'soft window light' lighting instruction
- + High-quality texture on the red book cover
- − The glass container is more of a rectangular prism than a perfect cube
- − The sphere is floating unnaturally rather than resting on the bottom
Vidu Q2
- + Perfect geometric cube shape
- + Highly realistic physics with the sphere resting on the bottom and the book at an angle
- + Strong lighting composition creating dynamic shadows
- − The sphere appears slightly matte, lacking the refractive depth seen in the other model
Verdict: Both models followed the prompt instructions perfectly, including the placement of the plant and sphere. Vidu Q2 is the winner because it rendered a more accurate cube shape and placed the objects in a way that feels physically grounded. FLUX1.1 [pro] produced a beautiful image but the container was tall rather than cubic and the central object lacked gravity.
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
FLUX1.1 [pro]
- + Captures the rainy atmosphere and wet pavement reflections beautifully
- + Excellent use of depth of field and bokeh
- + Perfectly nails the cinematic street photography aesthetic requested in the prompt
- − The bicycle anatomy is broken, with the frame appearing severed in the middle
- − The man is leaning on the bike rather than actively 'repairing' it
Vidu Q2
- + Much better focus on the 'repairing' aspect of the prompt
- + Incredible skin textures and realistic hand details
- + The bicycle architecture is more coherent and detailed
- − The 'imperfect framing' is a bit too aggressive, cutting off the man's head
- − Doesn't feel as much like a 50mm lens shot compared to Model A
Verdict: FLUX1.1 [pro] creates a more visually stunning, atmospheric image that feels like a professional photograph, but it fails on the structural integrity of the bicycle. Vidu Q2 is much more successful at depicting the specific action of repairing the bike and features superior skin and mechanical textures, despite the jarring crop. Overall, Vidu Q2 is preferred for its technical realism and adherence to the primary action requested.
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
FLUX1.1 [pro]
- + Exceptional skin texture with realistic pores and weathering.
- + High-quality 'lifelike eyes' that capture the intensity of the character.
- + Superior bokeh effect and depth of field that emphasizes the portrait.
- − The hair beads requested in the prompt are very subtle or missing.
- − The armor engraving is less detailed compared to Model B.
Vidu Q2
- + Excellent adherence to technical details like hair beads and specific armor engraving.
- + Visible leather straps and cloth underlayers as requested.
- + Strong metallic reflections and warm lighting.
- − The character looks much younger and less 'battle-worn' than requested.
- − The 'close portrait' framing is missed, resulting in a medium shot.
- − Skin texture is slightly too smooth and looks more like a 3D render than a photo.
Verdict: FLUX1.1 [pro] produces a far more convincing 'battle-worn' aesthetic with incredible facial realism and depth, though it slightly misses the hair beads. Vidu Q2 follows the technical armor and hair prompts more accurately but fails to deliver the cinematic 'close portrait' feel, opting for a wider shot and a much cleaner-looking character. FLUX1.1 [pro] is the preferred choice for its superior texture and adherence to the character's mood.
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
FLUX1.1 [pro]
- + Excellent professional presentation with realistic cutlery and layered menu cards.
- + Followed the grid photo prompt accurately with clear, high-quality images of pizza and food.
- + The typography is clean and highly legible, maintaining a realistic restaurant hierarchy.
- − The text content is mostly placeholder gibberish upon closer inspection.
- − The grid layout is slightly crowded at the bottom of the center card.
Vidu Q2
- + Strong use of vibrant colors and accents as requested in the prompt.
- + Each section is clearly defined with colorful photography.
- − The text and spelling are very poor and distorted (e.g., 'APEČIZEN', 'Piтaa').
- − The images look more like digital illustrations or heavily filtered photos rather than clean professional photography.
- − The font styles are inconsistent and lack the professional minimalist feel requested.
Verdict: FLUX1.1 [pro] provides a much more realistic and professional design that looks like an actual marketing mock-up, effectively using a grid of food photos and clean layouts. While Vidu Q2 followed the prompt regarding vibrant colors, its poor text rendering and messy graphic elements make it unusable compared to the polished output of FLUX1.1 [pro].
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
FLUX1.1 [pro]
- + Excellent photorealistic texture on the burger patties and bun
- + Clean typography with various modern styles
- + Beautiful use of depth of field and bokeh in the background
- − Failed the 'exploded' instruction as the burger is mostly assembled
- − The main burger text is redundant and uses a blue neon style instead of the requested fiery effect
- − Missed the 'starburst' container for the price
Vidu Q2
- + Perfectly adhered to the 'exploded' burger layout with suspended components
- + Text effectively uses the requested fiery, glowing style
- + Successfully included the starburst element for the price
- − The price symbol is incorrect (rendered as an 'E' cross or hash instead of the Euro '€' symbol)
- − The lighting on the bun and lettuce is slightly flatter compared to Model A
- − The background is very busy, making the 'exploded' effect slightly harder to distinguish
Verdict: Vidu Q2 effectively captured all structural requirements of the prompt, including the exploded burger layout, the starburst price tag, and the fiery text effects. While FLUX1.1 [pro] produced a more photorealistic image with superior textures, it failed on the key conceptual 'exploded' composition and most specific text styling instructions.
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
FLUX1.1 [pro]
- + Excellent text legibility and correct spelling for almost all items.
- + Clean and elegant presentation with a realistic wooden frame.
- + Background blur creates a pleasant café ambiance.
- − The text has a slightly digital feel and lacks the crumbly texture of real chalk.
- − Repeated and hallucinated line for the octopus dish with incorrect pricing ($228).
Vidu Q2
- + Superb chalk texture with smudge marks and dusty residues that feel authentic.
- + Better adherence to the 'handwritten variation' prompt with varying letter sizes and strokes.
- + Captures the tactile quality of a real chalkboard surface better.
- − Significant spelling and character errors throughout the menu items (e.g., 'Lemepun', 'Octopd').
- − The handwriting becomes chaotic and difficult to read toward the bottom of the board.
Verdict: FLUX1.1 [pro] followed the text instructions more accurately, providing legible items with only one repeated line, whereas Vidu Q2 captured a much more realistic chalk-on-board texture at the expense of spelling and clarity. FLUX1.1 [pro] is the more useful image for a menu display, while Vidu Q2 is more artistically convincing as a physical object.
The Reversed Rodeo
Text-to-Image“Horse riding astronaut in space — horse on top, not vice versa. Surreal, highly detailed, cinematic.”
AI Judge Analysis
FLUX1.1 [pro]
- + Excellent cinematic lighting and atmosphere
- + Realistic textures on the spacesuit and horse hair
- + Great dynamic posing of the horse
- − Failed the specific spatial instruction for the horse to be on top of the astronaut
- − Anatomy of the horse's underside and legs is slightly distorted
Vidu Q2
- + Vibrant colors and creative 'nebula' texture on the horse
- + Excellent clarity and sharp details
- + Compositionally balanced with the galaxy background
- − Failed the specific spatial instruction for the horse to be on top of the astronaut
- − The rider's hands and reins have some clipping and logical issues
Verdict: Both FLUX1.1 [pro] and Vidu Q2 failed to fulfill the primary surreal reversal requested in the prompt, which asked for the horse to be on top of the astronaut. FLUX1.1 [pro] produced a more cinematic and grounded image with superior lighting, while Vidu Q2 leaned into a more colorful, digital art aesthetic.
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
FLUX1.1 [pro]
- + Excellent shallow depth of field and bokeh in the background
- + High-quality fur texture and realistic lighting on characters
- − The composition places the passenger in the front passenger seat rather than the requested back seat
- − The capybara's front paws are not on a visible steering wheel
Vidu Q2
- + Strict adherence to composition instructions with the businesswoman in the back seat
- + Perfect execution of the capybara holding the steering wheel with both paws
- + Captures the 'bored' expression of the passenger perfectly
- − The capybara's hands look slightly more primate-like than capybara-like
- − The lighting on the capybara is slightly flat compared to the background
Verdict: While FLUX1.1 [pro] has superior artistic lighting and textures, it failed significantly on the spatial prompt instructions, placing the passenger in the front seat and omitting the steering wheel. Vidu Q2 followed every specific detail of the prompt, including the positioning of the characters and the specific action of the hands on the wheel, while maintaining high visual quality.
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
FLUX1.1 [pro]
- + Excellent atmospheric lighting and mood
- + Very crisp high-detail jack-o-lantern rendering
- + Clean, legible font for the event details
- − Repetitive text with multiple 'Party' and 'Location' lines
- − Incorrect spelling in the scroll banner: 'You inivted to a n night of frights'
- − Does not show the 'parchment' texture as clearly as model B
Vidu Q2
- + Strong 'vintage parchment' texture and aged aesthetic
- + Includes spiderwebs explicitly mentioned in the prompt
- + Accurate representation of thorns and twisted trees around the border
- − Severely garbled and misspelled text throughout ('Intovztion', 'invieed ta might of fiigts')
- − Incorrect date '30.70.2025' and mangled time 'Tmm'
- − Low-resolution artifacts around the text and borders
Verdict: FLUX1.1 [pro] produces a much more polished and cinematically lit image with legible event details, though it suffers from repetitive text elements and minor banner typos. Vidu Q2 captures the vintage gothic aesthetic and requested 'webs and thorns' border better, but the text is largely nonsensical and hallucinated. FLUX1.1 [pro] is the superior choice for a usable invitation due to its overall visual clarity and readable information.
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
FLUX1.1 [pro]
- + Excellent typography and layout.
- + Smooth, professional 3D stylized rendering with gentle lighting.
- + Higher resolution and cleaner details on the diorama elements.
- − Missed the flag icon completely.
- − The 'sushi' sub-text is a bit small and low contrast.
Vidu Q2
- + Included the requested flag icon.
- + Very accurate 45-degree top-down isometric perspective.
- + Better adherence to the requested text hierarchy.
- − The 'J' and 'N' in the text have slight rendering artifacts.
- − The rice texture is slightly lumpy and lacks the refined PBR look of the competitor.
Verdict: FLUX1.1 [pro] produced a much cleaner and more aesthetically pleasing 3D illustration with superior textures and lighting, although it failed to include the flag icon. Vidu Q2 followed the prompt instructions more closely by including the flag and managing the text hierarchy well, but the overall image quality and text rendering were not as refined.
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
FLUX1.1 [pro]
- + Excellent shallow depth of field and soft lighting
- + Very consistent and high-quality fur texture
- + Expressive and soulful eyes
- − Failed to include all four requested animals, missing the red fox kit
- − The butterflies are represented as glowing light blobs rather than detailed insects
Vidu Q2
- + Included all four requested animal types (puppy, kitten, bunny, fox)
- + Captured the dynamic 'tumbling' and 'chasing' actions requested in the prompt
- + Accurate butterfly anatomical details and diverse coloring
- − The fox's front right leg is anatomically incorrect and looks like it is floating
- − The image has a more 'digital art' feel compared to the photorealistic requirement
- − Some artifacts in the grass and flower rendering around the animal paws
Verdict: While FLUX1.1 [pro] produced a more aesthetically pleasing and high-fidelity image with superior lighting, it failed the prompt adherence test by omitting the fox. Vidu Q2 succeeded in including all requested animals and capturing the specified action ('chasing and tumbling'), though its technical execution of anatomy and realism is weaker. Vidu Q2 is the winner for better prompt adherence.
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
FLUX1.1 [pro]
- + Elegant decorative filigree and ornamentation.
- + High-quality vector aesthetic with clean lines.
- + Correct rendering of the establishment date 'Est. 1720'.
- − Misspelled the primary brand name as 'Caffé Franilian'.
- − The central icon looks more like a dome or cathedral than a typical restaurant cloche.
Vidu Q2
- + Accurately depicts the requested 'cloche dome' icon.
- + Included a subtle paper-like texture on the background as requested.
- + Matches the warm cream and brown color palette well.
- − Significant text failures including multiple misspellings like 'Farmiin' and 'Esttt'.
- − Redundant and garbled text at the bottom of the emblem.
- − The steam effects lack the clean vector look requested.
Verdict: While FLUX1.1 [pro] failed to spell 'Florian' correctly, it produced a much more professional and coherent vector emblem design with clean typography and balanced composition. Vidu Q2 followed the visual prompt for a cloche dome more closely, but the implementation was marred by severe text hallucinations and poor layout density.
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
FLUX1.1 [pro]
- + Excellent adherence to the navy, white, and muted red color palette.
- + Sophisticated composition that feels like a professional modern infographic.
- + High-quality vector aesthetic with crisp lines and elegant background details.
- − The text is largely illegible gibberish, failing to properly label the requested steps.
- − The icons for the six steps are repeated or out of order (e.g., using two icons labeled '1').
Vidu Q2
- + Layout follows a clear linear progression of steps (1, 2, 4, 5).
- + Icons for the Lunar Module and Saturn V-style rocket are more distinct and recognizable.
- + Much cleaner text rendering, even though several words are misspelled.
- − The color palette is mostly light gray and lacks the requested navy blue focus.
- − Missing the 'Apollo 11' title, instead using a nonsensical heading.
- − The composition feels like a collection of clipart rather than a cohesive infographic poster.
Verdict: FLUX1.1 [pro] produced a much more visually appealing and stylistically accurate 'modern infographic' with a professional color scheme, though it failed significantly on text and labeling logic. Vidu Q2 followed the step-by-step structure more clearly and had better text legibility, but the overall design felt amateur and failed to follow the color instructions. FLUX1.1 [pro] is the winner for capturing the requested artistic style more effectively.
Explore each model
ShengShu Technology's text-to-image and reference-to-image model with support for character consistency and multi-reference image processing