Black Forest Labs' ultra-high resolution image generation model, an enhanced version of FLUX1.1 [pro] optimized for premium quality output
Settled by community votes across 13 shared challenges, with an AI judge weighing in on each.
FLUX1.1 [pro] Ultra
#53 of 62 in Text-to-Image
Vidu Q2
#42 of 62 in Text-to-Image
Where the votes landed
FLUX1.1 [pro] Ultra
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] Ultra
- + Excellent photorealistic texture on the red book's leather and gold lettering.
- + Very clean glass materiality with realistic refraction and edge thickness.
- + Sophisticated soft lighting that feels natural for a window source.
- − The sphere is levitating unrealistically in the center of the cube.
- − The perspective of the table surface is slightly warped on the right side.
Vidu Q2
- + Natural placement of the blue sphere sitting on the bottom surface of the cube.
- + Dynamic shadow play from the fern-like plant across the table.
- + Strong adherence to the spatial requirements of the prompt.
- − The glass cube edges appear slightly distorted or doubled in some areas.
- − The red book looks a bit more generic or plastic-like compared to Model A.
Verdict: Both models followed the prompt instructions perfectly, including the specific spatial arrangement of the cube, sphere, book, and plant. FLUX1.1 [pro] Ultra has higher visual fidelity and more realistic materials, though the sphere is floating; Vidu Q2 offers better physics with the sphere resting on the bottom but has slightly lower detail quality in the glass edges.
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] Ultra
- + Excellent execution of long-exposure motion blur on passing vehicles.
- + Professional-grade cinematic composition and lighting.
- + High overall image clarity and realistic pavement reflections.
- − The subject appears to be just holding the bike rather than 'repairing' it.
- − Skin texture is slightly too smooth and clean for the prompt's 'natural' requirement.
- − The bicycle design is a bit generic and modern.
Vidu Q2
- + Perfectly captures the 'imperfect framing' and 'candid' street photography aesthetic.
- + Incredible detail in the hands, forearms, and bike mechanical parts.
- + Highly realistic weathered textures on both the red bicycle and the man's skin.
- − Failed to incorporate the requested motion blur from passing cars.
- − The rear of the bike features broken or floating chain segments.
- − The raining effect is very subtle, almost missing compared to Model A.
Verdict: FLUX1.1 [pro] Ultra excels at the cinematic atmosphere, capturing the motion blur and lighting of a rainy street perfectly, though it feels a bit staged. Vidu Q2 captures the soul of the prompt with a grit and realism that feels like a true candid photo, showing incredibly detailed skin and mechanical textures, though it missed the motion blur requirement. Vidu Q2 is the preferred choice for its superior interpretation of 'candid' and 'natural' textures despite minor technical glitches in the bike chain.
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] Ultra
- − The image failed to load or is a solid black square, meaning it has zero prompt adherence or visual quality.
Vidu Q2
- + Excellent adherence to technical details like the hair braids with beads and the ornate engraving on the plate armor.
- + Beautiful lighting work with warm torchlight reflections and realistic bokeh sparks in the background.
- + High-quality texture work on the leather straps and the woven fabric of the underlayer.
- − The facial scars are a bit subtle given the 'battle-worn' description.
- − The skin appears slightly too clean for the requested 'dirt on the skin' prompt.
Verdict: FLUX1.1 [pro] Ultra failed to generate a visible image, resulting in a black square. Vidu Q2 produced a high-quality, detailed portrait that successfully captured almost every element of the prompt, including the complex armor and specific hair decorations.
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] Ultra
- + Excellent professional layout that looks like a real marketing mockup.
- + Very clean typography and white space usage.
- + Food photos are high resolution and look appetizing and consistent.
- − Contains minor spelling errors like 'Pizzzans' and 'Appet Love'.
- − Section logic is slightly disjointed with text overlapping images.
Vidu Q2
- + Strong adherence to the grid layout requested in the prompt.
- + Includes all requested sections (Appetizers, Pizza, Mains) clearly labeled.
- + Vibrant accents were interpreted well through colorful underlining and borders.
- − Text is highly distorted and mostly illegible gibberish.
- − Image quality is lower with visible AI artifacts in the food photos.
- − The layout feels cluttered and less professional compared to the other model.
Verdict: FLUX1.1 [pro] Ultra produces a much more professional and realistic menu mockup with high-quality photography and clean design principles. While Vidu Q2 followed the grid and section requirements more literally, its execution suffered from poor image quality and severely garbled text, making FLUX1.1 [pro] Ultra the superior choice for a professional design task.
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] Ultra
- + Excellent typography and layout design suitable for a real advertisement.
- + Crisp, high-resolution food textures with realistic lighting on the bun and patties.
- + Great use of depth with floating embers and nuggets.
- − Missed the starburst element for the price.
- − The burger is more of a stack than an 'exploded' view where components are clearly separated by space.
- − Includes small hallucinatory text at the bottom corners.
Vidu Q2
- + Successfully included all requested elements including the starburst for the price.
- + Better interpretation of the 'exploded' motion with clear air gaps between all ingredients.
- + Dynamic fiery background fills the frame effectively.
- − Incorrect symbol for the price (used a hash/double bar instead of the Euro sign).
- − Lower overall image resolution and slightly soft textures compared to the competitor.
- − The text rendering is less polished with some artifacts around the edges of the letters.
Verdict: FLUX1.1 [pro] Ultra produces a much more professional and high-fidelity image with superior food photography aesthetics, though it missed the starburst requirement. Vidu Q2 followed the prompt instructions more literally by including every requested element and a better 'exploded' arrangement, but failed on the specific currency symbol and overall image clarity. FLUX1.1 [pro] Ultra is the better choice for a commercial-quality output.
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] Ultra
- + The handwriting style is very realistic and matches the 'chalk' texture requested.
- + The wooden frame and background bokeh enhance the 'cozy café' atmosphere.
- + Minimal spelling errors compared to the competitor, though some duplication occurs.
- − The text includes redundant lines and gibberish beneath the main items.
- − Failed to use 'elegant cursive' for the title as requested.
- − Spelling errors like 'Truffle mushroomm ris' and 'Ask's' are present.
Vidu Q2
- + Excellent chalk texture with realistic smudging and layered strokes.
- + Followed the instruction for the title to be in a more cursive/stylized script.
- + High visual appeal in terms of color variation and font 'weight'.
- − Severe spelling hallucinations throughout every single line (e.g., 'Octopd wpila', 'Browd Botter').
- − Changed the requested price for the first item from $24 to $34.
- − The text becomes almost entirely illegible at the bottom pf the board.
Verdict: Both models struggled with the complex spelling requirements of the long prompt. FLUX1.1 [pro] Ultra produced much clearer and more readable text despite some line duplication, while Vidu Q2 captured the 'elegant cursive' title and the physical chalk texture much better but failed significantly on legibility and spelling. Overall, FLUX1.1 [pro] Ultra is the winner for creating a functional menu that preserves the primary content requested.
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] Ultra
- + Excellent photorealism and cinematic scale with a clear view of Earth's atmosphere
- + High detail in the astronaut's suit textures and the horse's anatomy
- + Superior lighting and composition that feels more 'cinematic' than 'digital art'
- − Failed the negative constraint entirely; the astronaut is riding the horse
Vidu Q2
- + Beautiful surreal color palette with nebula patterns on the horse's coat
- + Dynamic pose for both the horse and the astronaut
- + Detailed harness and space-suit design
- − Failed the negative constraint entirely; the astronaut is riding the horse
- − The anatomy where the astronaut's legs meet the horse is slightly messy
Verdict: Both models failed the specific prompt instruction to have the 'horse on top' of the astronaut, instead defaulting to the common trope of an astronaut riding a horse. FLUX1.1 [pro] Ultra is preferred for its significantly higher image quality, realistic textures, and grand cinematic scale, whereas Vidu Q2 has a more saturated digital-art aesthetic with less clarity.
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] Ultra
- + Excellent fur texture and lighting on the capybara.
- + Cinema-quality bokeh and atmosphere in the background.
- − Fundamental failure of spatial composition with the passenger appearing to sit in the front/middle next to the driver.
- − The passenger is also holding a steering wheel, which contradicts the prompt.
Vidu Q2
- + Perfect adherence to spatial instructions with the passenger clearly in the back seat.
- + Accurate depiction of the capybara's paws on the steering wheel.
- + Clear, high-quality rendered interior and city background.
- − The passenger's expression is slightly more vacant than 'bored.'
- − The capybara's paws look a bit like a mix between human hands and paws.
Verdict: While FLUX1.1 [pro] Ultra has slightly more realistic textures, it completely failed the spatial logic of the prompt by placing the passenger in the front seat and giving her a second steering wheel. Vidu Q2 followed every instruction perfectly, placing the businesswoman in the back seat and the capybara in the driver's seat as requested.
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] Ultra
- + Excellent typography rendering with almost perfect spelling
- + High-quality cinematic lighting with a professional digital illustration style
- + Sophisticated layout that uses the scroll and thorn border effectively
- − Missed the word 'Party' in the main title
- − Generated an extra line of redundant, garbled text below the banner
Vidu Q2
- + Strong 'vintage' texture on the parchment paper
- + Includes both webs and thorns as requested in the border
- − Significant spelling errors throughout all text elements
- − The date and time were hallucinated incorrectly (30.70.2025)
- − The composition feels less balanced and more cluttered
Verdict: FLUX1.1 [pro] Ultra is the clear winner due to its superior text legibility and aesthetic polish, despite a minor redundancy in the text. Vidu Q2 struggles significantly with spelling and fails to follow the specific date/time details provided in the prompt.
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] Ultra
- + Excellent typography with a stylish, curved 'JAPAN' text
- + Superior lighting and refined textures that give a professional 3D render feel
- + Includes subtle details like steam and varied sushi types that enhance the scene
- − The text is a bit light in color, making it slightly less legible against the background
- − Includes an odd ladybug-like artifact on the wooden board
Vidu Q2
- + Bold, highly legible text that perfectly follows the prompt's layout
- + Clear interpretation of the 'raised diorama base' and flag icon
- + Vibrant colors that pop against the blue background
- − Texture quality is a bit generic and waxy compared to a realistic PBR look
- − Text rendering on the 'J' and 'N' has minor aliasing artifacts
Verdict: FLUX1.1 [pro] Ultra produces a much more sophisticated and artistic 3D scene with superior lighting and texture work, though its text is less bold. Vidu Q2 adheres more literally to the layout requests but lacks the high-end aesthetic quality found in the competing model. Overall, FLUX1.1 [pro] Ultra is the better image due to its professional finish and composition.
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] Ultra
- + Exquisite rendering of soft backlight and golden rays.
- + Beautiful, consistent art style with very clean fur textures.
- + Captures the 'big expressive eyes' and 'wholesome vibe' perfectly.
- − The animals look very similar in style, almost like plush toys rather than distinct hyper-photorealistic species.
- − The animals are mostly sitting still rather than 'tumbling' as requested.
Vidu Q2
- + Captures the action and movement of 'tumbling' and 'chasing' much better.
- + Shows a more distinct variety of animal species and markings.
- + More accurate representation of a 'lush wildflower meadow' with a wider view.
- − Anatomy errors including a second golden retriever puppy that wasn't requested.
- − Noticeable artifacts around the butterflies and cluttered background elements.
- − The fox and kitten have slightly distorted facial features.
Verdict: FLUX1.1 [pro] Ultra produces a much more polished and aesthetically pleasing 'masterpiece' with superior lighting, though it is more static. Vidu Q2 follows the action of the prompt more closely by showing the animals actually playing, but it suffers from significant anatomical inaccuracies and lower overall image clarity. FLUX1.1 is preferred for its high technical quality despite being more stylized.
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] Ultra
- + Strong composition with a balanced circular emblem
- + Excellent color palette and vintage texture
- + Clear and professional typography
- − Misspelled the name as 'Framilian' instead of 'Florian'
Vidu Q2
- + Matches the warm brown and cream tones well
- + Included the cloche dome design as requested
- − Severe text rendering issues with multiple misspellings and redundant text
- − The 'Esttt' typo is distracting
- − Low visual clarity and poor vector style execution compared to the other model
Verdict: While both models failed to spell 'Florian' correctly, FLUX1.1 [pro] Ultra produced a much more professional and aesthetically pleasing logo with superior composition and texture. Vidu Q2 struggled significantly with text legibility and consistency, resulting in a cluttered and amateur appearance.
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] Ultra
- + Excellent typography and layout for a professional poster.
- + Includes the requested 6 steps with clear, distinct icons.
- + Perfectly adheres to the NASA-inspired color palette and flat-vector style.
- − Nonsense filler text throughout the infographic.
- − The order of the steps on the visual timeline is confusing and non-linear.
Vidu Q2
- + Clean, simple vector icons for the lunar module.
- + Follows the light gray and white color palette well.
- − Severe spelling errors even on main titles (e.g., 'ALFONCH').
- − Poor layout with icons and text overlapping.
- − Missing several specific steps requested in the prompt.
Verdict: FLUX1.1 [pro] Ultra created a much more visually sophisticated infographic that looks like a real poster, despite the presence of gibberish text. Vidu Q2 failed significantly on both text rendering and layout composition, producing a messy result that did not follow the requested six-step sequence.
Explore each model
ShengShu Technology's text-to-image and reference-to-image model with support for character consistency and multi-reference image processing