Black Forest Labs' open-weights image generation model with frontier performance, available for non-commercial local deployment
Settled by community votes across 20 shared challenges, with an AI judge weighing in on each.
FLUX.2 [dev]
#20 of 62 in Text-to-Image
Vidu Q2
#42 of 62 in Text-to-Image
Where the votes landed
FLUX.2 [dev]
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
FLUX.2 [dev]
- + Excellent adherence to the 'soft light' instruction.
- + High photorealism with natural glass reflections.
- + Accurate spatial arrangement and object interaction.
- − The plant is slightly less detailed than in Model B.
Vidu Q2
- + Sharp details on the plant and book spine.
- + Vibrant colors and high contrast.
- + Correct placement of all requested elements.
- − The lighting is harsh rather than the requested 'soft windows light'.
- − Shadows on the table are inconsistent with soft window light.
Verdict: Both models successfully followed all spatial instructions, placing the sphere inside the cube and the book on top. FLUX.2 [dev] is the winner because it captured the 'soft window light' much more realistically, whereas Vidu Q2 produced harsh, direct sunlight shadows that didn't match the prompt's mood.
Man and Car in California
Editing“Make a photo of the man driving the car down the California coastline”
AI Judge Analysis
FLUX.2 [dev]
- + Excellent preservation of the man's specific clothing and hairstyle
- + Maintains the luxury interior details of the original car from a side profile
- + Realistic lighting and depth of field consistent with the California coastline
- − The man is on the wrong side of the car for a left-hand drive vehicle
- − The exterior silhouette of the car is partially lost due to the close framing
Vidu Q2
- + Successfully places the car on a scenic California mountain road
- + Preserves the overall look and model of the white convertible car well
- + Good motion blur on the wheels and road indicating speed
- − Significant loss of the man's specific identity, hair, and clothing from the source image
- − The man appears strangely small and poorly integrated into the driver's seat
- − The road curves and perspectives are slightly warped
Verdict: FLUX.2 [dev] is much better at preserving the identity and specific clothing of the man, creating a believable and stylish scene despite putting the driver on the 'wrong' side of the car. Vidu Q2 captures the grander scale of the coastline but fails to maintain the man's features, resulting in a generic character that looks like a sticker placed in the car. FLUX.2 [dev] is preferred for its high-quality rendering and alignment with the provided source images.
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]
- + Excellent adherence to all prompt elements including motion blur, rain, and reflections.
- + Highly realistic skin textures and natural-looking hands.
- + Captures the requested 'imperfect framing' while maintaining a cinematic quality.
- − The handlebars and cables on the bicycle are slightly physically incoherent.
Vidu Q2
- + Strong depiction of the bicycle chain and mechanical parts.
- + Good use of reflections on the wet sidewalk.
- − Failed to include motion blur on the car in the background.
- − Anatomical issues with the man's hands/fingers merging together.
- − Missing the sense of light rain requested in the prompt.
Verdict: FLUX.2 [dev] followed the technical requirements of the prompt much better, successfully incorporating motion blur, visible rain, and a realistic street photography aesthetic. Vidu Q2 produced a more static image that ignored the motion blur and environmental atmospheric requests, and suffered from significant anatomical defects in the subject's hands.
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]
- + Excellent adherence to the 'beads in hair' prompt with multiple colorful beads visible
- + Highly realistic skin textures with convincing grime and battle scars
- + Superior bokeh effect with cinematic sparks and a visible torch source
- − The engraving on the armor is a bit soft in certain areas compared to the metal sheen
Vidu Q2
- + Ornate engraving on the plate armor is very sharp and intricate
- + Good texture on the cloth underlayer
- + Distinct facial features with a strong, intense expression
- − Missed the 'hair braided with small beads' instruction, featuring only metal bands at the end of braids
- − Skin looks slightly more digital/smooth than the requested battle-worn texture
- − Bokeh sparks are less integrated into the lighting of the scene
Verdict: FLUX.2 [dev] followed every detail of the prompt accurately, specifically the beads in the hair and the gritty, battle-worn skin texture. Vidu Q2 produced a high-quality image with impressive armor engraving, but failed to include the colorful beads and provided a less convincing interpretation of 'grime and dirt'.
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]
- + Excellent typography with legible headers and aligned pricing.
- + High-quality, realistic food photography that fits a restaurant aesthetic.
- + Clean, professional grid layout that follows graphic design principles.
- − Nonsense filler text for item descriptions.
- − Header names are slightly misspelled (PIZZAU).
Vidu Q2
- + Colorful and vibrant layout with creative accents.
- + Good adherence to the 'sections' requirement of the prompt.
- − Typography is distorted and difficult to read.
- − Food photography contains AI artifacts and lacks professional clarity.
- − Layout is a bit cluttered with overlapping elements and inconsistent spacing.
Verdict: FLUX.2 [dev] significantly outperforms Vidu Q2 by producing a layout that looks like a real design piece. While FLUX.2 has some minor spelling errors in the headers, its grasp of typography, alignment, and high-quality imagery makes it the superior choice for 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.”
AI Judge Analysis
FLUX.2 [dev]
- + Excellent typography with clean, glowing neon effects that perfectly match the prompt.
- + Superior photorealistic textures on the bun and patty.
- + Well-balanced composition with an effective starburst element for the price.
- − The 'exploded' effect is a bit static with simple vertical stacking.
Vidu Q2
- + Dynamic 'exploded' composition with more interesting angles and motion.
- + Vibrant fiery background that feels more energetic.
- + Generally good detail on the lettuce and tomato slices.
- − The pricing text contains a typo in the currency symbol.
- − The typography for the main titles is slightly less refined compared to Model A.
- − The cheese texture appears a bit plastic-like.
Verdict: Both models followed the prompt well, but FLUX.2 [dev] produced a more professional-looking advertisement with perfect text rendering and highly realistic food textures. While Vidu Q2 captured a better sense of motion and 'exploded' energy, the error in the currency symbol and slightly inferior font treatment makes FLUX.2 [dev] the more usable image for an actual ad.
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]
- + Excellent text accuracy with almost no spelling errors despite the complex prompt.
- + Very realistic chalk texture with smudge marks and natural variation in stroke weight.
- + Clear, legible layout that follows the hierarchy of the prompt perfectly.
- − A slight smudge/artifact appears between 'with' and '$28' on the second item line.
Vidu Q2
- + Good use of chalk highlights and shadows to create a multi-dimensional look.
- + Captures the cozy café background atmosphere effectively.
- − Significant spelling errors on almost every line (e.g., 'Musshoom', 'Lemepun', 'Browd Botter').
- − Inconsistent price rendering, including a nonsensical '$#' for the cookies.
- − Handwriting style is messy and becomes garbled at the bottom of the board.
Verdict: FLUX.2 [dev] significantly outperforms Vidu Q2 by maintaining nearly perfect legibility and spelling for a complex set of text instructions. While FLUX.2 produces a clean and professionally handwritten board, Vidu Q2 struggles with text generation, resulting in numerous spelling errors and garbled characters.
Pose & Character Mashup
Editing“Use Image 1 as the exact pose reference and Image 2 as the character reference. Recreate the person/character from Image 2 in the exact dynamic pose and body position from Image 1. Keep the exact face, hair, clothing style/details, and expression from Image 2. Match the lighting and environment of Image 1. The final image must show the character from Image 2 performing the precise action/pose from Image 1 with perfect anatomy and natural integration.”
AI Judge Analysis
FLUX.2 [dev]
- + Successfully captured the specific scarf and sunglasses from the character reference.
- − Catastrophic anatomical failure with a second head growing out of the shoulder.
- − Poorly rendered floating limbs and incoherent body structure.
Vidu Q2
- + Successfully translated the complex pose from Image 1 to the character in Image 2 with coherent anatomy.
- + Preserved character details like the scarf, sunglasses, and black sweatshirt.
- + High visual clarity and natural integration with the yellow background.
- − The scarf follows the vertical orientation of the character rather than the horizontal dynamic of the pose.
- − Added a watch and shifted the shirt logo text which was not in the original reference.
Verdict: Vidu Q2 is the clear winner as it successfully performed the complex pose transfer with logical human anatomy, whereas FLUX.2 [dev] produced a disturbing image with two heads and floating limbs. Vidu Q2 managed to maintain the character identity of the man in the second image while accurately mimicking the difficult balance pose from the first 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]
- + Excellent photorealistic rendering of the spacesuit and horse fur.
- + High cinematic quality with realistic lighting and planet reflection.
- + Superior anatomical correctness of the horse.
- − Failed the negative constraint to have the horse on top of the astronaut.
Vidu Q2
- + Beautiful, vibrant colors and a highly creative surreal aesthetic.
- + Interweaves the celestial background into the horse's body effectively.
- + Good interpretation of the space environment with nebulae and stars.
- − Failed the negative constraint to have the horse on top of the astronaut.
- − Noticeable anatomical issues with the horse's front-left leg and hoof.
Verdict: Both models failed the specific prompt instruction to place the horse on top of the astronaut, instead defaulting to the common trope of an astronaut riding a horse. FLUX.2 [dev] is the superior image due to its incredible photorealistic detail and lighting, whereas Vidu Q2, while artistically vibrant, suffers from anatomical distortions in the horse's legs.
Outfit Transfer Challenge
Editing“Use Image 1 as the base person. Dress them in the exact elaborate outfit from Image 2 (including all layers, accessories, jewelry, and shoes). Carefully adapt the clothing to the body shape and pose in Image 1 while maintaining realistic fabric behavior, correct proportions, and perfect lighting/shadow matching. Keep the person’s exact face, hair, and background completely unchanged.”
AI Judge Analysis
FLUX.2 [dev]
- + Successfully replicates the specific scarf pattern and coat style from Image 2.
- + Maintains the specific waistband branding from the source subject.
- + Good integration of gold jewelry and sunglasses requested by the edit.
- − Completely changes the subject's face to match the person in Image 2, failing the 'exact face' instruction.
- − The skin conditions/vitiligo on the forehead are altered into a different pattern.
- − Background details and the wooden structure are partially modified.
Vidu Q2
- + Retains the original subject's facial features and bone structure much better than the competitor.
- + Cleverly artistic integration of the sand from the original image onto the new clothing.
- + Background remains significantly more consistent with Image 1.
- − The coat is missing its right sleeve, leaving the arm bare.
- − The sunglasses and facial hair are copied from Image 2 rather than being accessories added to the original face.
- − The vitiligo pattern on the forehead is distorted and looks like a digital artifact.
Verdict: Both models struggled with the complex task of identity preservation while transferring clothing. FLUX.2 [dev] successfully transferred the outfit but failed significantly by replacing the subject's face with the man from Image 2. Vidu Q2 preserved the original subject's identity much better, but the final image contains major structural errors, such as the coat missing a sleeve and poorly rendered skin details.
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]
- + Excellent photorealistic texture on the capybara's fur and the leather steering wheel.
- + The lighting on the businesswoman's face from the phone screen is very realistic.
- + Stronger proximity to the requested 'professional expression' for the capybara.
- − The perspective makes the capybara look slightly too large for the vehicle interior.
- − The 'T' on the cap is a bit generic compared to official taxi insignia.
Vidu Q2
- + Better overall composition showing the full interior and both characters clearly.
- + Captures a more realistic automotive perspective from outside the window.
- + Accurately depicts the businesswoman sitting in the back seat as requested.
- − The capybara's hands look somewhat skeletal/distorted on the steering wheel.
- − The passenger is reflected in the foreground glass in a way that looks slightly messy.
Verdict: Both models handled this surreal prompt impressively, but FLUX.2 [dev] wins on sheer image quality and texture realism. While Vidu Q2 offers a better wide-angle composition that clearly separates the driver and passenger, FLUX.2 [dev] produces a more convincing 'photorealistic' result with superior lighting and fur detail.
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]
- + Perfect text rendering for all requested strings.
- + Excellent composition with a professional, cinematic aesthetic.
- + Strong adherence to all design elements including webs, thorns, and dark parchment.
- − The dark, moody lighting makes the overall image feel a bit heavier than a traditional poster.
Vidu Q2
- + Good vintage parchment texture and bright, glowing jack-o-lantern.
- + Captures the gothic aesthetic well in terms of the border and bat silhouettes.
- − Significant spelling errors in every single line of text.
- − Incorrect date (30.70.2025) and missing time details.
- − The layout is a bit cluttered with the thorns overlapping the scroll awkwardly.
Verdict: FLUX.2 [dev] followed the prompt perfectly, delivering accurate text and a professional, cohesive design that feels like a real invitation. Vidu Q2 failed significantly on the text rendering, with multiple spelling errors and incorrect data points despite having a good illustrative style.
Bald man challenge
Image Editing“Give the person a full, thick head of natural hair with realistic texture, density, and a natural hairline. Preserve facial features and lighting.”
AI Judge Analysis
FLUX.2 [dev]
- + Excellent preservation of the original face, lighting, and background.
- + Highly realistic hair texture with individual strands visible in the afro style.
- − The choice of hair texture (Afro) does not match the person's existing facial hair and eyebrow texture.
- − The hairline looks slightly pasted onto the forehead.
Vidu Q2
- + Natural-looking hair color and texture that perfectly matches the existing beard.
- + Excellent integration of the hairline and temples with the original face.
- + Highly realistic density and volume that feels appropriate for the character.
- − Very minor sharpening/smoothing effect on the facial features compared to the source.
Verdict: Both models did an exceptional job of preserving the source image. FLUX.2 [dev] selected an afro-textured hair type that arguably clashes with the man's existing beard texture, whereas Vidu Q2 added hair that looks completely natural for this specific individual. Vidu Q2 is the clear winner for creating a more believable and cohesive transformation.
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]
- + Excellent adherence to isometric perspective and clean composition.
- + Text and flag icon are rendered with perfect clarity and alignment.
- + Materials feel sophisticated with soft, realistic PBR shading.
- − The sushi looks a bit more realistic than the '3D cartoon' style requested.
Vidu Q2
- + Strong '3D cartoon' aesthetic with more vibrant colors.
- + Creative implementation of the flag attached to the text.
- + Good variety of sushi types on the plate.
- − The diorame base is not perfectly isometric or centered.
- − Some lighting choices create a slightly wet/plastic look rather than refined PBR textures.
- − Text alignment and font weight feel a bit unbalanced.
Verdict: FLUX.2 [dev] produced a much cleaner and professional result that perfectly follows the layout instructions and text requirements. While Vidu Q2 captured a more playful cartoon style, it struggled with the precise isometric alignment and high-clarity rendering found in the FLUX.2 [dev] output.
Over-the-top cartoon caricature
Editing“Create a caricature of me and my job. Make it exaggerated and humorous, incorporating my profession as a tv show anchor and my love for dogs and hockey.”
AI Judge Analysis
FLUX.2 [dev]
- + Successfully incorporates all elements including hockey, dogs, and the TV anchor desk in a cohesive set.
- + The caricature style is very effective with exaggerated head proportions and classic illustration shading.
- + Maintains facial recognizeability from the source image quite well despite the stylized format.
- − The text on the anchor desk is gibberish.
- − The hands are quite small and slightly mutated in their grip on the items.
Vidu Q2
- + Excellent preservation of the source image's clothing (denim shirt over black top).
- + Clean, vibrant comic-book style with high resolution and sharp lines.
- + Good inclusion of thematic details like the puck, the hockey goal, and paw prints on the script.
- − The anatomy of the right hand holding the microphone is poor, with an extra finger-like shape.
- − The small dog sitting on the papers is disproportionately tiny compared to the other elements.
- − The background hockey rink is a bit abstract and lacks the 'broadcast' feel of Model A.
Verdict: Both models followed the complex instructions well, creating humorous caricatures. FLUX.2 [dev] felt more like a professional editorial caricature by placing the subject behind a broadcast desk and integrating the hockey theme into the outfits of the 'guests.' Vidu Q2 succeeded in keeping the subject's original clothing and provided a cleaner art style, but suffered from significant anatomical issues in the hands.
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]
- + Consistent and high-quality fur texture across all animals
- + Excellent lighting with realistic god rays and backlighting effects
- + Clean composition with distinct, well-rendered characters
- − The animals are mostly sitting still rather than 'playfully chasing' or 'tumbling'
- − Included an extra animal (two bunnies) which wasn't specifically requested
Vidu Q2
- + Captures the 'playfully chasing' and 'tumbling' motion part of the prompt much better
- + High energy and dynamic composition that fits a 'joyful vibe'
- + Vibrant colors and a high quantity of butterflies and flowers
- − Several anatomical issues including extra limbs on the puppy and fox
- − Visible AI artifacts in the background and messy fur rendering
Verdict: FLUX.2 [dev] produces a much more polished and photorealistic image with superior lighting and texture, but it is quite static. Vidu Q2 does a better job of capturing the requested action and movement, but it suffers from significant anatomical errors and Lower overall image clarity. FLUX.2 [dev] is the winner for its technical excellence and coherence.
Studio Ghibli Anime Style
Editing“Transform this photo into a Studio Ghibli–inspired illustration. Use soft pastel colors, hand-painted textures, gentle lighting, dreamy backgrounds, and a warm, nostalgic mood”
AI Judge Analysis
FLUX.2 [dev]
- + Excellent application of soft pastel colors and a dreamy, nostalgic mood.
- + High-quality hand-painted texture that significantly changes the aesthetic.
- + Creatively transforms the urban background into a flower field while keeping the character composition identical.
- − The background change, while beautiful, deviates more from the source image's context than Model B.
Vidu Q2
- + Perfectly preserves the source image's architectural background while applying a watercolor style.
- + Captures the Ghibli-style facial expressions and line art very effectively.
- + Maintains accurate clothing patterns and colors from the original.
- − The lighting feels slightly flatter and less 'dreamy' compared to Model A.
Verdict: Both models successfully interpreted the 'Distracted Boyfriend' meme into a Ghibli aesthetic. FLUX.2 [dev] went further with the 'dreamy' prompt by replacing the street with a floral field and soft lighting, creating a more cohesive 'illustration' feel, whereas Vidu Q2 focused on preserving the original scene's geometry while applying a high-quality watercolor overlay and character redesign.
Golden Hour Stroll
Image Editing“Add dynamic motion to this photo: make hair blow in the wind, add leaves flying, energetic and lively feel.”
AI Judge Analysis
FLUX.2 [dev]
- + Excellent wind physics applied to the hair with realistic strand separation.
- + High preservation of the original facial features and clothing details.
- + The leaves integrated naturally with the lighting and shadows of the scene.
- − The hair length appears slightly exaggerated compared to the source image.
- − Some leaves look a bit small and repetitive in shape.
Vidu Q2
- + Successfully added a large volume of colorful leaves to create energy.
- + Good hair motion that maintains the general shape of the original hairstyle.
- + High fidelity to the source image's composition and color palette.
- − The wind direction on the hair (blowing left) contradicts the wind direction suggested by the leaves (blowing right).
- − Some leaves in the foreground have slightly blurry or jagged edges compared to the background.
Verdict: Both models followed the instructions well, but FLUX.2 [dev] is the winner because its wind effect on the hair is more dynamic and physically convincing. While Vidu Q2 added more colorful leaves, it created a conflicting wind direction between the leaves and the hair that makes the image feel less coherent.
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]
- + Perfect text rendering for all requested strings including the accent on 'Caffè'.
- + Excellent vector emblem style with clean, professional lines.
- + Follows all prompt instructions including the steam, banner, and texture.
- − The steam is a bit small/minimalistic compared to the rest of the logo.
Vidu Q2
- + Nice soft, warm color palette.
- + Good use of gradients on the cloche dome to imply a metallic shine.
- − Major text errors including 'FARMIIN', 'Esttt', and 'Fopli20'.
- − Low-quality illustrative style rather than the requested vector emblem.
- − Excessive and redundant text cluttered at the bottom.
Verdict: FLUX.2 [dev] followed the prompt nearly perfectly, producing a clean, professional-looking vector logo with accurate typography and a consistent vintage style. In contrast, Vidu Q2 failed significantly on text rendering, producing multiple misspellings and redundant lines of text, while also failing to capture the 'minimalist vector' aesthetic.
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]
- + Excellent adherence to the color palette using navy, white, and muted red.
- + High-quality, detailed icons that accurately reflect the spacecraft mentioned.
- + Logical layout that mostly follows the requested mission steps.
- − Several spelling errors in the labels and scrambled text in the footer icons.
- − The order of icons is a bit jumbled, placing 'Launch' at the bottom after earlier steps.
Vidu Q2
- + Clean light-gray background follows the requested palette style.
- + Consistent flat-vector aesthetic across all icons.
- − Severe text corruption and illegibility for almost every label.
- − Incorrect number of steps and illogical flow compared to the prompt.
- − Did not accurately render the Saturn V or the specific mission stages requested.
Verdict: FLUX.2 [dev] produces a much more professional and visually complex infographic that captures the spirit of the NASA prompt, despite some jumbled text and layout issues. Vidu Q2 fails significantly on text legibility and icon accuracy, providing a much simpler and less informative graphic.
Explore each model
ShengShu Technology's text-to-image and reference-to-image model with support for character consistency and multi-reference image processing