Distilled version of HiDream AI's 17B parameter text-to-image model
Settled by community votes across 13 shared challenges, with an AI judge weighing in on each.
HiDream I1 Fast
#50 of 62 in Text-to-Image
Vidu Q2
#42 of 62 in Text-to-Image
Where the votes landed
HiDream I1 Fast
100.0%
win rate
Ties
0.0%
Vidu Q2
0.0%
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
HiDream I1 Fast
- + Clean glass rendering with logical edge highlights
- + Sphere is centered and well-contained within the cube structure
- − The sphere is quite large, ignoring the 'small' descriptor in the prompt
- − The glass cube lacks a top lid, making the book appear to float or sit on the thin edges
Vidu Q2
- + Highly accurate adherence to the 'small' descriptor for the blue sphere
- + Exceptional realism in the textures of the book and the wooden table grain
- + Successfully captures the specific lighting interaction, including shadows from the plant
- − The plant is more overhead than strictly 'behind' the cube
- − Minor distortion in the glass refraction at the front edge
Verdict: Vidu Q2 is the clear winner as it followed every part of the prompt, including the scale of the 'small' sphere and the placement of the red book on a solid glass top. While HiDream I1 Fast produced a clean image, it failed to capture the correct size proportions and the physics of the book sitting on the cube.
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
HiDream I1 Fast
- + Excellent atmospheric lighting and reflections on the wet pavement.
- + Accurately represents the 50mm shallow depth of field requested.
- + Strong composition with a cinematic mood.
- − Misses the 'motion blur' requirement for the car in the background.
- − The man is sitting on the bike rather than actively repairing it.
- − The bicycle's anatomy is slightly simplified and unrealistic in the frame area.
Vidu Q2
- + Successfully captures the specific action of 'repairing' the bicycle.
- + Outstanding skin texture and realistic detail in the hands and face.
- + Includes subtle motion blur on the passing vehicle as requested.
- − The composition is very tight, making the framing feel cramped rather than 'imperfect' and candid.
- − The bicycle's frame geometry is physically impossible (dual front forks/frames intersecting).
Verdict: Vidu Q2 is the winner because it adhered more closely to the specific details of the prompt, including the action of repairing and the motion blur. While HiDream I1 Fast produced a more aesthetically pleasing cinematic wide shot, Vidu Q2 captured the 'natural skin texture' and 'no stylization' requirements with much higher fidelity.
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
HiDream I1 Fast
- + Excellent adherence to the 'beads in braids' requirement with vibrant details.
- + Superior engraving fine-detail on the armor plates.
- + Strong atmospheric lighting with effective torchlight reflections and bokeh.
- − The scars look a bit like face paint rather than physical wounds.
- − Hair merging slightly into the armor on the left side.
Vidu Q2
- + Naturalistic skin texture and dirt application that feels authentic.
- + Excellent technical detail on leather straps and textile underlayers.
- + Very lifelike eyes and expression.
- − The braid beads are very sparse compared to the prompt request.
- − Armor engravings are less intricate than Model A's.
Verdict: HiDream I1 Fast delivers a more 'fantasy epic' look with highly intricate armor engravings and very prominent beads in the hair as requested. However, Vidu Q2 captures a more realistic 'battle-worn' texture with superior fabric and leather detailing. HiDream I1 Fast is the winner for better literal adherence to the specific decorative elements like the beads and ornate engravings.
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
HiDream I1 Fast
- + Strong typography in the header
- + Well-defined grid layout for food photos
- + High contrast and bold design elements
- − Nonsensical header text
- − Poor rendering of smaller text and numbers
- − Lacks variety in food items, showing mostly pizza
Vidu Q2
- + Excellent adherence to the sections requested (Appetizers, Pizza, Mains)
- + Vibrant and high-quality food photography
- + Superior design aesthetics that mimic a real modern menu
- − Text consists of gibberish characters
- − Slightly cluttered composition due to the amount of content
Verdict: Vidu Q2 is the clear winner for its sophisticated design and faithful adherence to the multiple sections requested in the prompt. While HiDream I1 Fast provides a bold header, its core content is repetitive and less professional than the colorful, well-structured layout of Vidu Q2.
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
HiDream I1 Fast
- + Text rendering for 'MAGIC BURGER' is extremely clean and legible.
- + Excellent photorealistic detail on the textures of the bun and sesame seeds.
- + Integrated a clear starburst for the price as requested.
- − Failed the 'exploded' requirement as the burger remains largely assembled.
- − The secondary text 'LIMITED TIME ONLY' is garbled and contains spelling errors.
- − Lacks a strong sense of motion in the burger components.
Vidu Q2
- + Followed the 'exploded' instruction well, showing clear separation between layers.
- + Captures a dynamic sense of motion with splashes of sauce and floating components.
- + Successfully rendered all requested text elements accurately and legibly.
- − The currency symbol in the price starburst is slightly deformed.
- − The fire effect is a bit more illustrative and less photorealistic than Image A.
Verdict: Vidu Q2 is the clear winner as it successfully followed the core prompt instructions for an 'exploded' burger with a sense of motion, whereas HiDream I1 Fast produced a static, mostly assembled burger. Additionally, Vidu Q2 managed to render all the requested text accurately, while HiDream I1 Fast failed on the secondary text message.
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
HiDream I1 Fast
- + The handwriting style is very neat and mostly legible.
- + Includes the full café context with plants, lighting, and a coffee cup.
- − Numerous overlay artifacts where text overlaps or doubles up.
- − Many spelling errors such as 'Buter' and 'Herbs' having numbers mixed into letters.
- − Significant 'ghost' text and digital-looking artifacts in the middle of the board.
Vidu Q2
- + Very realistic chalk texture with smudges and natural handwriting variations.
- + Captures the cursive title accurately as requested.
- + The 'handwritten' feel is more authentic than a digital replica.
- − Significant spelling errors throughout the menu items (e.g., 'Truffe Mushhoom', 'Octopd wpiln').
- − Missed a few of the specific pricing requests (e.g., $34 instead of $24).
Verdict: Vidu Q2 is the superior choice because it captures the requested 'handwritten chalk style' with much more authenticity, including natural texture and smudging. While HiDream I1 Fast has a clearer environmental shot, the board is riddled with digital-looking glitches and overlapping text that breaks the requested realism.
The Reversed Rodeo
Text-to-Image“Horse riding astronaut in space — horse on top, not vice versa. Surreal, highly detailed, cinematic.”
AI Judge Analysis
HiDream I1 Fast
- + Clean, high-resolution rendering of the space suit and horse.
- + Consistent lighting and shadows on the ground.
- − Completely failed the semantic prompt to put the horse on top of the astronaut.
- − Failed the location prompt by placing the subject in a desert instead of space.
- − Traditional, non-surreal composition.
Vidu Q2
- + Successfully adhered to the 'in space' setting with a vibrant, celestial background.
- + Incorporated surreal elements with the galaxy-textured horse skin.
- + Highly detailed and artistic interpretation of the subject matter.
- − Failed the specific structural instruction 'horse on top, not vice versa'.
- − Some anatomical awkwardness in the horse's front legs.
Verdict: Both models failed to follow the specific 'horse on top' spatial instruction, which was a trick prompt to test structural understanding. However, Vidu Q2 is the superior image as it correctly followed the environment prompt (space) and the artistic style (surreal/cinematic), whereas HiDream I1 Fast generated a mundane desert scene.
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
HiDream I1 Fast
- + Excellent photographic quality and bokeh effect
- + High-quality fur texture and lighting
- + Realistic New York street atmosphere
- − The driver has human hands instead of capybara paws
- − The passenger is sitting in the front/middle seat rather than the requested back seat
- − The capybara's head is not anatomically connected to the body naturally
Vidu Q2
- + Successfully places the passenger in the back seat as requested
- + Includes animal-like paws on the steering wheel
- + Stronger adherence to the overall spatial layout requested in the prompt
- − The lighting in the cabin is a bit flat and less realistic than model_a
- − The capybara's head is slightly disproportionate to its body
- − The passenger's phone and hand grip look unnatural
Verdict: Model B (Vidu Q2) is the winner because it adhered to the difficult spatial requirements of the prompt, correctly placing the businesswoman in the back seat and giving the capybara paws instead of human hands. While Model A (HiDream I1 Fast) has superior lighting and textures, it failed significantly on physics and composition by merging human hands onto the capybara and placing the woman in the passenger seat.
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
HiDream I1 Fast
- + Includes all elements of the prompt including webs and trees
- + The date text '30.10.2026' is rendered perfectly
- + Clean illustrative style with good contrast
- − Failed to include 'Invitation' in the main title
- − Text on the scroll banner and event location contains messy, overlapping characters
- − Vignette feels a bit flat compared to the requested cinematic lighting
Vidu Q2
- + Excellent integration of the 'thorns' into the border composition
- + Better parchment texture and lighting on the jack-o-lantern
- + Captured the full title including the word 'Invitation'
- − Significant spelling errors in every single line of text
- − Incorrect date (2025 instead of 2026)
- − The web and thorn border is slightly cluttered and cuts off at the edges
Verdict: HiDream I1 Fast is the superior choice for a functional invitation because it rendered the critical event date correctly and with high legibility, despite missing a word in the title. Vidu Q2 had a more atmospheric and detailed 'gothic' aesthetic, but it suffered from severe spelling hallucinations like 'Intovztion' and 'invieed ta might of fiigts' which renders the invitation unusable.
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
HiDream I1 Fast
- + Excellent typography and layout design
- + Very clean 3D render with soft, professional lighting
- + Follows the isometric miniature aesthetic perfectly
- − The salmon nigiri has an odd cross-section texture that looks like a maki roll
- − Slightly less variety in sushi types compared to the other image
Vidu Q2
- + Includes a nice variety of sushi types (shrimp, tuna, etc.)
- + Good placement of the flag icon in relation to the text
- + Captures the diorama base requirement well
- − Text rendering is slightly blurry with some haloing artifacts
- − Shadows and lighting are less refined than the competitor
- − The 'JAPAN' text has a slight letter distortion on the 'N'
Verdict: HiDream I1 Fast produces a significantly cleaner and more professional-looking graphic with superior typography and lighting. While Vidu Q2 offers more variety in the sushi models, it suffers from lower clarity and artifacting around the text, making HiDream I1 Fast the better overall interpretation of the 'ultra-clean' prompt.
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
HiDream I1 Fast
- + Excellent fur texture rendering and soft lighting.
- + Expressive and aesthetically pleasing facial features for the animals.
- + Strong rim lighting that enhances the golden sunrise theme.
- − Failed to include the baby bunny entirely.
- − The animals are sitting still rather than 'playfully chasing butterflies' or 'tumbling'.
- − One of the kittens is duplicated/blended into the composition.
Vidu Q2
- + Successfully included all requested animals: retriever, kitten, fox, and bunny.
- + Captures the action of 'playfully chasing' with dynamic posing.
- + Includes more butterflies and visible dew sparkles as requested in the prompt.
- − Anatomy errors present, such as the fox kit having a puppy-like fourth leg/tail confusion.
- − The fox kit has a slightly distorted face compared to the other animals.
- − Image composition feels a bit cluttered with many overlapping elements.
Verdict: Vidu Q2 is the winner because it adhered much better to the specific entity and action requirements of the prompt, including all four animal types and the requested dynamic motion. While HiDream I1 Fast produced a more polished portrait with superior fur detail, it failed a significant part of the prompt by omitting the bunny and ignoring the 'chasing and tumbling' action.
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
HiDream I1 Fast
- + Excellent typography with correct spelling of 'Caffè Florian'
- + Clean vector emblem style with high contrast
- + Well-balanced composition with a clear banner element
- − Typos in the numerical date showing '17210' instead of '1720'
- − Steam elements are a bit stylized and look like detached arcs
Vidu Q2
- + Subtle texture on the background matches the prompt
- + Good representation of steam coming from the cloche
- − Severe spelling errors including 'Farmiin' and 'Fopli20'
- − Confused composition with redundant and redundant text lines
- − Poor typography that lacks professional logo quality
Verdict: HiDream I1 Fast produces a professional-looking vector logo that follows the layout instructions and colors perfectly, despite a minor digit error in the date. Vidu Q2 fails significantly on text legibility and spelling, outputting multiple garbled lines of text that clutter the design. HiDream I1 Fast is the clear winner for its superior visual clarity and brand adherence.
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
HiDream I1 Fast
- + Stronger adherence to the requested navy, white, and red color palette
- + Composition more closely resembles a traditional infographic poster with a central focal point
- + Illustrations like the Saturn V and US flag are recognizable
- − Text rendering is severely garbled and includes misspellings like 'DESCENG'
- − The logical flow of the steps is confusing and doesn't follow a clear sequential path
Vidu Q2
- + Much cleaner vector icons with consistent line weights and style
- + Higher visual quality with crisp, modern execution of the 'flat-vector' request
- + Clearer grid-based information hierarchy
- − Failed the main title text entirely, displaying 'ALFONCH' instead of 'Apollo 11'
- − Text throughout the image is gibberish despite having a clean font
- − Included unnecessary green and blue tones that deviate from the requested NASA palette
Verdict: HiDream I1 Fast followed the requested color palette more accurately and captured the spirit of the Apollo mission icons, but suffered from messy presentation. Vidu Q2 produced much higher quality vector artwork and a cleaner layout, but failed completely on the text content and specific title instruction. Vidu Q2 is preferred for its superior aesthetic quality and icon consistency, which are harder to fix than text in post-production.
Explore each model
ShengShu Technology's text-to-image and reference-to-image model with support for character consistency and multi-reference image processing