Head to head
Esc

Models · slot A

to navigate to pick

HiDream I1 Fast HiDream AI Stable Diffusion 3.5 Large Turbo Stability AI

Settled by community votes across 13 shared challenges, with an AI judge weighing in on each.

HiDream I1 Fast

18.2 arena score

#50 of 62 in Text-to-Image

Skill signature · Text-to-Image

Stable Diffusion 3.5 Large Turbo

10.7 arena score

#61 of 62 in Text-to-Image

Vote tally

Where the votes landed

HiDream I1 Fast

0%

win rate

Ties

0%

Stable Diffusion 3.5 Large Turbo

0%

win rate

Shared challenges 13

Challenge by challenge

The strongest take from each model on every shared challenge, with the AI judge's read.

Geometric Composition

Text-to-Image

“A glass cube on a wooden table. Inside the cube is a small blue sphere. On top of the cube sits a red book. A green plant is behind the cube, partially visible through the glass. Soft window light from the left.”

HiDream I1 Fast
Stable Diffusion 3.5 Large Turbo

AI Judge Analysis

HiDream I1 Fast

  • + Excellent adherence to the spatial requirements of the prompt.
  • + Realistic glass transparency and reflections.
  • + High quality photographic aesthetic with natural depth of field.
  • The sphere appears slightly large for the cube.
  • The blue sphere seems to be floating rather than resting on the bottom.

Stable Diffusion 3.5 Large Turbo

  • + Sharp lighting and shadows consistent with window light.
  • + Clean, modern aesthetic.
  • Failed the spatial prompt: the red book is inside the cube rather than on top.
  • The glass cube has dark frames that weren't requested, making it look more like a display case.
  • The plant is to the left rather than clearly behind and visible through the glass.

Verdict: HiDream I1 Fast followed all spatial instructions perfectly, placing the sphere inside the cube and the book on top. Stable Diffusion 3.5 Large Turbo failed several positional requirements, placing the book inside the cube and the plant to the side. HiDream I1 Fast is the clear winner for its superior prompt adherence and realistic photographic quality.

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.”

HiDream I1 Fast
Stable Diffusion 3.5 Large Turbo

AI Judge Analysis

HiDream I1 Fast

  • + Excellent atmosphere with realistic reflections and wet pavement
  • + Accurately captures the 'shallow depth of field' and 'candid' street photography aesthetic
  • + Strong adherence to the 'motion blur from passing cars' request
  • The man appears to be sitting through the bike frame rather than interacting with it naturally
  • Anatomical issues with the man's hands being small or indistinct

Stable Diffusion 3.5 Large Turbo

  • + Clear rain streaks and detailed red bicycle frame
  • + Focuses squarely on the act of repairing the bike
  • Lacks the requested 'motion blur' from cars and cinematic depth of field
  • Skin and clothing textures appear plastic and unnaturally smooth
  • Anatomical distortion where the man's head blends into his collar/hood awkwardly

Verdict: HiDream I1 Fast better captures the specific photographic mood and technical requirements of the prompt, such as the motion blur and wet pavement reflections. Stable Diffusion 3.5 Large Turbo fails to deliver the cinematic realism requested, producing an image that looks more like a 3D render with significant anatomical errors in the subject's neck and head area.

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.”

HiDream I1 Fast
Stable Diffusion 3.5 Large Turbo

AI Judge Analysis

HiDream I1 Fast

  • + Excellent adherence to the 'beads in hair' prompt element.
  • + The engraved plate armor looks metallic and high-quality with clear torchlight reflections.
  • + Highly detailed facial hair and realistic skin texture with subtle scarring.
  • The scars look slightly painted on rather than integrated into the skin.
  • Background bokeh shapes are a bit busy and distracting.

Stable Diffusion 3.5 Large Turbo

  • + Strong composition with a focus on the facial features.
  • + Good depiction of the quilted cloth collar and layered armor pieces.
  • + Smooth skin rendering with a youthful aesthetic.
  • Failed to include the requested beads in the braided hair.
  • Lighting feels more like studio lighting than warm environmental torchlight.
  • Blood/dirt marks on the face look like flat textures rather than battle-worn grime.

Verdict: HiDream I1 Fast followed the prompt much more accurately, successfully including the specific 'beads in braids' and 'torchlight' requirements that Stable Diffusion 3.5 Large Turbo missed. Additionally, HiDream I1 Fast provided a more convincing 'battle-worn' texture on both the skin and the armor, whereas the character in the Stable Diffusion output looks too polished for the requested theme.

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.”

HiDream I1 Fast
Stable Diffusion 3.5 Large Turbo

AI Judge Analysis

HiDream I1 Fast

  • + Strong layout that resembles an actual single-page menu card
  • + Large bold header and clear price indicators
  • + Food photos are arranged in a clean, professional grid
  • Text is highly garbled and illegible even for main headings
  • Food items are almost exclusively pizza despite several general sections
  • Severe graphical artifacts on the text lines

Stable Diffusion 3.5 Large Turbo

  • + High visual quality with vibrant, saturated food photography
  • + Cleaner text rendering for headers like 'Pizza' and 'Mians'
  • + Effective use of white space and shadow depth for a modern aesthetic
  • The layout is more of a flat-lay photography scene than a single menu design
  • Some food items look like 3D plastic renders rather than real food
  • Grid of photos is somewhat disjointed from the text sections

Verdict: HiDream I1 Fast creates a layout that feels more like a functional restaurant menu, but the text is incredibly messy and the food lacks variety. Stable Diffusion 3.5 Large Turbo produces much higher quality imagery and cleaner typography (despite some spelling errors like 'Mians'), offering a more professional and modern aesthetic for a casual dining brand.

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.”

HiDream I1 Fast
Stable Diffusion 3.5 Large Turbo

AI Judge Analysis

HiDream I1 Fast

  • + Excellent text rendering with 'MAGIC BURGER' and '€6.99' clear and legible.
  • + Successfully includes all requested elements like the starburst and primary/secondary messages.
  • + High photorealistic detail on the ingredients, especially the patty and vegetables.
  • The 'exploded' effect is minimal; most components are still stacked rather than suspended in mid-air.
  • A circular graphic overlaps the secondary text redundantly.

Stable Diffusion 3.5 Large Turbo

  • + Stronger sense of motion and 'exploded' feel with dripping sauces and intense fire.
  • + Dramatic lighting and high-contrast background align well with the 'fiery' prompt.
  • + Creative interpretation of the burger being cooked by the flames.
  • Completely failed to generate the requested text and starburst element.
  • The image has a more 'digital illustration' feel rather than the requested 'photorealistic' detail.
  • Component separation is less distinct than in a traditional exploded view.

Verdict: HiDream I1 Fast is the clear winner as it successfully integrated all the complex text and layout requirements of the prompt, including the price starburst and title. Stable Diffusion 3.5 Large Turbo produced a more visually dynamic image in terms of the fire and motion, but it failed entirely on the textual and advertising components requested.

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.”

HiDream I1 Fast
Stable Diffusion 3.5 Large Turbo

AI Judge Analysis

HiDream I1 Fast

  • + Excellent adherence to the requested text content
  • + Realistic chalk texture and natural handwriting variations
  • + Convincing cozy café atmosphere with shallow depth of field
  • Noticeable overlapping of text and artifacts near the prices
  • Spelling error in 'Brown Buter'

Stable Diffusion 3.5 Large Turbo

  • + Clean layout and composition
  • + High-quality lighting effects and background details
  • Severe spelling errors and garbled text across the entire board
  • Failed to include the specific date requested (April 30, 2026)
  • Font looks digital rather than a realistic handwritten chalk texture

Verdict: HiDream I1 Fast followed the prompt much more effectively, accurately rendering the specific date and most of the menu items in a believable chalk style. Stable Diffusion 3.5 Large Turbo failed significantly on text legibility, producing garbled words and missing the prompt's specific content requirements.

The Reversed Rodeo

Text-to-Image

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

HiDream I1 Fast
Stable Diffusion 3.5 Large Turbo

AI Judge Analysis

HiDream I1 Fast

  • + Excellent anatomical realism of the horse and rider.
  • + Consistent lighting and high-quality textures on the spacesuit.
  • Failed the negative constraint; the astronaut is riding the horse.
  • Failed the environmental constraint; the setting is a desert, not space.
  • Lacks the requested surrealism.

Stable Diffusion 3.5 Large Turbo

  • + Correctly placed the scene in space with Earth and a moon in the background.
  • + Strong cinematic lighting with high contrast.
  • + Composition feels more surreal and imaginative.
  • Failed the primary logic constraint; the astronaut is riding the horse instead of the horse riding the astronaut.
  • Minor anatomical issues with the horse's legs and hooves in the shadow.

Verdict: Both models failed the specific logic constraint of having the 'horse on top' of the astronaut. However, Stable Diffusion 3.5 Large Turbo is the clear winner because it correctly placed the scene in space, whereas HiDream I1 Fast generated a standard desert environment. Stable Diffusion 3.5 Large Turbo also better captured the 'surreal' and 'cinematic' style requested.

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.”

HiDream I1 Fast
Stable Diffusion 3.5 Large Turbo

AI Judge Analysis

HiDream I1 Fast

  • + The lighting in the taxi and the bokeh in the background are very realistic.
  • + The businesswoman is clearly visible and following the prompt's instructions regarding her expression and phone.
  • The capybara has human hands, which is a significant anatomical error.
  • The capybara is positioned in the driver's seat but its body seems to blend awkwardly with human clothing/arms.

Stable Diffusion 3.5 Large Turbo

  • + The capybara has realistic paws on the steering wheel as requested.
  • + The composition and perspective inside the vehicle feel very authentic to a taxi ride.
  • The businesswoman in the back seat is out of focus and less detailed compared to Model A.
  • The background city lights feel slightly more generic and less like Manhattan than Model A.

Verdict: Stable Diffusion 3.5 Large Turbo is the winner because it successfully rendered the capybara's paws, whereas HiDream I1 Fast gave the animal distinctly human hands. While HiDream I1 Fast had better detail on the passenger, Stable Diffusion 3.5 Large Turbo followed the anatomical instructions of the prompt much better.

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.”

HiDream I1 Fast
Stable Diffusion 3.5 Large Turbo

AI Judge Analysis

HiDream I1 Fast

  • + Successfully included all the specific event details like date, time, and location.
  • + Captures a strong 'vintage parchment' aesthetic with a balanced composition.
  • + Includes the requested scroll banner and gothic title text.
  • Text rendering is messy, with several typos and overlapping characters at the bottom.
  • The background trees and jack-o-lantern are somewhat generic in style.

Stable Diffusion 3.5 Large Turbo

  • + High visual clarity and sharp, polished vector-style graphics.
  • + Highly effective interpretation of the 'thorns and webs' border requirement.
  • + The central jack-o-lantern has a very strong, expressive design.
  • Fails to include almost all requested text including the date, time, location, and scroll message.
  • Missing the moody night sky, opting for a bright, glowing background instead.

Verdict: HiDream I1 Fast followed the prompt much more comprehensively, including all the specific event details and banners requested, despite some text artifacts. Stable Diffusion 3.5 Large Turbo produced a cleaner image with a superior border, but failed to include the majority of the required information, making it ineffective as an invitation.

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.”

HiDream I1 Fast
Stable Diffusion 3.5 Large Turbo

AI Judge Analysis

HiDream I1 Fast

  • + Excellent text rendering with correct spelling and layout.
  • + Clean, solid blue background as requested in the prompt.
  • + Superior 3D cartoon aesthetics with soft, refined textures.
  • Logic error in sushi construction where toppings and fillings overlap strangely.
  • The miniature flag icon includes some messy artifacts.

Stable Diffusion 3.5 Large Turbo

  • + Stronger isometric 3D perspective and diorama shading.
  • + Good use of PBR materials with realistic reflections on the plate.
  • Spelling error in 'SUSHI' rendered as 'SIIHI'.
  • Incorporated a sign board instead of the requested top-center bold text style.
  • The flag icon is incorrect, resembling a generic red/white block rather than the Japanese flag.

Verdict: HiDream I1 Fast is the clear winner as it correctly followed the text instructions and background color requirements. While Stable Diffusion 3.5 Large Turbo had nice lighting and materials, it failed on spelling and ignored the specific layout instructions for the text and background.

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.”

HiDream I1 Fast
Stable Diffusion 3.5 Large Turbo

AI Judge Analysis

HiDream I1 Fast

  • + Excellent variety and accuracy of the requested animals including the fox and two kittens.
  • + Captures the golden sunrise lighting and god rays effectively.
  • + Higher level of fur detail and realistic textures.
  • Missing the baby bunny requested in the prompt.
  • The background is very blurred, losing some of the 'lush meadow' feel.

Stable Diffusion 3.5 Large Turbo

  • + Dynamic 'tumbling' interaction between the characters.
  • + Lush and vibrant flower detail in the foreground.
  • + Whimsical butterfly designs.
  • The animals look more like generic cartoons or hybrids than specific breeds like Golden Retriever or Fox.
  • Missing the baby bunny and has an inconsistent number of legs/paws for the central puppy.
  • Lower photorealistic quality with some 'plastic' fur textures.

Verdict: HiDream I1 Fast is the superior image as it more accurately depicts the specific animals requested (like the fox and tabby kitten) and achieves a much higher level of photorealistic fur texture and cinematic lighting. Stable Diffusion 3.5 Large Turbo struggles with anatomical coherence and produces a more stylized, less realistic result that fails to capture the distinct species described in the prompt.

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.”

HiDream I1 Fast
Stable Diffusion 3.5 Large Turbo

AI Judge Analysis

HiDream I1 Fast

  • + Clean vector-style execution
  • + Accurate color palette according to the prompt
  • + Good use of negative space on the cloche dome
  • Typos in the text including an extra zero in '17210'
  • The steam is rendered as abstract crescent shapes that look like loose lines
  • Text alignment within the cloche is slightly cluttered

Stable Diffusion 3.5 Large Turbo

  • + Excellent typography rendering for both the main name and established date
  • + Beautiful vintage woodcut texture and shading
  • + Creative integration of a coffee mug base with the cloche dome
  • Added an extra 'e' to 'Caffe' (Caffee)
  • The background texture is a bit heavy-handed compared to the 'light background' request

Verdict: Stable Diffusion 3.5 Large Turbo produces a much more sophisticated and professional-looking logo with superior shading and text legibility, despite a minor spelling error. HiDream I1 Fast delivers a simpler vector style but fails significantly on the date accuracy, rendering 17210 instead of 1720.

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.”

HiDream I1 Fast
Stable Diffusion 3.5 Large Turbo

AI Judge Analysis

HiDream I1 Fast

  • + Successfully followed the requested steps in a logical sequence
  • + Icons are generally distinct and relevant to the labels
  • + Good use of the requested NASA-inspired color palette
  • Text rendering is poor with numerous typos like 'DESCENG' and 'EOH OPBIT'
  • Visual layout feels cluttered with thin, disconnected lines

Stable Diffusion 3.5 Large Turbo

  • + Superior aesthetic with a professional flat-vector infographic style
  • + Clean typography and layout balance
  • + Creative use of negative space and composition
  • Failed to follow the specific 6-step sequence requested in the prompt
  • Text rendering contains gibberish and misspellings like 'Apoll.o' and 'Laurch'
  • Missing specific requested icons like the Saturn V

Verdict: HiDream I1 Fast followed the instructional structure of the prompt much better, attempting to display all six mission steps in order, though it suffered from significant spelling errors and messy lines. Stable Diffusion 3.5 Large Turbo produced a much more visually impressive and 'modern vector' piece of art, but it largely ignored the specific step-by-step requirements of the infographic. HiDream I1 Fast is the winner for utility, despite the poor text quality.

Next steps

Explore each model