Head to head
Esc

Models · slot A

to navigate to pick

HiDream I1 Full HiDream AI Stable Diffusion 3.5 Medium Stability AI

Settled by community votes across 12 shared challenges, with an AI judge weighing in on each.

HiDream I1 Full

15.2 arena score

#60 of 62 in Text-to-Image

Skill signature · Text-to-Image

Stable Diffusion 3.5 Medium

16.8 arena score

#58 of 62 in Text-to-Image

Vote tally

Where the votes landed

HiDream I1 Full

100.0%

win rate

Ties

0.0%

Stable Diffusion 3.5 Medium

0.0%

win rate

100.0% 0.0% ties 0.0%
Shared challenges 12

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 Full
Stable Diffusion 3.5 Medium

AI Judge Analysis

HiDream I1 Full

  • + Excellent photorealism with convincing textures on the red book and the wooden table.
  • + Accurate lighting and reflections, including the sphere's reflections on the inner glass surfaces.
  • + Superior composition and depth of field.
  • The plant behind the cube is quite blurry, though technically visible.

Stable Diffusion 3.5 Medium

  • + Successfully includes all requested elements in the prompt.
  • + Clear visibility of the plant through the glass.
  • The physics and perspective of the glass cube look somewhat distorted and flat.
  • Visual quality is lower with harsher lighting and less convincing material textures.

Verdict: HiDream I1 Full produces a much higher quality, photorealistic image with beautiful lighting and complex reflections that make the scene feel tangible. Stable Diffusion 3.5 Medium follows the prompt accurately but lacks the artistic polish and realistic depth found in the other model.

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 Full
Stable Diffusion 3.5 Medium

AI Judge Analysis

HiDream I1 Full

  • + Excellent character detail with natural skin texture and expression.
  • + High-quality reflections and wet pavement rendering.
  • + Clean composition with a convincing shallow depth of field.
  • The man is oddly sitting/straddling the rear wheel in a physically impossible way.
  • Missing the requested motion blur on the passing cars.
  • Background cars lack a specific Japanese aesthetic.

Stable Diffusion 3.5 Medium

  • + Captures a very authentic 'candid street photo' feel with imperfect framing.
  • + Accurately depicts the rainy atmosphere and wet textures.
  • + Better adherence to the 'imperfect framing' and 'candid' aspects of the prompt.
  • Serious anatomical and structural issues with the man's hands and the bicycle's geometry.
  • The man's face is largely obscured and lacks detail.
  • Lower overall image resolution and clarity compared to Model A.

Verdict: HiDream I1 Full produces a much higher quality image with impressive textures and reflections, though it fails to include the requested motion blur and features a physically impossible seating position. Stable Diffusion 3.5 Medium does a better job of capturing the specific requested 'candid' and 'imperfect' photography style but suffers from significant distortions in the man's hands and the bicycle's parts. HiDream I1 Full is the winner for its superior visual fidelity and realistic human rendering despite the minor structural oddity.

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 Full
Stable Diffusion 3.5 Medium

AI Judge Analysis

HiDream I1 Full

  • + Excellent depiction of ornate engraved plate armor
  • + Clear and distinct beads in the braided hair
  • + Highly detailed realism in the leather strap textures
  • The scars look like surface paint rather than realistic skin texture

Stable Diffusion 3.5 Medium

  • + Excellent warm torchlight lighting and skin texture
  • + Strong use of bokeh sparks and atmospheric background
  • + More natural integration of dirt and grime on the face
  • The 'small beads' in the hair are largely missing or indistinct
  • The armor engraving is less detailed compared to Model A

Verdict: HiDream I1 Full excels in capturing technical prompt details like the ornate armor engravings and specific leather textures, as well as the 'small beads' in the hair. Stable Diffusion 3.5 Medium provides a more atmospheric and lifelike lighting effect with superior skin rendering, but fails to incorporate the requested beads. Overall, HiDream I1 Full is the winner for its superior prompt adherence and sharp detail clarity.

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 Full
Stable Diffusion 3.5 Medium

AI Judge Analysis

HiDream I1 Full

  • + Excellent text legibility and clean sans-serif typography
  • + High-quality, appetizing food photography
  • + Clear, professional layout that matches the minimalist prompt
  • Limited variety in food images as they are all very similar pizzas
  • Lacks the specific separate sections for 'Appetizers' and 'Mains' as distinct categories with diverse items

Stable Diffusion 3.5 Medium

  • + Features a diverse grid of various food types including salads and main dishes
  • + Better adherence to the 'grid' aspect of the prompt with multiple small photos
  • + More comprehensive menu layout with more items and pricing
  • Text is largely gibberish and poorly rendered compared to the competition
  • Fonts are stylized/sketchy rather than the requested bold sans-serif
  • Images contain some minor AI artifacts and inconsistent lighting

Verdict: HiDream I1 Full produces a much more professional and realistic menu with coherent text and high-clarity images, though it struggles with the variety of food types requested. Stable Diffusion 3.5 Medium follows the layout and grid complexity instructions more closely but fails significantly on text legibility and font style. HiDream I1 Full is the overall winner for its superior visual quality and professional finish.

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 Full
Stable Diffusion 3.5 Medium

AI Judge Analysis

HiDream I1 Full

  • + Legible title text with correct date
  • + Clean visual presentation
  • + Realistic chalk texture on the coffee illustration
  • The menu items are mostly gibberish or nonsensical words like 'Fart Sanl'
  • The text looks more like a digital font rather than natural handwriting
  • Failed to include any of the specifically requested menu items

Stable Diffusion 3.5 Medium

  • + Attempts the specific menu items like 'Mushroom Risato' and 'Grilled'
  • + Very realistic chalk texture with smudges and natural variations
  • + Hand-drawn artistic style matches the 'no digital fonts' requirement well
  • Spelling is inconsistent and messy in several areas
  • The date at the top is jumbled and incorrect
  • The layout is a bit cluttered compared to Model A

Verdict: HiDream I1 Full produces a cleaner image with better spelling for the title, but it relies on a digital-looking font and fails to include the requested menu items. Stable Diffusion 3.5 Medium follows the prompt's content and artistic style much better, capturing the specific food items and a genuine hand-drawn chalk feel despite some spelling artifacts. Stable Diffusion 3.5 Medium is the winner for better prompt adherence and creative execution of the 'handwritten' requirement.

The Reversed Rodeo

Text-to-Image

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

HiDream I1 Full
Stable Diffusion 3.5 Medium

AI Judge Analysis

HiDream I1 Full

  • + Dynamic and cinematic composition with a sense of motion.
  • + Excellent lighting on the horse's coat and astronaut's suit.
  • + Better anatomical rendering of the horse compared to the competitor.
  • Failed the specific spatial instruction 'horse on top, not vice versa'.
  • The number of horse legs becomes slightly indistinct in the movement blur.

Stable Diffusion 3.5 Medium

  • + Sharp details on the astronaut's patches and gear.
  • + Clearer star field and cosmic background.
  • Failed the specific spatial instruction 'horse on top, not vice versa'.
  • Highly distorted leg anatomy with extra joints and misplaced limbs.
  • The horse's back legs appear to be growing out of its stomach area.

Verdict: Both models completely failed the negative constraint and specific spatial prompt to place the horse on top of the astronaut, providing a standard 'astronaut riding a horse' image instead. HiDream I1 Full is the clear winner as it produces a much more coherent and aesthetically pleasing image, whereas Stable Diffusion 3.5 Medium suffers from severe anatomical glitches and bizarre leg placement on the horse.

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 Full
Stable Diffusion 3.5 Medium

AI Judge Analysis

HiDream I1 Full

  • + Excellent adherence to the prompt regarding both paws on the steering wheel.
  • + Clear text rendering of 'TAXI' on the cap.
  • + High-quality rendering of the passenger's face and phone interaction.
  • The composition feels a bit tight, cutting off the back of the passenger.
  • The capybara's hands look slightly more human-like/primate than capybara paws.

Stable Diffusion 3.5 Medium

  • + Effective cinematic lighting and use of bokeh for city lights.
  • + Captures the professional, calm expression of the capybara well.
  • + Good texture on the capybara's fur and whiskers.
  • Failed to include the phone in the passenger's hand as requested.
  • The capybara's paws are not on a steering wheel; they appear to be resting on the dashboard or hood.
  • The passenger's expression is more focused on the driver than bored and looking at a phone.

Verdict: HiDream I1 Full followed all aspects of the prompt, including the specific requirement for the passenger to be on her phone and the driver's paws to be on the wheel. Stable Diffusion 3.5 Medium missed the phone and the steering wheel entirely, though it offered a nice atmospheric look. HiDream I1 Full is the clear winner for its superior prompt adherence and logical composition.

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 Full
Stable Diffusion 3.5 Medium
100% wins 0% ties 0% wins

AI Judge Analysis

HiDream I1 Full

  • + Successfully rendered the central glowing jack-o-lantern as requested.
  • + The scroll banner text is perfectly legible and accurate.
  • + Superior graphic design layout with elegant gothic styling.
  • The numerical event details at the bottom contain gibberish and incorrect dates.
  • Missing the specific name of the location 'The Arches' in the text.

Stable Diffusion 3.5 Medium

  • + Captures a more atmospheric, 'vintage' paper texture.
  • + Good use of space with twisted trees and cobweb borders.
  • Failed to render a central jack-o-lantern, placing two on the sides instead.
  • Significant spelling errors in every line of text, including 'Halloweeen' and 'Inviloween'.
  • The title text and location details are garbled and messy.

Verdict: HiDream I1 Full is the clear winner for its superior composition and legibility. While both models struggled with the specific date and location text, HiDream I1 Full followed the 'central glowing jack-o-lantern' instruction and produced clear, correctly spelled banner text, whereas Stable Diffusion 3.5 Medium suffered from severe spelling errors and poor layout.

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 Full
Stable Diffusion 3.5 Medium

AI Judge Analysis

HiDream I1 Full

  • + Excellent adherence to the 3D isometric cartoon aesthetic.
  • + Text rendering is clean and accurate for both JAPAN and SUSHI.
  • + Well-defined diorama base as requested.
  • Missing the small flag icon mentioned in the prompt.

Stable Diffusion 3.5 Medium

  • + Realistic textures on the roe and seaweed.
  • + Solid light blue background aligns with the prompt.
  • Failed to follow the text hierarchy, placing SUSHI as the primary word.
  • Missing the diorama base and the term JAPAN is very small and poorly integrated.
  • The composition is less balanced and has lower overall clarity.

Verdict: HiDream I1 Full significantly outperforms Stable Diffusion 3.5 Medium by adhering more closely to the stylistic requirements of a 3D isometric diorama. While both models missed the request for a small flag icon, HiDream I1 Full produced much cleaner text and a more visually appealing 3D cartoon style consistent with the prompt's aesthetic instructions.

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 Full
Stable Diffusion 3.5 Medium

AI Judge Analysis

HiDream I1 Full

  • + Successfully included four animals including a puppy, kittens, and a fox kit.
  • + Atmospheric lighting with clear god rays and a soft morning glow.
  • + Better rendering of butterfly wings and flower details.
  • Failed to include the baby bunny, replacing it with a second kitten.
  • The style is somewhat painterly/illustrative despite the hyper-photorealistic request.

Stable Diffusion 3.5 Medium

  • + More dynamic 'chasing' poses compared to the static posing in the alternative.
  • + Vibrant colors that enhance the joyful, wholesome vibe.
  • + Good fur texture and lighting effects.
  • Significant prompt failure by missing both the baby bunny and the tabby kitten (rendering a generic ginger animal instead).
  • Anatomical issues with the puppy's front legs and paws merging into the grass.
  • Only three distinct animals are present instead of the requested four.

Verdict: HiDream I1 Full is the winner because it adhered more closely to the complex prompt, successfully rendering four animals even though it swapped the bunny for a second kitten. Stable Diffusion 3.5 Medium failed to include several requested animals and suffered from more noticeable anatomical blurring in the foreground, though it captured the dynamic action better.

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 Full
Stable Diffusion 3.5 Medium

AI Judge Analysis

HiDream I1 Full

  • + Clean vector emblem style that matches the minimalist request.
  • + Accurate rendering of the date 'Est. 1720'.
  • + Excellent negative space usage with the coffee cup inside the cloche.
  • Completely omitted the primary text 'Caffè Florian'.
  • The steam effect is a bit generic.

Stable Diffusion 3.5 Medium

  • + Beautiful vintage hand-drawn illustration style.
  • + Attempts all text requirements from the prompt.
  • + Rich texture and intricate line work.
  • Several spelling errors including 'Florrian' and 'Est 170'.
  • The cloche is stylized as a sphere, losing the distinct dome shape.
  • Fails the 'minimalist' requirement with its high level of detail.

Verdict: HiDream I1 Full creates a much better logo for professional use due to its clean vector lines and successful 'minimalist' aesthetic, though it failed to include the brand name. Stable Diffusion 3.5 Medium captures the vintage vibe beautifully but fails on both the minimalist style and the spelling accuracy, which are critical for logo design.

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 Full
Stable Diffusion 3.5 Medium

AI Judge Analysis

HiDream I1 Full

  • + Clean vector aesthetic that matches the requested flat-vector style.
  • + Excellent typography for the main title with a thematic NASA-inspired logo.
  • + The central illustration is high-quality and well-balanced.
  • Failed to provide all six specific infographic steps requested in the prompt.
  • Output includes some nonsense text labels like 'EARTH V + ICON'.
  • Illustrations for 'Translunar' and 'Earth Orbit' include spaceships that do not match the historical Saturn V or Apollo hardware.

Stable Diffusion 3.5 Medium

  • + Successfully captured the requested number of steps (six icons).
  • + Accurate adhering to the requested NASA-inspired color palette.
  • + Includes a trajectory arc which was a specific requirement for the Translunar step.
  • Text is largely illegible and contains significant gibberish.
  • The 'Lunar Orbit' and 'Landing' steps feature images of Earth instead of the Moon.
  • The layout is cluttered and lacks the clean 'modern infographic' feel requested.

Verdict: HiDream I1 Full is the likely winner due to its superior visual quality and adherence to the 'flat-vector' style, producing a clean, professional-looking poster despite missing several requested steps. Stable Diffusion 3.5 Medium followed the structural instructions more closely by providing six icon steps, but its output is marred by illegible text and confusing iconography that makes it ineffective as an infographic.

Next steps

Explore each model