Head to head
Esc

Models · slot A

to navigate to pick

HiDream I1 Full HiDream AI Wan 2.7 Alibaba

Settled by community votes across 16 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

Wan 2.7

20.5 arena score

#39 of 62 in Text-to-Image

Vote tally

Where the votes landed

HiDream I1 Full

0.0%

win rate

Ties

0.0%

Wan 2.7

100.0%

win rate

0.0% 0.0% ties 100.0%
Shared challenges 16

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
Wan 2.7

AI Judge Analysis

HiDream I1 Full

  • + Excellent lighting and atmospheric quality with soft window light.
  • + Highly realistic glass textures and refraction effects.
  • + Floating sphere adds an interesting, artistic touch to the composition.
  • The plant is less visible through the glass compared to Model B.
  • The blue sphere is levitating, which may not have been the intended physics.

Wan 2.7

  • + Highly detailed book cover with visible text and texture.
  • + Very clear execution of the plant being visible through the glass panels.
  • + Excellent wooden table texture and realistic reflections on the glass floor of the cube.
  • The lighting feels a bit flatter and less 'soft' compared to Model A.
  • Slight perspective misalignment on the far right edge of the glass cube.

Verdict: Both models followed the prompt perfectly, but Model B (Wan 2.7) is slightly preferred for its superior detail in the book and table textures, as well as the clearer visibility of the green plant through the glass. HiDream I1 Full produced a more aesthetically pleasing lighting environment, but the floating placement of the sphere felt less grounded than Wan 2.7's rendition.

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
Wan 2.7

AI Judge Analysis

HiDream I1 Full

  • + Strong bokeh effect representing shallow depth of field
  • + Vibrant colors on the bicycle
  • + Dramatic reflections on the wet pavement
  • Physical impossibilities: the man is sitting on a bike with no seat post, and the wheel floats through his leg
  • Lacks the requested motion blur from passing cars
  • Anatomical issues with the hands

Wan 2.7

  • + Expertly captures the 'no stylization' cinematic street photography look
  • + Highly realistic skin textures and wet clothing
  • + More natural interaction between the man and the bicycle
  • Lacks the requested motion blur for passing cars
  • Depth of field is deeper than the requested 'shallow' 50mm look
  • The bystander in the background is slightly distorted

Verdict: Wan 2.7 dramatically outperforms HiDream I1 Full by following the 'no stylization' and 'candid photo' instructions to produce an image that looks like a real photograph. HiDream I1 Full suffers from severe structural hallucinations, such as the man sitting on a bicycle frame that lacks a seat post and passes through his leg, whereas Wan 2.7 maintains physical coherence.

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
Wan 2.7

AI Judge Analysis

HiDream I1 Full

  • + Intense, high-contrast lighting that emphasizes the torchlight reflection.
  • + Exquisite detail on the ornate engravings of the chestplate.
  • + Sharp, lifelike eye detail and symmetrical facial structure.
  • The scars look a bit like digital paint or face paint rather than integrated skin texture.
  • The bokeh sparks in the foreground are slightly distracting and less natural.

Wan 2.7

  • + Superior skin texture with realistic-looking faint scars and dirt integration.
  • + Excellent leather strap texture and believable armor distressing.
  • + Natural hair braiding with clear bead detailing.
  • The lighting is a bit flatter than Model A, lacking some of the 'warm glow' asked for.
  • The armor engravings are less complex than those in Model A.

Verdict: Both models followed the prompt exceptionally well, but Wan 2.7 produces a more grounded and realistic portrait with better skin and material cohesion. HiDream I1 Full offers a more 'epic' cinematic look with superior armor detail, though it feels slightly more synthetic in its facial rendering compared to Wan 2.7.

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
Wan 2.7

AI Judge Analysis

HiDream I1 Full

  • + Excellent text legibility for headers
  • + Clear, high-quality food photography
  • + Adheres strictly to the requested bold sans-serif fonts
  • Lack of variety in food photos as they are all pizzas
  • Significant amount of empty space and simple composition
  • Gibberish text in the item descriptions

Wan 2.7

  • + Sophisticated grid layout with a wide variety of food items
  • + Added branding elements like a logo, QR code, and social media handles
  • + Excellent use of color accents and secondary styling elements
  • Text becomes very blurry and illegible in smaller descriptions
  • Image includes non-requested background props like salt and oil
  • Misspelled words in some item titles

Verdict: Wan 2.7 provides a much more convincing and professional interpretation of a restaurant menu, featuring a diverse grid of food photos and realistic branding elements. While HiDream I1 Full has sharper text for the main headers, it fails to provide a variety of food types, showing only pizza for every section and leaving large areas of the layout unfinished.

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
Wan 2.7

AI Judge Analysis

HiDream I1 Full

  • + Clean layout with a nice illustrative sketch of a coffee cup.
  • + Legible title font.
  • Failed significantly on text prompt adherence, resulting in gibberish menu items.
  • Text style looks like a digital font rather than realistic chalk handwriting.
  • Ignored the specific menu items requested in the prompt.

Wan 2.7

  • + Excellent prompt adherence, accurately rendering all requested menu items and numbers.
  • + Text looks much more like hand-drawn chalk with natural variations.
  • + Captures the 'cozy café' atmosphere with superior lighting and background details.
  • The 'cursive' style for the title is more of a decorative print than traditional flowing cursive.

Verdict: Wan 2.7 is the clear winner as it followed every detail of the prompt, including the specific date and complex menu items. HiDream I1 Full failed to render the requested text, producing generic gibberish instead of the specific list provided in the prompt.

The Reversed Rodeo

Text-to-Image

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

HiDream I1 Full
Wan 2.7

AI Judge Analysis

HiDream I1 Full

  • + Dynamic, cinematic composition with a sense of motion
  • + Good integration of lighting between the astronaut and the environment
  • + Creative take on the 'surreal' aspect with the clouds and lighting.
  • Anatomical issues with the horse's front legs and hoof joints
  • The astronaut's legs are merged awkwardly with the horse's body

Wan 2.7

  • + Cleaner image resolution and finer textures on the astronaut suit
  • + Better anatomical consistency for the horse
  • + Impressive detail in the background galaxies and planetary bodies
  • Static and stiff composition compared to the dynamic energy of Model A
  • The lighting on the horse feels a bit flat compared to the bright Earth below

Verdict: Both models struggled with the specific instruction of 'horse on top, not vice versa,' with both defaulting to the common trope of an astronaut riding a horse. Wan 2.7 is preferred for its significantly higher image quality, better anatomical rendering of the horse, and intricate background details, whereas HiDream I1 Full suffers from noticeable anatomical glitches in the horse's legs.

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
Wan 2.7
0% wins 0% ties 100% wins

AI Judge Analysis

HiDream I1 Full

  • + Excellent photographic clarity and lighting
  • + Highly accurate texture on the capybara's fur
  • + Good depth of field emphasizing the driver while keeping the passenger visible
  • The passenger appears to be in the front seat next to the driver rather than the back

Wan 2.7

  • + Successfully places the passenger in the back seat as requested
  • + Detailed New York City architecture visible in the background
  • + Captures the bored expression of the passenger well
  • The capybara's fur looks slightly illustrative or artificial compared to the environment
  • The steering wheel position and paws have slight clipping/anatomical issues

Verdict: HiDream I1 Full produces a much higher quality, more photorealistic image with superior lighting and texture, although it fails to place the passenger in the back seat. Wan 2.7 follows the spatial positioning of the prompt better but is let down by lower-quality textures and a less realistic capybara. HiDream I1 Full is preferred for its professional aesthetic and believable rendering of the animal.

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
Wan 2.7

AI Judge Analysis

HiDream I1 Full

  • + Successfully includes the central glowing jack-o-lantern and bats as requested.
  • + Features a clean, high-contrast gothic font for the header.
  • Fails significantly on event details, with gibberish text like 'Yootmber' and incorrect times.
  • Missing the required 'Location' and specific date '30.10.2026'.
  • The 'Invitation' part of the title is missing, only showing 'Halloween Party'.

Wan 2.7

  • + Excellent text rendering, correctly including all event details: date, time, and location.
  • + High adherence to the prompt's decorative elements, including the thorny border and scroll banner.
  • + Superior composition with a more detailed background including the moody night sky, moon, and twisted trees.
  • The 'Halloween Party Invitation' text is slightly clipped at the top of the 'H'.
  • The aesthetic is closer to a modern illustration than a 'distressed' vintage parchment.

Verdict: Wan 2.7 is the clear winner as it successfully rendered all the specific text requirements, including the date, time, and location, which HiDream I1 Full failed to do, producing gibberish instead. Wan 2.7 also integrated the requested thorny border and scroll banner much more effectively into a cohesive vintage-style poster.

Bald man challenge

Image Editing
Edit instruction

“Give the person a full, thick head of natural hair with realistic texture, density, and a natural hairline. Preserve facial features and lighting.”

Before After
HiDream I1 Full
Before After
Wan 2.7

AI Judge Analysis

HiDream I1 Full

  • + Attempts to add hair length in the back.
  • Completely changes the subject's face, identity, and background.
  • Adds bizarre artifacts like a black object protruding from the beard.
  • Fails to provide a natural hairline on top, keeping the forehead bald.

Wan 2.7

  • + Excellent source preservation, keeping the face and background identical to the original.
  • + Successfully adds a full head of hair with realistic texture and a natural-looking hairline.
  • + Perfectly matches the lighting and color of the existing beard.
  • Very minor blending inconsistency where the new hair meets the sideburns.

Verdict: Wan 2.7 followed the instructions perfectly, providing a realistic head of hair while preserving the identity of the person and the environment. HiDream I1 Full failed significantly, generating a completely new person and background with numerous strange artifacts.

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
Wan 2.7

AI Judge Analysis

HiDream I1 Full

  • + Excellent 3D miniature 'PBR' material look with clean lighting.
  • + Clean and legible typography for the main text.
  • + Strong isometric perspective that fits the miniature theme perfectly.
  • Completely missed the request for a flag icon.
  • The rice grains appear a bit large and blob-like for a realistic miniature.

Wan 2.7

  • + Followed all text constraints, including the flag icon.
  • + High quality textures on the fish and shrimp with better grain definition.
  • + Higher compositional complexity with additional elements like soy sauce and chopsticks.
  • The text 'JAPAN' has slightly uneven character spacing and alignment.
  • The lighting is a bit flatter compared to the soft 3D rendering of the competitor.

Verdict: Wan 2.7 is the superior model for this prompt as it followed every instruction, including the small flag icon which HiDream I1 Full missed. While HiDream I1 Full produced a very attractive 3D render, Wan 2.7 delivered a more detailed and accurate scene with better sushi textures.

Over-the-top cartoon caricature

Editing
Edit instruction

“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.”

Source
HiDream I1 Full
Wan 2.7

AI Judge Analysis

HiDream I1 Full

  • + Maintains a high degree of facial similarity to the source person
  • + Successful caricature art style with exaggerated features
  • Fails to incorporate any noticeable hockey elements
  • Professional setting is very generic and lacks specific TV anchor cues

Wan 2.7

  • + Excellently incorporates all prompt elements including dogs, a TV studio setting, and specific hockey imagery like the puck and rink
  • + Uses more exaggerated and humorous expressions suitable for a caricature
  • + Good preservation of the selfie-style composition from the source
  • Text in speech bubbles contains typos ('Rolee')
  • The facial similarity to the source person is slightly lower than the competitor model

Verdict: Wan 2.7 is the clear winner as it successfully integrated every requirement of the prompt, including the hockey and TV anchor themes which HiDream I1 Full largely ignored. While HiDream I1 Full captured the subject's likeness better, Wan 2.7 created a much more creative and humorous caricature that actually told the requested story.

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
Wan 2.7

AI Judge Analysis

HiDream I1 Full

  • + Features very cute and emotive characters with big expressive eyes
  • + Excellent lighting with a soft, warm glow and prominent sunburst
  • Failed to include the baby bunny requested in the prompt
  • Includes two kittens instead of one
  • Looks more like a digital illustration than a hyper-photorealistic scene

Wan 2.7

  • + Successfully included all four specific animals: puppy, kitten, bunny, and fox
  • + Better captures the 'playfully chasing' and 'tumbling' movement
  • + Provides a more photorealistic texture for the fur and meadow
  • + Includes beautiful dew sparkles and god rays
  • The fox kit has a slightly awkward facial structure
  • The kitten's tongue/mouth rendering is a bit messy upon close inspection

Verdict: Wan 2.7 is the clear winner because it adhered to all elements of the prompt, successfully including the baby bunny which HiDream I1 Full missed. Furthermore, Wan 2.7 better captured the requested photorealism and the active 'chasing' vibe, whereas HiDream I1 Full felt more like a static, stylized portrait.

Studio Ghibli Anime Style

Editing
Edit instruction

“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”

Source
HiDream I1 Full
Wan 2.7

AI Judge Analysis

HiDream I1 Full

  • + Strong Studio Ghibli character design aesthetic with clean linework and expressive eyes.
  • + Successfully changed the environment to a Japanese-style street consistent with the theme.
  • + Matches the 'warm, nostalgic mood' and soft colors very well.
  • Fails to preserve the source image composition, turning the 'distracted boyfriend' meme into a generic group scene.
  • The man's beard and hat do not match the source subject.
  • The iconic expression of the jealous partner is completely lost.

Wan 2.7

  • + Excellent source preservation, maintaining the exact pose, clothing, and expressions of the original meme.
  • + Very effective application of 'hand-painted textures' using a watercolor style.
  • + Preserves the composition and identities of the source image perfectly while applying the filter.
  • The style lean more toward western watercolor book illustration than Studio Ghibli specifically.
  • Colors are slightly more muted than a typical vibrant Ghibli palette.

Verdict: HiDream I1 Full captures the 'Studio Ghibli' look much better in terms of character art, but it fails as an editing tool because it ignores the composition and narrative of the source image entirely. Wan 2.7 succeeds by perfectly preserving the source image's layout and expressions while applying a beautiful hand-painted texture that meets the aesthetic requirements of the prompt.

Golden Hour Stroll

Image Editing
Edit instruction

“Add dynamic motion to this photo: make hair blow in the wind, add leaves flying, energetic and lively feel.”

Before After
HiDream I1 Full
Before After
Wan 2.7

AI Judge Analysis

HiDream I1 Full

  • + Strong creative interpretation of 'energetic and lively' through a running pose.
  • + Significant quantity of flying leaves added to the scene.
  • + Effective wind effect on the hair.
  • Fails to preserve the source image identity, changing the subject's face and removing the dog entirely.
  • Drastically changes the environment and clothing (denim jacket vs. jeans).
  • Poor anatomy on the feet/shoes.

Wan 2.7

  • + Excellent source preservation, keeping the person, dog, and background almost perfectly intact.
  • + Successfully adds the blowing hair and flying leaves as requested.
  • + Maintains original image quality and lighting.
  • The 'energetic and lively' feel is more subtle compared to the dramatic change in model A.
  • Motion blur on the leaves is slightly inconsistent.

Verdict: Model HiDream I1 Full failed the image editing task by generating a new image that removed the dog and changed the woman's face, despite capturing the energy well. Wan 2.7 followed all instructions perfectly, adding the wind and leaf effects while maintaining the integrity of the original source image.

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
Wan 2.7

AI Judge Analysis

HiDream I1 Full

  • + Clean minimalist graphic design
  • + Perfect rendering of 'EST. 1720' text
  • + Effective simple vector style
  • Completely ignored the primary brand name 'Caffè Florian'
  • The steam effect is slightly asymmetrical

Wan 2.7

  • + Successfully included all requested text elements
  • + Beautiful vintage emblem composition with stars and leaf motifs
  • + Excellent paper-like texture and warm color palette
  • Slight spelling error in the name ('Florion' instead of 'Florian')
  • Cloche dome is transparent, which looks a bit unusual for a logo mark

Verdict: Wan 2.7 is the clear winner for following the full text instructions, including the brand name which HiDream I1 Full omitted entirely. While Wan 2.7 has a minor spelling error, its overall aesthetic, composition, and adherence to the 'vintage' and 'emblem' prompts are superior to the overly simplistic output of Model A.

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
Wan 2.7

AI Judge Analysis

HiDream I1 Full

  • + Captures the bold, flat-vector aesthetic well.
  • + Adheres strictly to the requested NASA-inspired color palette.
  • + Clear, large typography for the main title.
  • Failed to include all 6 requested steps, stopping after 3 or 4 confusingly ordered items.
  • Text labels include literal prompt instructions like '+ ICON'.
  • The layout is cluttered and unconventional for an infographic.

Wan 2.7

  • + Includes all 6 requested steps in a logical vertical progression.
  • + Excellent adherence to the 'infographic' style with clean iconography and supporting data.
  • + Consistent and professional layout with good use of negative space.
  • Minor spelling errors in labels such as 'Tranquiliry' and 'Descript'.
  • The star field is slightly cluttered compared to the requested clean flat style.

Verdict: Wan 2.7 is the clear winner as it successfully followed the complex instruction to create a 6-step infographic, whereas HiDream I1 Full only included four steps and included prompt text in the final image labels. Wan 2.7's layout is much more functional and aesthetically aligned with professional vector design standards.

Next steps

Explore each model