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
#51 of 62 in Text-to-Image
Wan 2.7
#39 of 62 in Text-to-Image
Where the votes landed
HiDream I1 Fast
0%
win rate
Ties
0%
Wan 2.7
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
- + Excellent clean lighting and reflections on the sphere
- + The glass cube has a very minimalist, modern aesthetic
- + Adheres to the 'sphere' descriptor with a perfectly smooth shape
- − The sphere appears to be floating unnaturally rather than resting on the surface
- − The plant in the background is very blurred, losing some level of detail
Wan 2.7
- + Highly realistic textures on the wooden table and the book spine
- + Excellent spatial logic with the sphere correctly resting on the bottom of the cube
- + Complex reflections and refractions through the glass facets
- − The 'cube' is a bit deep and rectangular rather than a perfect isometric cube
- − The sphere has a slightly rough, textured surface rather than a smooth finish
Verdict: Wan 2.7 provides a much more realistic and detailed scene with superior textures on the wood and book, whereas HiDream I1 Fast opts for a cleaner, more stylized look. Wan 2.7 is the winner due to its better handling of physics (the ball resting on the surface) and its impressive rendering of refraction and material detail.
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 shallow depth of field and bokeh
- + Subtle and cinematic rain reflections
- + Realistic skin texture and facial lighting
- − Anatomy and logic issues with the bike pedals and the man's seat position
- − Background cars are static rather than showing the requested motion blur
Wan 2.7
- + Perfectly captures the authentic 'street photo' aesthetic with natural lighting
- + Highly accurate bike details and clothing textures
- + Captures the environment with a realistic 50mm lens perspective
- − Does not show the requested motion blur from passing cars
- − Depth of field is slightly deeper than requested
Verdict: Wan 2.7 is the clear winner for its superior realism and adherence to the 'no stylization' instruction, creating an image that looks like a genuine photograph. While HiDream I1 Fast has a more dramatic cinematic look with better bokeh, it contains significant structural errors in the bicycle and a less natural posture for the subject.
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
- + Exceptional sharpness and clarity in the engraving of the armor
- + Vibrant and dramatic lighting with strong warm and cool contrast
- + Intricate hair braiding and clear bead details
- − The facial skin and scars look slightly airbrushed or hyper-realized
- − Armor looks somewhat pristine for a 'battle-worn' character
Wan 2.7
- + Extremely realistic skin texture with lifelike scars and weathering
- + The armor shows authentic-looking dents and scratches that fit the 'battle-worn' prompt
- + Very natural lighting and depth of field
- − Engravings on the armor are slightly less defined compared to the other model
- − Beads in the hair are less prominent and colorful than requested
Verdict: Wan 2.7 delivers a superior level of realism, particularly in the skin textures and the weathered state of the armor, which perfectly matches the 'battle-worn' description. HiDream I1 Fast produces a more stylized and high-contrast image with incredible detail in the metalwork, but it lacks the gritty, lifelike soul found in the Wan 2.7 output.
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
- + Includes a clean grid of high-quality food photography
- + Follows the bold sans-serif font requirement in the header
- − Text rendering is heavily corrupted and unreadable
- − Failed to create distinct sections for appetizers, pizza, and mains
- − Composition is unbalanced with most elements pushed to the right
Wan 2.7
- + Excellent layout that strictly adheres to the 'grid' and 'sections' prompt
- + Clean, legible font usage with a professional aesthetic
- + High visual quality with realistic food textures and smart branding elements like the QR code
- − Minor spelling errors in small body text
- − The prompt requested a white background (presented as a flat design), whereas this is a 3D mockup on a table
Verdict: Wan 2.7 is significantly superior in terms of professional layout, prompt adherence, and text legibility. While HiDream I1 Fast struggles with basic text rendering and overall balance, Wan 2.7 creates a functional, aesthetically pleasing menu with distinct sections for different food categories.
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
- + Excellent typography rendering for the primary title
- + High-quality photorealistic textures on the burger bun and patty
- + Good integration of elements on a realistic fiery base
- − Failed to provide an 'exploded' view; the burger is mostly assembled
- − Includes messy, garbled text within the golden circle
Wan 2.7
- + Perfectly captures the 'exploded' view with all components suspended
- + Dynamic composition with splashes of sauce and flying seeds
- + Includes all requested text with clear, legible rendering and fiery effects
- − The lighting on the burger components is slightly more artificial than Model A
- − The lettuce looks a bit less realistic compared to its counterpart
Verdict: Wan 2.7 is the clear winner as it followed the 'exploded burger' and layout instructions perfectly, whereas HiDream I1 Fast generated a mostly assembled burger. Wan 2.7 also accurately rendered all pieces of required text without the gibberish found in the HiDream output.
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
- + Successfully creates a photographic depth-of-field effect in the background.
- + Captures a believable hand-drawn texture for the chalk.
- − Numerous spelling errors including 'Risotto', 'Butter', and 'Herbs'.
- − Garbled text and overlapping numbers make the menu unreadable.
- − Includes artifacts and nonsensical scribbles on the middle section.
Wan 2.7
- + Excellent text legibility and perfect adherence to the specified menu items.
- + Consistent and aesthetically pleasing handwriting style across the entire board.
- + Successfully completes the truncated prompt text with 'Brown Butter Chocolate Chip Cookies'.
- − Text looks slightly more like a digital font than natural irregular handwriting.
- − Lacks the depth-of-field variety seen in Model A's composition.
Verdict: Wan 2.7 is the clear winner as it successfully rendered all the requested text with perfect spelling and logical layout, whereas HiDream I1 Fast suffered from significant legibility issues and spelling errors. Model B also correctly interpreted the truncated prompt to finish the last menu item logically.
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
- + Natural-looking lighting and textures on the astronaut and horse.
- + Good sense of motion and dust physics around the horse's hooves.
- − Completely failed the environment prompt, placing the subjects in a desert instead of space.
- − Failed the specific spatial instruction 'horse on top' by rendering a standard rider configuration.
Wan 2.7
- + Successfully rendered the environment as space with planets and galaxies.
- + Clean, high-resolution details on both the space suit and the horse.
- − Failed the specific spatial instruction 'horse on top', rendering a standard astronaut riding a horse.
- − The composition feels a bit more generic or 'stitched' compared to the lighting in image A.
Verdict: Both models failed the complex spatial reasoning task of placing the horse on top of the astronaut. However, Wan T2V is much closer to the prompt as it correctly situated the scene in space, whereas HiDream I1 Fast ignored the 'in space' requirement entirely and generated a 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 lighting and night atmosphere.
- + Cleverly compositioned to show the passenger clearly through the window.
- − The capybara has human hands instead of front paws.
- − The passanger is sitting in the front seat instead of the back seat as requested.
Wan 2.7
- + Successfully rendered the capybara's front paws on the steering wheel.
- + The passenger is correctly seated in the back seat per the prompt.
- − The capybara's fur has a slightly flat, artificial texture compared to the rest of the scene.
- − The perspective of the car interior is slightly warped near the steering wheel.
Verdict: Wan 2.7 is the clear winner because it correctly placed the passenger in the back seat and adhered to the detail of the capybara using its paws rather than human hands. While HiDream I1 Fast has superior lighting and aesthetic quality, its failure to generate animal anatomy and its incorrect seating arrangement make it less successful in prompt adherence.
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
- + Strong moody cinematic lighting with high contrast
- + Good central focal point with the glowing jack-o-lantern
- − Text is garbled and contains significant misspellings and duplications
- − Scroll banner text is cut off and illegible
- − The composition feels slightly cluttered despite the simple layout
Wan 2.7
- + Perfect text rendering for both the title and the fine details
- + Excellent adherence to all prompt elements including the thorns and scroll banner
- + Polished and professional layout suitable for a real invitation
- − Lighting is a bit flat compared to the requested 'cinematic' style
- − The illustration style leans more toward 2D comic/vector than a realistic poster
Verdict: Wan 2.7 is the clear winner due to its exceptional performance in text rendering and prompt adherence, accurately including every specific detail from the address to the banner text. While HiDream I1 Fast captures a more atmospheric and moody lighting style, its failure to produce legible or accurate text makes it unusable 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.”
AI Judge Analysis
HiDream I1 Fast
- + Excellent 3D miniature toy-like aesthetic with soft, plastic-like textures.
- + Very clean typography that follows the requested layout.
- + Accurate isometric perspective and faithful use of the solid light blue background.
- − The sushi design is a bit nonsensical, specifically the salmon piece having filling inside the rice.
- − The small icon next to the word SUSHI is distorted and unrecognizable.
Wan 2.7
- + High variety of well-rendered sushi types including Nigiri and Maki rolls.
- + Sophisticated material rendering with realistic sheen and texture on the fish.
- + Cleaner and more legible text arrangement.
- − Includes more garnish than requested in the 'minimal garnish' constraint.
- − The chopsticks are physically disconnected/broken visually.
Verdict: HiDream I1 Fast captures the 'cartoon miniature' aesthetic perfectly with its soft toy-like textures, while Wan 2.7 provides more realistic materials and a greater variety of items. Wan 2.7 is the likely winner as it offers higher artistic clarity and more coherent rendering of the food, despite its slightly more complex scene composition.
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
- + Beautiful soft bokeh and backlighting
- + Animals have very cute, expressive eyes
- − Missed the baby bunny entirely
- − Included two kittens instead of one
- − Animals are sitting still rather than 'tumbling and chasing'
Wan 2.7
- + Successfully included all four requested animals
- + Captures the 'playfully chasing' action much better
- + Excellent depiction of god rays and dew sparkles
- − The cat's front right leg is anatomically incorrect
- − A butterfly is awkwardly merged with a blade of grass
- − Composition is a bit cluttered
Verdict: Wan 2.7 followed the prompt much more accurately by including all four specific animals and capturing the action of chasing. HiDream I1 Fast failed the prompt instructions by omitting the bunny and doubling the kittens, though it produced a more polished, artifact-free image of the animals it did include.
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
- + Strong vector emblem aesthetic with clean lines
- + Creative use of steam for framing the composition
- + Accurate color palette and warm tones
- − Typos in the text including '17210' and overlapping characters in 'Florian'
- − The banner geometry is slightly warped
Wan 2.7
- + Highly legible and accurate text rendering for 'Est. 1720'
- + Excellent use of subtle paper texture on the background
- + Symmetrical and balanced composition
- − Misspelled the main name as 'Florion' instead of 'Florian'
- − The cloche handle is slightly off-center
Verdict: Both models struggled with spelling, but in different areas: HiDream I1 Fast failed the date and the layout of the main title, while Wan 2.7 nailed the date but failed the main name. Wan 2.7 is the stronger overall image due to its superior texture, symmetrical layout, and more professional-looking vector execution.
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
- + Strong heading typography for the main title.
- + Uses the requested NASA-inspired color palette effectively.
- − Poor text rendering for the smaller labels with multiple spelling errors.
- − Failed the sequential step-by-step logic of the requested infographic.
- − Cluttered composition with mismatched icons.
Wan 2.7
- + Excellent adherence to the requested 6-step infographic structure.
- + Highly legible and mostly accurate text rendering.
- + Authentic NASA-style vector aesthetic with a clean, professional layout.
- − Minor spelling errors such as 'Tranquiliry' and 'Descript'.
- − The star field is a bit busy, slightly distracting from the central path.
Verdict: Wan 2.7 significantly outperformed HiDream I1 Fast by accurately following the requested 6-step infographic structure and maintaining a professional vector aesthetic. While HiDream I1 Fast struggled with text legibility and logical flow, Wan 2.7 produced a coherent, educational poster with sophisticated layout and iconography.
Explore each model
Alibaba's Wan 2.7 image generation and editing model for text-to-image, reference-guided generation, and instruction-based image edits