HiDream AI's 17B parameter text-to-image model using sparse diffusion transformer with mixture of experts, achieving state-of-the-art image generation quality with strong prompt following
Settled by community votes across 7 shared challenges, with an AI judge weighing in on each.
HiDream I1 Full
13.7
arena score
#60 of 62 in Text-to-Image
Skill signature
· Text-to-Image
Qwen Image Max
21.3
arena score
#35 of 62 in Text-to-Image
Vote tally
Where the votes landed
HiDream I1 Full
0%
win rate
Ties
0%
Qwen Image Max
0%
win rate
Shared challenges
7
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
Qwen Image Max
AI Judge Analysis
HiDream I1 Full
- + Excellent depiction of window lighting and reflections on the wooden surface
- + Convincing glass material with realistic thickness and edge refraction
- + Accurately places the plant behind the cube as requested
- − The blue sphere appears small but physically disconnected/floating without a clear base
- − The top book lacks significant detail on its cover
Qwen Image Max
- + Stronger visual detail on the red book with some graphic elements
- + High clarity and sharp focus throughout the scene
- + Accurate adherence to all spatial requirements in the prompt
- − The glass is overly mirror-like, especially on the bottom face, which looks less realistic
- − The blue sphere feels unnaturally large for the 'small' descriptor in the prompt
Verdict: Both models followed the prompt instructions perfectly regarding object placement. HiDream I1 Full is the winner due to its superior handling of light and glass physics; the soft window light creates realistic dapples and reflections on the table, whereas Qwen Image Max has a slightly more artificial, CG-like quality to its glass surfaces.
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
Qwen Image Max
AI Judge Analysis
HiDream I1 Full
- + Excellent depiction of ornate engraved plate armor
- + Follows the request for braided hair with beads very clearly
- + Strong lighting effects with torchlight reflecting off the metal surfaces
- − The scars look a bit like surface-level paint rather than deep, aged tissue
- − Some symmetry issues in the armor's fine filigree
Qwen Image Max
- + Highly realistic skin textures and believable aged scars
- + Excellent rendering of leather straps and weathered cloth layers
- + More naturalistic bokeh sparks and background atmosphere
- − The armor engravings are slightly less sharp/distinct compared to Model A
- − The lighting on the face is a bit flat despite the torch background
Verdict: Qwen Image Max produces a much more believable and 'battle-worn' character with superior skin and textile textures. While HiDream I1 Full captures the ornate nature of the armor very well, it has a slightly more artificial, 'digital' look compared to the cinematic realism and grit found in Qwen Image Max.
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
Qwen Image Max
AI Judge Analysis
HiDream I1 Full
- + Excellent character placement and clear visibility of the passenger
- + Modern, high-quality cinematic lighting and sharpness
- + Accurate rendering of the capybara's professional facial expression
- − The capybara's paws look more like primate hands than capybara feet
- − Composition feels slightly cramped with the car frame clipping heavily
Qwen Image Max
- + Atmospheric interior lighting with realistic dashboard and street details
- + Better integration of the capybara's neck and body into the driver's seat
- + The yellow cap has realistic material texture
- − The passenger is partially cropped out and her context is less clear
- − Capybara's hands/paws are anthropomorphized with human-like fingers
- − Low-quality texture on the roof liner of the car
Verdict: HiDream I1 Full is the winner because it successfully captures both the primary subject (the capybara) and the secondary subject (the bored businesswoman) in a clear, cohesive composition. While Qwen Image Max has excellent lighting and background detail, the passenger—who was a specific requirement of the prompt—is poorly framed and less identifiable.
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
Qwen Image Max
AI Judge Analysis
HiDream I1 Full
- + Features a central glowing jack-o-lantern as requested.
- + The layout is clean and balanced for an invitation.
- − Text rendering is poor, with incorrect words like 'Yootmber' and missing event details.
- − The 'thorns' in the border are very simplistic and look like flat clip-art.
Qwen Image Max
- + Excellent text rendering, accurately capturing all the specific event details requested.
- + Sophisticated artistic style with cinematically lit trees, moon, and a detailed thorn border.
- + The scroll banner is well-designed and the font choice is elegantly gothic.
- − The parchment edges appear a bit integrated into the background rather than being a distinct separate layer.
Verdict: Qwen Image Max is the clear winner as it successfully rendered all the requested text, including the specific date, time, and location, which HiDream I1 Full failed to do significantly. Qwen Image Max also provided a much more atmospheric and polished aesthetic that better matched the 'vintage gothic' and 'cinematic' requirements.
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
Qwen Image Max
AI Judge Analysis
HiDream I1 Full
- + Excellent adherence to the wood diorama base style
- + Perfectly clean and bold typography
- + Uniform and aesthetically pleasing cartoon textures
- − Unintentional text shadow effect is a bit heavy
- − Circular plate on a square base creates a slightly busier composition
Qwen Image Max
- + Successfully included the requested flag icon
- + Higher detail in the food textures and materials
- + Interesting use of a glass-like diorama base
- − Missed the small flag icon requested in the prompt
- − Slightly less realistic PBR material on the rice compared to Model B
Verdict: Both models followed the prompt closely, but Qwen Image Max is the winner for including all requested elements, specifically the small flag icon which HiDream I1 Full missed. Qwen Image Max also exhibited more intricate material work on the sushi itself, while HiDream I1 Full excelled at the clean, geometric diorama aesthetic.
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
Qwen Image Max
AI Judge Analysis
HiDream I1 Full
- + Excellent fur texture and softness rendering
- + Vibrant colors with a strong golden hour feel
- + Very clean and cute facial features on all animals
- − Failed to include the requested baby bunny
- − Includes two kittens instead of one
- − The scene is a static pose rather than the requested 'playfully chasing' and 'tumbling' action
Qwen Image Max
- + Successfully captures the active 'tumbling' and 'chasing' movement requested in the prompt
- + Captures beautiful god rays and lighting atmosphere
- + Better diversity of butterflies and flora
- − Failed to include the requested baby bunny
- − Adds an extra puppy instead of a bunny
- − Anatomy on the fox kit's reaching paw is slightly distorted
Verdict: Both models failed to include the baby bunny, but Qwen Image Max is the superior choice as it actually followed the behavioral instructions of the prompt (tumbling and chasing). HiDream I1 Full produced a very high-quality static portrait, but it lacked the dynamic action and storytelling elements that Qwen Image Max successfully integrated with its more complex composition.
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
Qwen Image Max
AI Judge Analysis
HiDream I1 Full
- + Clean vector illustration style
- + Correct typography for the date banner
- + Effective use of negative space within the cloche
- − Completely missed the primary text 'Caffè Florian'
- − The cloche handle is detached and floating
- − Background is flat with no 'subtle texture'
Qwen Image Max
- + Perfect text adherence including 'Caffè Florian' and 'Est. 1720'
- + Beautiful vintage texture on the paper background
- + Excellent shading and line work on the cloche dome
- − The steam looks a bit like hair or a wig sprout
- − Slightly less 'minimalist' than Model A
Verdict: Qwen Image Max is the clear winner as it followed every part of the prompt, including the specific name of the restaurant, which HiDream I1 Full omitted entirely. Qwen Image Max also provided the requested 'subtle texture' on the background, creating a much more convincing vintage aesthetic.
Next steps
Explore each model
The Max series of Tongyi Qwen’s image generation model excels across a wide range of generation tasks. Compared with the Plus series, it significantly reduces the “AI-like” feel in generated images, enhancing their realism. It delivers more lifelike material textures for human subjects, finer and more detailed natural textures, and more visually appealing text rendering.