Distilled version of HiDream AI's 17B parameter text-to-image model
Settled by community votes across 8 shared challenges, with an AI judge weighing in on each.
HiDream I1 Fast
17.9
arena score
#51 of 62 in Text-to-Image
Skill signature
· Text-to-Image
Qwen Image Max
21.5
arena score
#35 of 62 in Text-to-Image
Vote tally
Where the votes landed
HiDream I1 Fast
0%
win rate
Ties
0%
Qwen Image Max
0%
win rate
Shared challenges
8
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
Qwen Image Max
AI Judge Analysis
HiDream I1 Fast
- + Excellent handling of glass transparency and reflections.
- + Accurate lighting direction from the left.
- + Clean, minimalist composition that looks highly realistic.
- − The sphere is quite large relative to the cube, barely fitting based on its diameter.
Qwen Image Max
- + Realistic texture on the wooden table and book cover.
- + Successfully captures the plant behind the cube visible through the glass.
- + Accurate placement of all requested elements.
- − The glass refractive logic is slightly distorted on the left side.
- − The sphere appears to be floating mid-air inside the cube without support.
Verdict: Both models followed the complex spatial prompt perfectly. HiDream I1 Fast produces a cleaner, more aesthetically pleasing image with superior lighting, while Qwen Image Max offers slightly better texture detail on the book and table. HiDream I1 Fast is the winner due to its better handling of transparent glass physics and lighting.
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
Qwen Image Max
AI Judge Analysis
HiDream I1 Fast
- + Excellent engraving details on the plate armor
- + Impressive rendering of lifelike eyes and facial hair
- + Perfect adherence to the 'hair braided with small beads' requirement
- − The scar appears more like face paint or a fresh superficial scratch than a battle-worn mark
- − Overall skin texture is a bit too clean and smooth for a battle-worn character
Qwen Image Max
- + Captures a much more convincing 'battle-worn' aesthetic with realistic scars and dirt
- + Superior texture on leather straps and worn cloth underlayer
- + Dynamic bokeh sparks and lighting integration
- − The braids are very thin and could be interpreted as dreadlocks rather than the requested braids
- − The engraving on the armor is slightly less crisp than Model A
Verdict: Qwen Image Max is the winner as it perfectly captures the 'battle-worn' atmosphere with authentic scars, dirt, and weathered textures. While HiDream I1 Fast produces a very clean and attractive image with great armor detail, it feels more like a model in costume than a veteran paladin.
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
Qwen Image Max
AI Judge Analysis
HiDream I1 Fast
- + Clean font rendering for the main title
- + High clarity and photorealism in the burger ingredients
- − Failed the 'exploded' motion requirement, showing a static burger
- − Garbled text in the secondary circular graphic ('LIMITED TINIK')
- − The €6.99 starburst lacks the requested fiery glowing effect
Qwen Image Max
- + Excellent adherence to 'fiery, glowing effect' on text
- + Strong sense of motion and dynamic composition
- + Accurate rendering of all requested text elements
- − The burger is tilted but not truly 'exploded' with all components suspended separately
- − Slightly less realistic texture on the cheese compared to the other model
Verdict: Qwen Image Max is the clear winner as it followed all prompt instructions, including the complex text styling and the fiery atmosphere. HiDream I1 Fast produced a static-looking image with misspelled text and failed to capture the 'exploded' or 'dynamic' nature of the request.
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
Qwen Image Max
AI Judge Analysis
HiDream I1 Fast
- + Crisp, high-contrast night lighting for the background city lights.
- + Clearly legible 'TAXI' text on the cap.
- + Woman's expression is very calm and fits the 'normal' requirement.
- − Anatomical failure: the capybara has human hands holding the steering wheel.
- − The woman is sitting in the front passenger seat instead of the back seat as requested.
Qwen Image Max
- + Correct composition, with the businesswoman seated in the back seat as requested.
- + The capybara has furry paws consistent with its species rather than human hands.
- + The worn taxi interior adds a layer of grimey realism typical of NYC cabs.
- − The woman in the back is slightly out of focus and less detailed.
- − The steering wheel placement looks a bit awkward relative to the driver's body.
Verdict: Qwen Image Max successfully followed the complex spatial instructions, placing the woman in the back seat and providing the capybara with animal-appropriate paws. HiDream I1 Fast produced a sharper image with better lighting but failed significantly on anatomy by giving the capybara human hands and placing the passenger in the front seat.
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
Qwen Image Max
AI Judge Analysis
HiDream I1 Fast
- + Includes all elements of the prompt structurally
- + Bold, readable main header font
- − Significant text rendering errors in the banner and bottom details
- − Visual quality is lower with flat, cartoonish lighting compared to the requested cinematic look
- − Unnecessary repetition of the location name
Qwen Image Max
- + Exceptional text rendering with no spelling errors
- + Beautiful cinematic lighting and detailed textures on the pumpkin and trees
- + Framing accurately follows the instruction for a thorn and web border
- − The transition between the parchment edge and the background is slightly softer than a traditional 'poster on background' look
Verdict: Qwen Image Max is the clear winner as it successfully rendered all the text perfectly, including the specific date and location. While HiDream I1 Fast followed the layout instructions, it failed significantly on text legibility and artistic quality, whereas Qwen Image Max delivered a polished, professional-looking invitation that nailed the gothic aesthetic.
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
Qwen Image Max
AI Judge Analysis
HiDream I1 Fast
- + Excellent adherence to the 'cartoon scene' style with clean, soft textures.
- + Text is perfectly legible and formatted as requested.
- + Strong composition with a clear 45° isometric perspective.
- − The salmon nigiri sushi piece has an illogical interior filling visible on the side.
- − There is some minor graphical noise/artifacts around the word 'SUSHI'.
Qwen Image Max
- + High-quality PBR materials, especially on the salmon and glass base.
- + More diverse and realistic-looking sushi varieties.
- + Excellent text rendering and clean graphic design.
- − The perspective is slightly more tilted than a true 45° isometric view.
- − Missing the chopsticks visible in the other model.
Verdict: Both models followed the prompt exceptionally well, but Qwen Image Max is the winner due to its superior material rendering (PBR) and much higher quality food details. While HiDream I1 Fast nailed the 'cartoon' request, it included logical errors in the sushi construction that Qwen Image Max avoided while maintaining superior clarity and professional aesthetics.
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
Qwen Image Max
AI Judge Analysis
HiDream I1 Fast
- + Excellent softness and rim lighting on the fur
- + Expressive and endearing facial features
- + Clean, high-quality rendering with a professional bokeh effect
- − Missed the baby bunny entirely
- − Animals are sitting still rather than 'playfully chasing and tumbling' as requested
Qwen Image Max
- + Captures the movement and 'tumbling' action from the prompt
- + Beautiful 'god rays' and atmosphere with detailed wildflowers
- + Better diversity of butterflies and interaction with the environment
- − Missed the baby bunny, instead generating two golden retrievers
- − The fox's anatomy is slightly stiff compared to the other animals
- − Some minor blending issues where the animals touch
Verdict: Qwen Image Max is the winner for better capturing the energy of the prompt, showing the animals actually tumbling and interacting in a lush meadow with the requested god rays. While both models failed to include the baby bunny, HiDream I1 Fast produced a static, posed portrait rather than the active scene described.
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
Qwen Image Max
AI Judge Analysis
HiDream I1 Fast
- + Successfully includes most prompt elements
- + Good use of the warm brown and cream color palette
- − Typos in the text including '17210' instead of '1720' and a floating 'O' at the end
- − Clunky integration of typography inside the cloche image
- − Messy, incoherent steam lines
Qwen Image Max
- + Perfect text rendering for both name and date
- + High-quality vector illustration style with clean cross-hatching
- + Excellent vintage paper texture that perfectly matches the 'subtle texture' request
- − The paper texture is more heavy than 'subtle'
Verdict: Qwen Image Max is the clear winner as it followed all instructions perfectly, including accurate spelling of the name and the specific date. HiDream I1 Fast struggled with the text, producing a significant typo in the year ('17210') and awkward font placement, whereas Qwen Image Max produced a professional-grade vector emblem.
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.