Unified multimodal model for text-to-image generation, instruction-guided image editing, personalized generation, and virtual try-on
Settled by community votes across 9 shared challenges, with an AI judge weighing in on each.
OmniGen v2
#57 of 62 in Text-to-Image
Qwen Image 2.0 Pro
#32 of 62 in Text-to-Image
Where the votes landed
OmniGen v2
0%
win rate
Ties
0%
Qwen Image 2.0 Pro
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
OmniGen v2
- + Excellent photographic realism and lighting
- + Correctly places the sphere on the floor of the cube
- + Clear glass refraction and plant visibility through the object
- − The glass box appears to be open at the top rather than a solid cube
Qwen Image 2.0 Pro
- + Successfully renders the plant behind the cube visible through the glass
- + Good texture on the red book and wooden table
- − The blue sphere is floating physically impossible in the center of the air
- − Strange perspective shifts on the glass edges
- − The internal reflections are messy and confusing
Verdict: OmniGen v2 produced a much more realistic image with convincing lighting and material physics. Qwen Image 2.0 Pro struggled with basic physics, causing the blue sphere to float inside the cube, and the overall composition felt less cohesive than OmniGen v2.
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
OmniGen v2
- + Text rendering is clean and very legible.
- + High contrast and vibrant colors create a striking ad visual.
- + Follows the request for a starburst price tag accurately.
- − Fails the 'exploded burger' requirement, showing a mostly assembled patty stack.
- − Lacks the sense of motion and mid-air suspension requested.
- − Missing the currency symbol on the price tag.
Qwen Image 2.0 Pro
- + Successfully captures the 'exploded burger' layout with suspended components.
- + High level of photorealistic detail in the textures of the meat and bun.
- + Perfectly integrates all requested text with the fiery, glowing effect.
- − The price tag text overlaps the bun slightly.
- − The 'starburst' shape is a bit generic and flat compared to the rest of the 3D scene.
Verdict: Qwen Image 2.0 Pro is the clear winner as it followed every instruction, specifically the difficult 'exploded burger' requirement and the inclusion of the currency symbol. While OmniGen v2 produced a high-quality graphic, it failed the core compositional prompt to have components suspended in mid-air.
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
OmniGen v2
- + Captures the realistic texture of chalk effectively.
- + Follows the layout instructions for a chalkboard frame.
- − Numerous spelling errors including 'Specals', 'Lemont', and 'Musonhom'.
- − Text layout is cluttered and contains repetitive, nonsensical lines of pricing.
- − Fails the cursive requirement for the title.
Qwen Image 2.0 Pro
- + Near-perfect spelling and adherence to the complex menu item list.
- + Authentic chalkboard aesthetic with realistic smudges and chalk dust.
- + Excellent composition that includes a 'cozy café' background as requested.
- − The title is in a clean print/script rather than an 'elegant cursive' style.
- − Slight distortion in the perspective of the board's top edge.
Verdict: Qwen Image 2.0 Pro is the clear winner as it successfully rendered almost all the text accurately and placed it within a believable cafe environment. OmniGen v2 struggled significantly with text legibility and spelling, resulting in a disorganized and incoherent menu.
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
OmniGen v2
- + Clean, high-resolution visual quality
- + The capybara's head blends well with the collar of the jacket
- − The capybara has human hands holding the steering wheel
- − The passenger is sitting in the front passenger seat instead of the back seat
- − The proportions of the car interior are unrealistic
Qwen Image 2.0 Pro
- + Successfully places the passenger in the back seat as requested
- + Rendered capybara paws on the steering wheel instead of human hands
- + High level of detail in the taxi interior and New York street background
- − Slight spelling error on the 'TLC Licensed' sticker
- − The cap is floating slightly above the capybara's head
Verdict: Qwen Image 2.0 Pro is the clear winner for its superior prompt adherence, correctly placing the businesswoman in the back seat and providing the capybara with animal paws rather than the uncanny human hands seen in OmniGen v2. Qwen also captured the 'photorealistic' and 'New York' aesthetic much more effectively through detailed background elements and lighting.
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
OmniGen v2
- + Strong contrast and vibrant 'vintage postcard' color palette
- + Good layout with large legible header text
- + Includes the gothic parchment texture border
- − Several typos in the secondary text (e.g., 'FRIETS', 'ARCAS')
- − Jack-o-lantern is a flat silhouette rather than a rendered object
- − The central scroll banner contains gibberish text
Qwen Image 2.0 Pro
- + Perfect text rendering for all requested details including date and location
- + Highly detailed cinematic lighting and 3D rendering of the pumpkin
- + Accurately follows all prompt elements including the thorn border and scroll banner
- − The green glow might be seen as 'toxic' rather than traditional spooky orange
- − Composition is a bit crowded around the bat wings
Verdict: Qwen Image 2.0 Pro is the clear winner as it followed every instruction perfectly, specifically the text rendering which is virtually flawless across the title, banner, and event details. OmniGen v2 struggled with the specific text requirements, resulting in multiple misspellings and illegible script on the banner.
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
OmniGen v2
- + Excellent 3D depth and pop-out shadows
- + Vibrant, high-contrast colors
- + Dynamic 45° isometric perspective
- − The 'flag' icon is incorrect
- − The sushi anatomy is slightly nonsensical with shrimp tails attached to rolls
Qwen Image 2.0 Pro
- + Perfectly renders the Japanese flag as requested
- + Clean, accurate text layout with high legibility
- + More realistic sushi variety and presentation
- − Slightly washed out, lower contrast compared to Model A
- − Text is flat 2D which clashes slightly with the 3D diorama
Verdict: Qwen Image 2.0 Pro is the winner for its better adherence to specific details, such as the Japanese flag and more sensible sushi arrangements. While OmniGen v2 has more visually striking 3D rendering and vibrant colors, it failed significantly on the flag representation and produced odd hybrid sushi.
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
OmniGen v2
- + Bright, cheerful colors and strong lighting
- + Clean, symmetrical composition
- + Expressive character designs
- − Missed the baby bunny in the group
- − Style is more like a 3D animation or illustration than a photorealistic scene
- − Butterflies appear flat and pasted onto the image
Qwen Image 2.0 Pro
- + Exceptional photographic realism with natural textures
- + Includes all four requested animals correctly
- + Successful execution of god rays and morning dew
- − The fox kit has a slightly elongated tail that looks a bit stiff
- − The cat's anatomy is slightly merged with the animals below it
Verdict: Qwen Image 2.0 Pro followed the prompt perfectly, including the puppy, kitten, bunny, and fox in a highly realistic photographic style that captures the requested 'god rays'. OmniGen v2 failed to include the bunny and produced an illustrative, cartoon-like image that ignored the 'hyper-photorealistic' instruction.
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
OmniGen v2
- + Strong vector emblem style with clean lines
- + Accurate color palette of warm brown and cream
- + Correct date information formatted clearly
- − Significant spelling error in the main text ('CAFFFLORIN')
- − Minimalist design feels a bit generic compared to the vintage request
Qwen Image 2.0 Pro
- + Better rendering of the steam element
- + More elegant typography that matches the vintage theme well
- + Good use of subtle texture on the dome and background
- − Spelling error in the main name ('Floriian')
- − Steam is placed outside the dome rather than rising from the food it would cover
Verdict: Both models failed to spell the brand name correctly, but Qwen Image 2.0 Pro produced a much more sophisticated 'vintage' aesthetic with better texture and layout. OmniGen v2 achieved a cleaner vector look but the severe typo and overly simplistic steam graphic make it less appealing as a restaurant logo.
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
OmniGen v2
- + Successfully uses the requested color palette.
- + Follows a clean flat-vector layout style.
- − Incorrect mission number (Apollo 17 vs requested Apollo 11).
- − Nonsensical gibberish text throughout the infographic.
- − Icons do not accurately represent the specific objects requested (e.g., no Saturn V).
Qwen Image 2.0 Pro
- + Excellent adherence to the sequential 6-step prompt.
- + Near-perfect text rendering and name accuracy.
- + High-quality vector icons that match the specific descriptions like Saturn V and Lunar Module.
- − Introduces a more complex gradient/shading style than the 'subtle' request.
- − The 'Translunar' trajectory arc is a bit wavy rather than a direct mathematical curve.
Verdict: Qwen Image 2.0 Pro followed every specific detail of the prompt, including the complex 6-step sequence, accurate names of the astronauts, and specific icon types. OmniGen v2 failed significantly on text legibility, mission accuracy, and icon relevance. Qwen's output is a functional and visually appealing infographic, while OmniGen's is a series of abstract shapes with garbled text.
Explore each model
Alibaba's Qwen Image 2.0 Pro model offering higher quality image generation with enhanced detail and accuracy