Bria's 8B parameter model for controlled text-to-image generation with structured JSON prompts, trained exclusively on licensed data
Settled by community votes across 17 shared challenges, with an AI judge weighing in on each.
Bria FIBO
#56 of 62 in Text-to-Image
Wan 2.7 Pro
#38 of 62 in Text-to-Image
Where the votes landed
Bria FIBO
0%
win rate
Ties
0%
Wan 2.7 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
Bria FIBO
- + Excellent refraction and lighting effects within the glass
- + Very clean, modern aesthetic with high resolution
- + Captures the levitating effect of the sphere well
- − The plant appears to be growing inside/through the glass rather than strictly behind it
- − The blue sphere looks slightly flat and computer-generated compared to other elements
Wan 2.7 Pro
- + Highly realistic textures on the wooden table and red book
- + Naturalistic composition that feels like a real photograph
- + Accurate depiction of a fern-like plant visible through the glass
- − The glass cube has internal dividers or edges that make it look more like a glass case than a solid or hollow cube
- − The lighting inside the cube is a bit dark
Verdict: Both models followed the prompt instructions accurately, but Wan 2.7 Pro produced a much more convincing, photorealistic scene with beautiful textures on the table and book. Bria FIBO created a very clean, high-quality image, but it suffered from some spatial clipping where the plant leaf seems to exist inside the glass cube's volume.
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
Bria FIBO
- + Atmospheric cinematic lighting with vibrant red and blue contrast
- + Good skin texture on the man's face
- + Beautiful wet pavement reflections that enhance the mood
- − Anatomical errors in the hands, particularly the left hand appearing mangled
- − The bicycle structure is nonsensical, especially the connection between the fork and handlebars
- − Lack of clear motion blur from the passing car as requested
Wan 2.7 Pro
- + Highly realistic and grounded street photography aesthetic that feels like a real snapshot
- + Much more accurate bicycle anatomy and physical interaction
- + Excellent handling of reflections and the 'wet look' on the pavement
- − Failed to include motion blur on the background vehicles as requested
- − The framing is quite central despite the request for 'imperfect framing'
- − The lighting is a bit flat compared to the 'cinematic' prompt requirement
Verdict: Wan 2.7 Pro is the superior image because it manages to create a coherent, realistic scene with a correctly rendered person and bicycle, whereas Bria FIBO has significant anatomical errors in the hands and bicycle frame. While Bria FIBO captures the 'cinematic' and bokeh aesthetic better, Wan 2.7 Pro feels like a genuine candid photograph of a Japanese street, aligning better with the overall realism prompt.
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
Bria FIBO
- + Excellent intricate engraving on the armor
- + Very sharp and clear facial details
- + Accurately represents the braided hair and beads requested
- − The scars look more like surface dirt or mud than actual healed tissue
- − Lighting feels slightly flatter on the skin
Wan 2.7 Pro
- + Better 'battle-worn' feel with realistic scars and rough skin texture
- + Realistic warm torchlight lighting and bokeh sparks
- + High-detail texture on the leather straps and buckles
- − The hair beads look a bit more modern/plastic than historical fantasy
- − The face has a slightly more generic digital feel compared to Model A
Verdict: Both models followed the prompt exceptionally well. Bria FIBO captures a more 'refined' paladin with superior armor engravings and facial clarity, while Wan 2.7 Pro excels at the atmospheric requests, delivering a more gritty, battle-worn appearance with superior lighting and leather textures. Wan 2.7 Pro is the slight winner for capturing the requested 'battle-worn' and 'warm torchlight' mood more effectively.
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
Bria FIBO
- + Excellent typography style with bold, professional headers
- + Strong adherence to the requested neon/vibrant accents
- + Clean white background with logical content segments
- − The layout is fragmented into panels like a web UI rather than a single menu page
- − Text becomes complete gibberish at the item level
- − Food photos are somewhat abstract and poorly cropped
Wan 2.7 Pro
- + Perfect grid layout for food photography
- + Highly legible text with actual menu item names and pricing
- + Creates a realistic professional brand identity including logo and social media
- − The fonts are a mix of sans-serif and serif, whereas 'bold sans-serif' was requested
- − The food photography is slightly generic compared to more creative styles
Verdict: Wan 2.7 Pro is the clear winner as it produces a functional, realistic menu design that follows the grid layout and section requirements perfectly. While Bria FIBO has interesting graphic design elements, it fails to generate legible text and the layout feels like a collage rather than a professional menu.
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
Bria FIBO
- + Excellent photorealistic texture on the meat and bun
- + Very dynamic and atmospheric lighting integration with the fire
- + Highly legible glowing text for the main title
- − Missed the currency symbol (Euro) and the starburst element
- − The secondary text lacks the requested fiery/glowing effect
- − Composition feels a bit tight with the top bun partially cut off
Wan 2.7 Pro
- + Perfect adherence to all layout instructions including the starburst for pricing
- + Strong sense of an 'exploded' view with many disparate ingredients
- + Excellent text rendering for all requested strings
- − Food textures look slightly more illustrative compared to the realism of Model A
- − The 'fire' on top of the text looks like a repeated clip-art pattern
Verdict: Model B (Wan 2.7 Pro) is the winner because it followed every specific instruction, including the starburst element and the Euro currency symbol. While Model A (Bria FIBO) had superior photorealism in the food textures, it failed several key layout and text prompts.
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
Bria FIBO
- + Natural chalk texture on the board surface
- + Accurate cursive handwriting style for the title
- − Failed to render the required menu items, resulting in gibberish text
- − Incorrect date rendered as April 3 instead of April 30
Wan 2.7 Pro
- + Perfect text rendering of all requested menu items and prices
- + High-quality composition with realistic cafe background elements
- + Strict adherence to the specific date requested
- − Handwriting style is slightly too uniform, leaning toward a digital font aesthetic
Verdict: Wan 2.7 Pro is the clear winner as it successfully rendered every word and price from the prompt with zero spelling errors. Bria FIBO failed significantly on prompt adherence, producing illegible text for the menu items and failing to include the specific date.
The Reversed Rodeo
Text-to-Image“Horse riding astronaut in space — horse on top, not vice versa. Surreal, highly detailed, cinematic.”
AI Judge Analysis
Bria FIBO
- + Excellent use of glowing neon elements that enhance the surreal theme
- + Dynamic posing and vibrant cinematic lighting
- + Creative interpretation of a space-horse with glowing hooves
- − The astronaut has three legs or a leg fused with the horse's back
- − Failed the negative constraint; the astronaut is on top, not the horse
Wan 2.7 Pro
- + Realistic anatomical rendering of the horse and astronaut gear
- + Clean, high-resolution textures
- + Includes various celestial bodies like planets and a clear view of Earth
- − Failed the specific negative constraint to have the horse on top of the astronaut
- − Composition feels a bit static compared to the surreal prompt
Verdict: Both Bria FIBO and Wan 2.7 Pro failed to follow the logical reversal requested in the prompt ('horse on top, not vice versa'), instead providing the standard astronaut-on-horse image. Bria FIBO captured the surreal and cinematic atmosphere much better, while Wan 2.7 Pro leaned towards a more literal and realistic space aesthetic.
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
Bria FIBO
- + Excellent adherence to the 'bored' expression for the passenger
- + Strong composition with a clear separation between front and back seats
- + Higher level of photorealism in the skin and fur textures
- − Internal car structure is somewhat nonsensical near the roof/door frame
- − Capybara hands are slightly distorted
Wan 2.7 Pro
- + Natural street background through the windows
- + Correct cap and jacket placement on the capybara
- + Good sense of motion and city atmosphere
- − Passenger appears to be sitting in the front passenger seat rather than the back seat
- − Capybara hands look like human/primate hands, which is unsettling
- − Passenger's expression is slightly more engaged than 'bored'
Verdict: Bria FIBO followed the spatial instructions much better, correctly placing the passenger in the back seat to create the intended narrative of a professional ride. Wan 2.7 Pro placed the passenger in the front seat and struggled with the anatomy of the capybara's paws, resulting in distracting human-like fingers.
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
Bria FIBO
- + Features a high-quality, cinematic jack-o-lantern with realistic lighting
- + Incorporates the requested spiderweb and thorn border effectively
- + The banner text is clear and readable
- − Failed significantly on the event details text at the bottom, creating garbled gibberish
- − The scroll banner text changed 'frights' to 'nights'
Wan 2.7 Pro
- + Excellent text rendering, correctly following all specific date, time, and location details
- + Highly detailed illustrative style with additional gothic elements like lanterns and a cauldron
- + Perfectly follows the parchment and border instructions with a clean layout
- − The style is more illustrative/drawn than the 'cinematic' lighting requested
- − The jack-o-lantern is less central and slightly smaller compared to the overall frame
Verdict: Wan 2.7 Pro is the clear winner due to its superior adherence to the text requirements, accurately rendering every piece of information requested without errors. Bria FIBO produced a more atmospherically 'cinematic' image, but the bottom half of the invitation is composed of illegible text and incorrect details, making it non-functional as a graphic design piece.
Bald man challenge
Image Editing“Give the person a full, thick head of natural hair with realistic texture, density, and a natural hairline. Preserve facial features and lighting.”
AI Judge Analysis
Bria FIBO
- + Successfully added a very thick head of hair with stylized volume.
- + Maintained the general color palette and theme of the original image.
- − Completely failed to preserve the subject's facial features, essentially generating a new person.
- − Changed the clothing and the background environment significantly.
- − The hair texture looks somewhat airbrushed and less realistic compared to the beard.
Wan 2.7 Pro
- + Excellent source preservation, keeping the face, beard, clothing, and background identical to the original.
- + The added hair has a very realistic, natural texture that matches the existing beard.
- + Maintained the exact lighting and grain of the source photo.
- − The hairline transition on the forehead is slightly abrupt, though still believable.
Verdict: Bria FIBO failed the basic requirements of an image editing task by completely changing the person's face and the background, despite following the hair instruction. Wan 2.7 Pro performed a near-perfect edit, seamlessly adding realistic hair while preserving every other detail of the original image.
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
Bria FIBO
- + Excellent 45° isometric perspective with a clear diorama base
- + High-quality 3D PBR-style textures and material rendering
- + Clean and accurate text rendering for 'JAPAN' and 'SUSHI'
- − Includes stray watermark-like text/icons in the bottom corners
- − The wasabi and garnish placement feels slightly scattered
Wan 2.7 Pro
- + Beautiful, consistent 'cartoon' 3D aesthetic with soft lighting
- + Superior graphic design layout for the top-center text and flag
- + Very clean composition without accidental watermark artifacts
- − The camera angle is slightly lower than the requested 45° isometric view
- − The plate/base design is more rounded and less 'diorama-like' compared to the prompt
Verdict: Wan 2.7 Pro is the winner as it produces a cleaner, more professional-looking graphic without the distracting UI/watermark artifacts present in Bria FIBO. While Bria FIBO followed the 'diorama base' and perspective instructions more strictly, Wan 2.7 Pro delivered better artistic cohesion and more elegant typography.
Over-the-top cartoon caricature
Editing“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.”
AI Judge Analysis
Bria FIBO
- + Expertly captures the news anchor setting with complex studio lighting and equipment.
- + Highly detailed and humorous caricature style with exaggerated features.
- + Includes a large, expressive dog integrated into the composition.
- − Fails to include any clear visual reference to hockey.
- − The background is extremely cluttered with visual artifacts and messy details.
Wan 2.7 Pro
- + Successfully incorporates the hockey element with a microphone hockey stick and team jerseys on the dogs.
- + Maintains a cleaner, more legible comic-book caricature style.
- + Explicitly addresses all three requested themes: anchor, dogs, and hockey.
- − The text bubbles are a bit generic and simple.
- − The background is less detailed compared to Model A.
Verdict: Wan 2.7 Pro is the winner because it successfully incorporated all three specific hobbies and professions requested (TV anchor, dogs, and hockey), whereas Bria FIBO completely missed the hockey requirement. While Bria FIBO had a more detailed background, Wan 2.7 Pro's creative solution of a hockey-stick microphone and dogs in jerseys made for a more accurate response to the prompt.
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
Bria FIBO
- + Successfully includes all four requested animal types.
- + Vibrant and saturated color palette enhance the joyful vibe.
- + Captures clear butterfly details and expressive eyes.
- − The fox kit's anatomy is slightly awkward with floating hind legs.
- − The lighting feels a bit more illustrative and less 'hyper-photorealistic' than the other model.
Wan 2.7 Pro
- + Exceptional realism in fur texture and lighting.
- + Beautiful, natural integration of god rays and dew sparkles.
- + High degree of physical interaction between the animals creating a cohesive scene.
- − The fox has black 'paws' that look a bit like gloves or orbs rather than natural paws.
- − The kitten's facial expression is slightly distorted.
Verdict: Both models followed the complex prompt extremely well, including all four specific animals and the environmental requests. Wan 2.7 Pro produces a significantly more photorealistic image with superior lighting and depth, whereas Bria FIBO has a more stylized, digital-art feel. Wan 2.7 Pro is the winner for its more convincing 8K textures and natural atmosphere.
Studio Ghibli Anime Style
Editing“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”
AI Judge Analysis
Bria FIBO
- + Captures the soft, dreamy Ghibli background aesthetic and lighting perfectly.
- + Effectively mimics the anime character design style often seen in modern Ghibli or Makoto Shinkai films.
- + Good application of the specified pastel color palette.
- − Fails to preserve the specific poses and spatial relationship of the source image, turning it into three people walking together.
- − Lost the humorous 'distracted boyfriend' narrative entirely.
Wan 2.7 Pro
- + Excellent source preservation, maintaining every detail of the original meme's composition and poses.
- + Beautiful watercolor texture that feels hand-painted and nostalgic.
- + Successful transformation of the faces into an illustrative style while keeping them recognizable.
- − The style leans more toward classic storybook watercolor than specifically 'Studio Ghibli' anime styling.
Verdict: Wan 2.7 Pro is the clear winner because it successfully applied the requested artistic style while perfectly preserving the composition and narrative of the original image. Bria FIBO created a pretty illustration that matched the 'Ghibli' prompt well, but it failed as an image edit by completely reconfiguring the characters' positions and losing the identity of the source meme.
Golden Hour Stroll
Image Editing“Add dynamic motion to this photo: make hair blow in the wind, add leaves flying, energetic and lively feel.”
AI Judge Analysis
Bria FIBO
- + Successfully captures a highly energetic and lively feel as requested.
- + Executes dramatic hair movement and dynamic poses for both the human and dog.
- + Adds a significant amount of autumn leaves that enhance the sense of motion.
- − Poor source preservation; drastically changes the lighting, scenery, and facial features of the woman and dog.
- − Lowers the overall image resolution and clarity compared to the original.
Wan 2.7 Pro
- + Excellent source preservation, maintaining the original woman, dog, and background with high fidelity.
- + Subtle but natural hair movement that flows horizontally effectively.
- + Integrates falling leaves realistically into the existing lighting of the scene.
- − The 'energetic and lively' feel is less pronounced than in the other model.
- − The dog remains static compared to the movement visible in the human's hair.
Verdict: Bria FIBO followed the creative aspects of the instruction more aggressively by changing the poses to a run, but it failed the core task of an image edit by completely re-generating the woman and dog's faces and the background. Wan 2.1 Pro successfully modified the hair and added leaves while keeping the original image almost perfectly intact, making it a much better tool for actual image editing.
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
Bria FIBO
- + Clean vector-style execution
- + Accurate color palette according to the prompt
- + Good center alignment for a minimalist emblem
- − Incorrect spelling of 'Florian'
- − Significant error in the date 'Est. 1320' instead of 1720
- − Text rendering is wobbly and inconsistent in some characters
Wan 2.7 Pro
- + Excellent typography and high readability
- + Correct date 'Est. 1720'
- + Sophisticated vintage aesthetic with professional line work
- − Minor spelling error 'Florion' instead of 'Florian'
- − Includes stray decorative elements in the corners not specifically requested
Verdict: Wan 2.7 Pro is the clear winner for its superior typography and adherence to the date. While both models struggled slightly with the name 'Florian', Wan 2.7 Pro produced a much more professional and coherent vintage emblem compared to Bria FIBO, which suffered from severe hallucinations on the date and text structure.
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
Bria FIBO
- + Features more detailed and visually interesting vector illustrations for Earth and Moon.
- + Layout has a good use of drop shadows and depth while remaining mostly flat.
- + Captures the color palette effectively with a professional navy background.
- − Text is entirely illegible gibberish.
- − The logical flow of the infographic steps is confusing and lacks clear labels.
- − The rocket and lunar module designs are inconsistent and abstract.
Wan 2.7 Pro
- + Excellent text rendering with clear, legible labels for every mission step.
- + Followed the logical progression of the prompt accurately from launch to landing.
- + Very clean, minimal vector aesthetic with consistent iconography.
- − The 'Descent' label is misspelled as 'DESCRIPT'.
- − The icons are quite small relative to the overall poster size.
- − The central axis layout is slightly repetitive.
Verdict: Wan 2.7 Pro is the clear winner because it successfully creates an actual infographic with legible text and a logical progression of the requested steps. While Bria FIBO has more intricate vector art, it fails as a communication piece because the text is unreadable and the mission steps are not clearly defined or ordered. Wan 2.7 Pro followed the sequential instructions of the prompt much more effectively.
Explore each model
Alibaba's Wan 2.7 Pro image generation and editing model with higher-quality outputs and support for 4K image generation