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 2.5 (Preview)
#27 of 62 in Text-to-Image
Where the votes landed
Bria FIBO
0%
win rate
Ties
0%
Wan 2.5 (Preview)
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 adherence to the glass refraction of the plant behind it
- + Superior composition with a more elegant, centered layout
- + Very clean and modern aesthetic with sharp glass edges
- − The blue sphere appears to be floating unnaturally without a shadow on the bottom glass face
Wan 2.5 (Preview)
- + Highly realistic textures on the vintage red book and wooden table
- + Accurate physical interaction with the sphere reflecting and resting on the bottom surface
- + Beautiful capture of the soft window light and dust motes
- − The plant looks more like it is growing out of/behind a separate pot than strictly 'behind the cube' in a clear way
- − The cube edges are slightly less defined compared to Model A
Verdict: Both models followed the spatial prompt perfectly. Bria FIBO produces a cleaner, more stylized commercial look with excellent glass refraction physics, whereas Wan 2.5 (Preview) excels at photographic realism, particularly in the weathered texture of the book and the naturalistic lighting and reflections.
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
- + Features cinematic lighting with vibrant reflections on the pavement.
- + Captures the 'light rain' atmosphere and wet textures effectively.
- + Good use of bokeh to create depth.
- − Anatomical failure with the hands, including extra and merged fingers.
- − The bicycle geometry is nonsensical, especially the pedals and frame construction.
- − The scale of the man relative to the bike feels slightly off.
Wan 2.5 (Preview)
- + Excellent anatomical detail in the aged skin and hands.
- + Highly realistic interaction with the bicycle including tools on the ground.
- + Adheres strongly to the 'candid street photo' requirement with convincing Japanese urban context.
- − The rain effect looks like static streaks rather than falling drops.
- − The bokeh on the car headlights is a bit busy/distracting.
Verdict: Wan 2.5 (Preview) produces a far more realistic and coherent image, specifically regarding the man's anatomy and the mechanical details of the bicycle. While Bria FIBO has a nice cinematic mood, it suffers from significant AI artifacts in the hands and bicycle frame, whereas Wan 2.5 feels like a genuine candid photograph.
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
- + Exquisite engraving detail on the plate armor
- + Highly realistic skin texture with subtle scarring
- + Excellent lighting composition with soft torchlight highlights
- − The hair beads are very subtle and blend into the hair
- − The leather straps are somewhat generic in texture compared to the metal
Wan 2.5 (Preview)
- + Stronger 'battle-worn' aesthetic with more visible dirt and abrasions
- + Better adherence to the 'beads in hair' prompt with prominent silver accents
- + Exceptional detail on the frayed cloth underlayer and leather stitching
- − The bokeh circles in the background are a bit distracting and large
- − The facial expression is slightly less lifelike than Model A
Verdict: Both models performed exceptionally well on this complex prompt. Bria FIBO captures a more elegant and polished version of the paladin with superior skin and metal luster, while Wan 2.5 (Preview) better emphasizes the gritty elements like frayed cloth, prominent hair beads, and actual smears of dirt and blood. Wan 2.5 is slightly preferred for its more complete adherence to the specific material textures requested.
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
- + Stronger adherence to the 'grid' layout requested
- + Includes price line indicators for a realistic menu feel
- + Vibrant use of teal and orange accents throughout
- − Image thumbnails are messy and lack focus
- − Text rendering is highly garbled and unreadable
- − Layout feels cramped and disorganized
Wan 2.5 (Preview)
- + Excellent food photography quality with clear isolated subjects
- + Clean, high-resolution rendering with a professional white background
- + Better overall legibility for section titles like 'Pizza' and 'Mains'
- − Repeated the prompt text 'Modern minimalist' in the actual design
- − Food items are repetitive and don't always match the section labels
Verdict: Wan 2.5 (Preview) is the clear winner due to its superior visual fidelity and professional presentation, featuring high-quality isolated food photography and a clean minimalist aesthetic. While Bria FIBO attempted a more complex grid with better use of color accents, the actual quality of the photos and the legibility of the text were significantly lower.
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 burger patty and sesame bun.
- + Vibrant, high-energy fiery background that integrates well with the theme.
- + Clean rendering of the 'MAGIC BURGER' title with a glowing neon effect.
- − Failed to include the currency symbol (€) for the price.
- − Did not render the price within a starburst as requested.
- − The secondary text 'LIMITED TIME ONLY' lacks the requested fiery/glowing effect.
Wan 2.5 (Preview)
- + Superior adherence to all text requirements, including the Euro symbol and starburst.
- + More dynamic 'exploded' composition with smaller ingredients flying outwards.
- + Creative typography with cheese-like drips integrated into the main title.
- − The 'MAGIC BURGER' text is slightly cropped at the top edges.
- − Burger patties look slightly less realistic compared to Model A.
Verdict: Wan 2.5 (Preview) provided a much more accurate response to the complex prompt, successfully including the starburst, the Euro symbol, and the specific lighting effects for all text elements. While Bria FIBO has slightly more realistic food textures, it failed on several key instructional details regarding the layout and specific characters in the advertisement text.
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
- + Excellent chalk-like texture in the handwriting style
- + Captures the requests for natural variations in letter size and slant
- − Extreme text rendering errors making all menu items illegible
- − Inaccurate date formatting ('April 3 2026' instead of 'April 30')
- − The bottom text at the base of the board uses a digital-looking font, violating the prompt
Wan 2.5 (Preview)
- + Near-perfect adherence to specific menu text including the difficult 'Brown Butter' item
- + Realistic composition with a wood-framed chalkboard and smudge marks
- + Accurate date and pricing rendering
- − Text appeared slightly cleaner than expected, borderline digital in appearance although capturing some chalk texture
- − Repeated the '$9' price on two lines for the cookies
Verdict: Wan 2.5 (Preview) significantly outperforms Bria FIBO by accurately rendering almost all of the specific text requested in the prompt, including the complex menu items and date. While Bria FIBO has a lovely, authentic chalk texture, the text is largely gibberish and fails to follow the content requirements.
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
- + Features creative details like glowing hooves and neon reins that suit a surreal prompt.
- + Strong color palette and nebula lighting.
- + Clear and coherent horse and astronaut anatomy.
- − The horse's legs are slightly stiff and lack dynamic movement.
- − Interpretation is more digital-art style than cinematic realism.
Wan 2.5 (Preview)
- + Excellent sense of motion with the horse's gallop and flowing mane.
- + Highly realistic textures on the spacesuit and horse's coat.
- + Stronger cinematic composition with a clear background of Earth and a galaxy.
- − The horse's front left leg has a slight anatomy glitch at the hoof.
- − The dust/particles at the bottom are slightly confusing given the space vacuum setting.
Verdict: Both models failed the negative constraint to have the horse on top of the astronaut, providing a standard astronaut-riding-horse image instead. Between the two, Wan 2.5 (Preview) produces a much more cinematic and dynamic image with superior lighting and realism, whereas Bria FIBO feels more like a static illustration.
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 interior detail and lighting coherence
- + Superior capybara fur texture rendering
- + Correct side-profile composition for a 'scene inside' feel
- − The capybara's hands look more like human-primate hybrids than capybara paws
- − The steering wheel placement is slightly awkward relative to the driver's body
Wan 2.5 (Preview)
- + Strong symmetrical composition that highlights the subject
- + Captures the 'bored' expression of the passenger very effectively
- + Better representation of capybara paws on the wheel
- − The lighting on the capybara's face is a bit flat compared to the background
- − The taxi sign on top appears inside the frame of the roof/windshield incorrectly
Verdict: Bria FIBO captures a more realistic interior atmosphere with impressive lighting and texture, making the absurdist prompt feel grounded. Wan 2.5 (Preview) excels in character expressions and specific anatomical details like the paws, though it has minor spatial errors with the taxi sign. Bria FIBO is preferred for its cinematic quality and superior integration of the animal into the jacket.
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
- + Successfully included the thorn and spiderweb border layout.
- + The central jack-o-lantern has a nice glow and realistic texture.
- + Captures a darker, more atmospheric moody night sky.
- − The text for the event details is heavily garbled and nonsensical.
- − The banner text has a typo, saying 'night of nights' instead of 'night of frights'.
- − The overall composition feels a bit cluttered with the text overlapping the imagery poorly.
Wan 2.5 (Preview)
- + Exceptional text rendering for both the শিরোনাম and the event details.
- + Highly accurate adherence to all specific text requests including the banner and date.
- + Clean and professional layout that feels like a real graphic design piece.
- − The lighting on the pumpkin is a bit more illustrative and less cinematic than the background.
- − The border is a bit busy with many overlapping thorns.
Verdict: Wan 2.5 (Preview) provided a significantly better result by following the text instructions perfectly, including the specific date and location which Bria FIBO failed to render correctly. While Bria FIBO captured a slightly moodier atmosphere, its inability to produce legible event details makes it unsuccessful as an invitation design.
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 thick, full head of hair with natural-looking texture.
- + The lighting on the hair matches the scene reasonably well.
- − Failed to preserve facial features, significantly altering the subject's face to look younger and different.
- − Failed to preserve the source image's background, clothing details, and overall composition.
Wan 2.5 (Preview)
- + Excellent preservation of the original person's facial features and identity.
- + Perfectly preserved the background, lighting, and clothing from the source image.
- + The added hair integrates seamlessly with the existing beard and glasses.
- − The hairline transition on the forehead is a bit abrupt.
- − The hair volume has a slightly 'wig-like' quality at the very top.
Verdict: Wan 2.5 (Preview) followed the instructions much better by adding a realistic head of hair while perfectly preserving the identity of the person and the details of the environment. Bria FIBO failed as an image editor by generating a completely new person and scene, losing almost all context from the source 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 text rendering and alignment.
- + Includes a variety of sushi types that enhance the scene.
- + Effective use of the isometric square diorama base as requested.
- − Includes some unwanted UI-like text/icons in the bottom corners.
- − Rice texture is slightly repetitive and bead-like.
Wan 2.5 (Preview)
- + Beautiful soft lighting and color palette.
- + Captures the 'miniature 3D cartoon' style perfectly.
- + Very clean composition with no extraneous artifacts or UI elements.
- − Perspective is more eye-level than the requested 45-degree top-down isometric view.
- − Only displays a single piece of sushi which feels a bit sparse for a 'scene'.
Verdict: Bria FIBO followed the technical layout instructions more closely, specifically the isometric perspective and the diorama base. However, Wan 2.5 (Preview) produced a higher quality, much cleaner artistic result that perfectly captured the requested 3D cartoon aesthetic without the messy watermark-like artifacts seen in Bria FIBO.
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
- + Excellent depiction of a crowded news studio set.
- + The character design captures a high-energy, exaggerated facial expression typical of caricatures.
- + Includes a large, well-rendered dog character.
- − Completely fails to include any hockey-related elements.
- − The subject's facial features and hair bear little resemblance to the source image.
- − Significant anatomical issues with the extra hand and messy background details.
Wan 2.5 (Preview)
- + Successfully incorporates all elements: tv anchor role, dogs, and hockey (stick and screen).
- + Maintains better source preservation by keeping the subject's hair color and denim shirt from the original photo.
- + Clean vector-style illustration with clear, legible composition.
- − The 'hockey game' shown on the monitor appears to be played on grass or a green field.
- − The caricature style is a bit safe and repetitive compared to traditional hand-drawn caricatures.
Verdict: Wan 2.5 (Preview) is the clear winner as it successfully incorporated every element of the prompt, including the specific request for hockey which Bria FIBO missed entirely. Wan 2.5 also did a better job of preserving the identity and clothing of the person in the source image while translating them into a cartoon style.
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 unavailable for this challenge.
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
- + Successfully captures the requested soft pastel color palette and dreamy background.
- + Maintains the core narrative of the meme while reimagining the setting in a lush, artistic way.
- − Significantly alters the character poses and spatial relationships of the source image.
- − The art style leans more towards generic modern shoujo anime rather than the specific hand-painted Studio Ghibli look.
Wan 2.5 (Preview)
- + Excellent preservation of the source image's composition, layout, and character poses.
- + Stronger adherence to the Ghibli aesthetic with clean line art and expressive facial shading.
- + Integrates thematic Ghibli elements like floating leaves to enhance the mood.
- − The color palette is a bit more muted than 'soft pastels', though it fits the requested nostalgia.
Verdict: Wan 2.5 (Preview) is the superior model for this edit as it manages to perfectly preserve the composition and character poses of the original meme while applying a authentic-looking Ghibli anime style. Bria FIBO captures the requested colors well but fails as an edit by completely redrawing the scene and losing the specific spatial context of the source image.
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
- + Strong sense of 'dynamic motion' with the running pose and flying hair.
- + Includes a large number of falling leaves as requested.
- − Poor source preservation, essentially generating a new image that looks different from the original.
- − Anatomical issues where the dog's leash connects to his collar incorrectly.
- − Low facial detail and blurred textures.
Wan 2.5 (Preview)
- + Excellent source preservation, keeping the original subjects and background nearly identical.
- + Accurately adds hair movement and leaves without distorting the original composition.
- + High visual quality and resolution matching the source.
- − The added leaves look a bit like digital overlays rather than integrated into the environment.
- − The 'energetic' feel is a bit subtle since the pose remains a walk.
Verdict: Wan 2.5 (Preview) is the clear winner as it successfully performs an image edit, whereas Bria FIBO creates a new image that merely resembles the source. Wan 2.5 (Preview) maintains all the fine details of the original woman and dog while adding the requested wind and leaves, whereas Bria FIBO changes their faces, clothing textures, and the background significantly.
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 illustration.
- + Excellent rendering of light steam inside the cloche.
- − Major spelling errors in the brand name ('Caffé Froaian').
- − Incorrect date 'Est. 1320' compared to the requested 1720.
Wan 2.5 (Preview)
- + Perfect adherence to text prompts including 'Caffè Florian' and 'Est. 1720'.
- + Excellent vintage atmosphere with subtle paper texture and framing.
- + Stronger vector emblem composition with logical steam placement.
- − Steam is a bit simple/stylized compared to a realistic vapor effect.
Verdict: While Bria FIBO produces a nice clean graphic, it fails significantly on the text requirements, misspelling both the restaurant name and the establishment date. Wan 2.5 (Preview) follows all instructions perfectly, providing correct typography, the requested banner, and a much more cohesive vintage aesthetic.
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
- + Excellent adherence to the 'flat-vector' aesthetic with clean, consistent iconography
- + Superior compositional balance that feels like a professional infographic poster
- + Follows the requested NASA-inspired color palette perfectly
- − Text consists of illegible placeholder symbols and gibberish
- − The 'Earth' icon has inconsistent perspective compared to the flat moon icon
- − Failed to include some of the specific labeled steps as readable text
Wan 2.5 (Preview)
- + Strong text legibility for step titles like 'LAUNCH' and 'TRANSLUNAR'
- + Accurate representation of the Saturn V rocket's silhouette
- + Clear inclusion of the landing site 'Tranquility' with a modern map pin icon
- − The mix of flat icons and photorealistic textures on the moon creates a stylistic clash
- − The line weights are inconsistent across the composition
- − The step sequence is somewhat disjointed and lacks a clear flow line
Verdict: Bria FIBO produces a much more cohesive professional design that perfectly captures the requested 'modern vector infographic' style, even though the text is illegible. Wan 2.5 (Preview) handles the specific text requirements and labels much better, but fails to maintain a consistent artistic style, mixing vector shapes with photographic elements which makes the composition feel cluttered.
Explore each model
Alibaba's text-to-image and image-to-image generation model from the Wan AI suite, offering high-quality visual generation capabilities