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 13 shared challenges, with an AI judge weighing in on each.
Bria FIBO
#55 of 62 in Text-to-Image
Qwen Image 2512
#30 of 62 in Text-to-Image
Where the votes landed
Bria FIBO
0%
win rate
Ties
0%
Qwen Image 2512
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 caustic light effects on the table
- + The blue sphere appears realistically suspended within the glass
- + High clarity and sharp photographic quality
- − The plant appears to be inside the glass rather than just behind it
- − The lighting on the book is slightly inconsistent with the window light source
Qwen Image 2512
- + Accurately places the plant behind the glass cube with realistic distortion
- + Excellent texture on the red book cover and pages
- + Consistent soft window lighting across all elements
- − Internal reflections in the glass are slightly messy/confusing
- − The blue sphere occupies the same space as its reflection without clear depth separation
Verdict: Both models followed the prompt requirements perfectly. Bria FIBO produces a cleaner, more 'magical' aesthetic with impressive glass physics, but it fails to keep the plant strictly behind the cube as requested. Qwen Image 2512 manages the spatial relationship of the plant behind the glass much better and offers a more grounded, realistic photographic look.
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
- + Excellent shallow depth of field and bokeh effects
- + Captures the 'repairing' action more convincingly
- + Strong rain effects and vibrant red color on the bicycle
- − Significant anatomical errors in the hands and fingers
- − The bicycle geometry is illogical, especially the pedals and frame connections
- − Central composition ignores the 'imperfect framing' request
Qwen Image 2512
- + More realistic 'imperfect' street photography framing
- + Superior facial features and hand anatomy
- + Natural skin texture and convincing lighting on the man's face
- − The subject is posing/looking at the camera rather than 'repairing' the bike
- − Background cars lack the requested motion blur
- − Bicycle anatomy has several structural clipping issues
Verdict: Qwen Image 2512 produces a much more believable person with natural skin textures and accurate hands, aligning better with the 'candid street photo' aesthetic. While Bria FIBO handles the environmental effects like rain and depth of field more dramatically, its severe anatomical failures and centered composition make it look less like a real 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 floral engraving details on the plate armor
- + Clean composition with effective use of sparks and lighting on face and metal
- + Excellent rendering of braided hair and skin texture
- − The 'battle-worn' scars and dirt appear a bit too superficial and clean
- − The armor assembly around the shoulder straps looks somewhat confusingly layered
Qwen Image 2512
- + Stronger adherence to the 'battle-worn' prompt with deeper scars and visible grime
- + Excellent implementation of beads within the braids as requested
- + Powerful, gritty atmosphere with realistic torchlight glow and bokeh
- − Some messy artifacts where the braids interact with the plate armor straps
- − The engraving on the armor is slightly less sharp compared to the other model
Verdict: Qwen Image 2512 is the preferred result because it better captures the 'battle-worn' aesthetic with more convincing scars and grit, as well as a more accurate interpretation of beads in the hair. Bria FIBO produces a very high-quality image with superior armor engravings, but the subject looks a bit too pristine for a veteran paladin.
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
- + Successfully includes all three requested sections: Appetizers, Pizza, and Mains.
- + The layout is very clean with logical spacing and use of whitespace.
- + Food photography is bright and integrates well with the colorful accents.
- − Text consists of nonsensical characters and severe typos.
- − The grid structure is a bit disorganized with overlapping elements.
Qwen Image 2512
- + Strict adherence to the 'grid' prompt with a clear 4x2 top-down food display.
- + Better legibility of bold sans-serif headers.
- + Excellent use of vibrant secondary colors for categorization.
- − The 'Mains' section is labeled incorrectly as 'Means'.
- − Text content remains gibberish despite better character formation.
Verdict: Qwen Image 2512 is the preferred choice because it demonstrates a much stronger understanding of the 'grid' layout and 'professional' aesthetic requested. While Bria FIBO captures the color palette well, its layout feels like a collection of disjointed scraps compared to the cohesive, structured menu design produced by Qwen Image 2512.
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 patty, lettuce, and tomatoes.
- + Dynamic vertical composition that clearly shows all layers suspended in air.
- + High-quality rendering of the fiery, smoky background.
- − Missed the Euro currency symbol (only shows 6.99).
- − The starburst effect for the price is slightly abstract compared to a traditional graphic element.
- − The text 'LIMITED TIME ONLY' lacks the requested glowing fiery effect.
Qwen Image 2512
- + Perfect adherence to all text requirements including the Euro symbol and starburst graphic.
- + Strong sense of motion with particles and sauce droplets spinning around the burger.
- + Consistent fiery glowing effect across all text elements.
- − The 'exploded' effect is less pronounced than in Model A, as the layers are still mostly touching.
- − Slightly less realistic texture on the bottom bun compared to Model A.
Verdict: While Bria FIBO captures the 'exploded' vertical layout and food textures with slightly more photorealism, Qwen Image 2512 is the superior overall advertisement. Qwen Image 2512 followed all specific text instructions—including the symbol, starburst, and glowing effects—while maintaining a very high level of visual quality and motion.
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-looking chalk texture on the individual letters.
- + Realistic board smudges and background cafe bokeh.
- − Failure to render legible words for the menu items.
- − Missing pieces of the specific text requested in the prompt.
- − Inaccurate date compared to the prompt requirement.
Qwen Image 2512
- + Excellent text rendering with near-perfect spelling and legibility of all items.
- + Beautiful cursive chalk typography that remains consistent throughout.
- + Strong adherence to all prompt details including specific date and prices.
- − The text looks slightly too clean and perfect, bordering on a digital 'chalk font' aesthetic rather than messy handwriting.
- − Minor spelling error in 'Risotto' (spelled as 'Risitto').
Verdict: Qwen Image 2512 is the clear winner as it successfully rendered almost all the specific text, including the complex menu items and prices, with high legibility. Bria FIBO captured the textured feel of chalk more realistically, but the text itself is largely nonsensical scribble that fails the prompt's core 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
- + Excellent use of color and vibrancy in the nebula background
- + Creative glowing horse hooves and reins that enhance the surreal theme
- + Very clean anatomical construction of both subjects
- − Failed the negative constraint; the astronaut is on top of the horse instead of the horse on top of the astronaut
Qwen Image 2512
- + Realistic lighting and texture on the spacesuit and horse's coat
- + High level of detail on the mechanical components of the astronaut gear
- + Dynamic posing of the horse's legs
- − Failed the negative constraint; the astronaut is on top of the horse instead of the horse on top of the astronaut
- − The scale feels slightly inconsistent between the astronaut's body and the horse's back
Verdict: Both models failed to correctly interpret the specific spatial instruction 'horse on top, not vice versa,' opting for the standard interpretation of an astronaut riding a horse. Performance is therefore judged on visual quality; Bria FIBO is preferred for its superior artistic composition and creative use of sci-fi accents like glowing hooves, whereas Qwen Image 2512 has a more grounded, realistic rendering style.
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 depiction of a realistic New York taxi interior from a side-profile perspective.
- + High-quality lighting from the smartphone screen illuminating the passenger's face.
- + Very detailed city background with recognizable Manhattan-style lighting.
- − The capybara's paws are rendered as five-fingered human-like hands with fur.
- − The capybara's perspective makes it seem excessively large for the car seat.
Qwen Image 2512
- + Stronger prompt adherence regarding the bored/normal expression of the passenger.
- + Better composition for a symmetrical 'driving' shot through the windshield.
- + The capybara's facial features look more natural and centered.
- − Serious anatomy issues with the hands/paws on the steering wheel.
- − The passenger's phone is clipping through her fingers.
- − The taxi interior looks less defined and more generic than the other model.
Verdict: Both models struggled with the 'paws on wheel' instruction, rendering them as strange human-animal hybrids. Bria FIBO captures the premium 'photorealistic' feel of Manhattan at night with superior lighting and atmospheric detail, while Qwen Image 2512 does a better job capturing the specific bored expression of the passenger and the central focus of the driver.
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
- + Strong parchment-style burned edge effect.
- + Accurate phrasing in the scroll banner text.
- − Failed to render all bottom event text correctly, including gibberish dates and locations.
- − The composition feels slightly cluttered with the large header and fragmented text layout.
Qwen Image 2512
- + Perfectly rendered event details with correct date, time, and location.
- + High visual clarity and symmetrical, balanced composition.
- + Beautifully detailed thorns and cobweb border.
- − Typo in the main title where 'Halloween' is spelled as 'Hallowern'.
- − The trees are a bit repetitive in their styling.
Verdict: Qwen Image 2512 is the clear winner for its superior ability to follow complex text instructions for the event details, despite a minor typo in the main title. Bria FIBO struggled significantly with the structured data at the bottom, resulting in illegible text that makes it unusable as an actual invitation.
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 PBR materials with realistic textures on the fish and rice.
- + Extremely clean typographic rendering for the main text elements.
- + High-clarity lighting that fits the square format perfectly.
- − Includes stray watermark-like text and icons at the bottom corners.
- − The flag icon is a simple red dot without a border context.
Qwen Image 2512
- + Perfect adherence to the 'cartoon scene' stylistic prompt.
- + Includes more creative garnish like bamboo leaves and small flowers that fit the diorama style.
- + Properly rendered flag icon within a border.
- − The 'JAPAN' text has minor coloring artifacts/inconsistency in the font fill.
- − The textures are slightly more flat compared to the requested 'realistic PBR' materials.
Verdict: Bria FIBO produced a very clean image with superior material rendering, especially in the rice and fish textures, but was marred by unwanted watermark-like artifacts at the bottom. Qwen Image 2512 followed the 'cartoon' and 'diorama' aspects more creatively, resulting in a more cohesive artistic piece despite slightly weaker text rendering. Qwen Image 2512 is preferred for its lack of artifacts and more charming composition.
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
- + Excellent dynamic action including a leaping fox kit and running puppy
- + Vibrant use of diverse wildflowers and colorful butterflies
- + Strong adherence to the 'tumbling together' part of the prompt
- − Anatomical errors such as the fox kit's missing ear and floating appearance
- − The animals look somewhat more like digital illustrations than raw photography
Qwen Image 2512
- + Superior photorealistic texture for the fur and eyes
- + Excellent lighting with well-defined god rays and dew sparkles
- + Cohesive composition with all requested animals clearly visible and correctly formed
- − The animals are posed more for a portrait than 'tumbling' or 'chasing'
- − The butterflies look slightly static compared to the high-quality animals
Verdict: Qwen Image 2512 produces a much more realistic image with superior fur textures and lighting, resulting in a true 8K masterpiece feel. While Bria FIBO captures the 'tumbling' action better, it suffers from several anatomical glitches and a more artificial, saturated look.
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 prompt
- − Failed to spell the name correctly, rendering it as 'Caffé Froaian'
- − Incorrect date 'Est. 1320' instead of '1720'
- − The cloche handle is detached and poorly rendered
Qwen Image 2512
- + Perfect text rendering of the name and date
- + High-quality vintage illustration style with excellent texture
- + Strong composition and visual appeal
- − The steam is a bit more dramatic than 'minimalist' might suggest
- − Missing the accent on the first 'e' in 'Caffè' (though correct on the 'a')
Verdict: Qwen Image 2512 is the clear winner as it correctly follows the complex text requirements for 'Caffè Florian' and 'Est. 1720', whereas Bria FIBO failed significantly on both pieces of text. Qwen Image 2512 also displays much higher artistic quality with its woodcut-style shading and 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
- + Elegant layout with custom iconography and a cohesive infographic structure.
- + Strictly adheres to the requested color palette and flat vector style with subtle gradients.
- + Excellent balance and visual hierarchy in the graphic design.
- − The text is entirely illegible gibberish.
- − Does not follow the 6-step logical flow requested in the prompt.
Qwen Image 2512
- + Attempts to label the specific steps requested in the prompt.
- + Recognizable Saturn V and Lunar Module designs.
- + Clean headline text that clearly identifies the topic.
- − Confused layout with repeating numbers (two 2s and two 3s) and messy numbering placement.
- − Significant spelling errors in the step labels (e.g., 'Desceeint', 'TranslauraJ').
- − The Saturn V rocket is missing its top half, appearing cut off.
Verdict: Bria FIBO captures the aesthetic of a professional infographic much better, with superior vector art and color harmony, though its text is completely decorative nonsensical characters. Qwen Image 2512 attempts to follow the specific 6-step prompt more literally but fails in execution with broken numbering, poor spelling, and a cut-off rocket illustration. Bria FIBO is the preferred choice for a design-forward task where style and composition are paramount.
Explore each model
Improved version of Alibaba's Qwen image model with better text rendering, finer natural textures, and more realistic human generation.