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
#56 of 62 in Text-to-Image
Stable Diffusion 3.5 Large
#30 of 62 in Text-to-Image
Where the votes landed
Bria FIBO
0%
win rate
Ties
0%
Stable Diffusion 3.5 Large
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 spatial logic with the book sitting securely on top of the glass.
- + Natural and high-quality rendering of the glass refractive properties.
- + Accurate placement of the plant behind the cube as requested.
Stable Diffusion 3.5 Large
- + Realistic lighting and texture on the wooden table.
- + Clear rendering of the glass edges and reflections.
- − Failed the spatial prompt; the red book is inside the glass cube instead of on top of it.
- − The blue sphere is sitting on the book rather than being the primary object inside the cube.
- − The perspective of the plant relative to the background is slightly disjointed.
Verdict: Bria FIBO followed every spatial instruction in the prompt perfectly, placing the red book on top of the cube and the plant behind it. Stable Diffusion 3.5 Large failed to follow the positional requirements, placing the book inside the cube and the sphere on top of the book. Bria FIBO is the clear winner for both prompt adherence and logical composition.
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 skin texture and face rendering
- + Strong adherence to the requested red bicycle color
- + Good use of shallow depth of field with realistic background bokeh
- − The bicycle anatomy is broken around the handlebars and front fork
- − The man's right hand has anatomical errors with the fingers
- − The rain is barely visible, appearing more like a dry street with some puddles
Stable Diffusion 3.5 Large
- + The rain effect is much more pronounced and matches the prompt better
- + Captures the 'candid' and 'imperfect framing' requested by the prompt
- + Good implementation of motion blur on the background car
- − The man's hands are severely distorted and merged into the bicycle
- − The bicycle frame logic is flawed near the seat post and rear wheel
- − The man's proportions and skin texture are less realistic than Image A
Verdict: Bria FIBO produces a much higher quality portrait with impressive skin textures, but fails to capture the weather conditions requested in the prompt. Stable Diffusion 3.5 Large successfully captures the 'candid street' atmosphere, rain, and motion blur, but suffers from significant anatomical distortions in the subject's hands and the bicycle's construction. Bria FIBO is the preferred image as its flaws are less distracting than the severe distortions in Stable Diffusion 3.5 Large.
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 high-contrast lighting with warm torchlight highlights
- + Vivid bead details in the braids and high-quality skin textures
- + Ornate engravings on the armor are intricate and well-defined
- − The scars appear more like surface dirt than actual scar tissue
- − The face has a slightly overly-smooth 'AI' finish in some areas
Stable Diffusion 3.5 Large
- + More realistic skin texture and convincing battle-worn scars
- + Superior hair braiding that matches the rugged paladin aesthetic
- + Excellent depth of field with a more natural color palette
- − Missed the request for beads in the hair braids
- − The eyes are slightly less lifelike and piercing than Model A
Verdict: Both models performed exceptionally well on the intricate details of the armor and lighting. Bria FIBO captures the specific details like the hair beads and warm torchlight glow more accurately, while Stable Diffusion 3.5 Large offers a more gritty, realistic interpretation of a 'battle-worn' character with better skin and scar textures.
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 use of vibrant accent colors (teal and orange) as requested.
- + Headings for Appetizers, Pizza, and Mains are clearly legible.
- + Layout more closely resembles a standard tri-fold or complex panel menu.
- − Food photos are abstract and messy, lacking appetizing clarity.
- − Text within the body blocks is completely nonsensical gibberish.
- − The grid structure is uneven and feels cluttered.
Stable Diffusion 3.5 Large
- + Food photos are high quality, appetizing, and clearly recognizable as pizza and salad.
- + Excellent minimalist composition with a professional, clean aesthetic.
- + Typography is cleaner and follows the requested bold sans-serif style effectively.
- − Minor spelling errors in main headers (e.g., 'MAIMAES', 'APPETIZRS').
- − The grid layout takes up a large portion of the page, potentially leaving less room for price/item descriptions.
Verdict: Stable Diffusion 3.5 Large is the clear winner as it produces high-quality, recognizable food photography and a sophisticated minimalist layout that truly looks professional. While Bria FIBO follows the instruction for vibrant accents well, its food imagery is distorted and the overall composition lacks the polish and clarity of Stable Diffusion 3.5 Large.
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 adherence to text requirements, rendering all requested phrases correctly.
- + Perfect execution of the 'exploded' concept with clear, suspended layers.
- + High-quality commercial food photography aesthetic with realistic textures.
- − Missing the Euro currency symbol (€) before the price.
- − The secondary text 'LIMITED TIME ONLY' lacks the requested fiery, glowing effect.
Stable Diffusion 3.5 Large
- + Great sense of heat and fire with realistic melting cheese and flames.
- + Very detailed rendering of the burger patties and charcoal base.
- − Completely failed to include any of the requested text.
- − Failed to create an 'exploded' view; the burger is mostly assembled and hovering.
- − Composition is less of an 'advertisement' and more of a conceptual image.
Verdict: Bria FIBO is the clear winner as it followed almost every instruction, including the complex request for an exploded view and multiple specific text strings. Stable Diffusion 3.5 Large completely ignored the text requirements and the 'exploded' burger layout, providing a standard assembled burger instead.
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 realistic chalk texture on the lettering
- + Captures the 'handwritten' feel with natural variations very well
- + Good focus on the board as requested
- − Significant spelling errors in every menu item
- − Failed to include the specific date 30
- − Text becomes complete gibberish at the bottom
Stable Diffusion 3.5 Large
- + Better overall cafe composition and interior aesthetics
- + Closer adherence to the requested date format
- + Contains more of the requested keywords in the menu section
- − The text looks more like a digital font than natural chalk handwriting
- − Significant spelling errors including 'Todaay' and 'Cockies'
- − The grid layout contradicts the simple three-item list request
Verdict: Bria FIBO captures the texture and soul of a chalk menu much better, though it fails significantly on spelling and specific content. Stable Diffusion 3.5 Large provides a much nicer environment and clearer text, but the text style feels too clean and digital, missing the authentic chalk texture requested in the prompt. Bria FIBO is slightly more successful in meeting the specific stylistic constraints of the text rendering.
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 high-contrast colors and cinematic lighting
- + Creative interpretation with glowing 'space hooves' and neon reins
- + Clear, high-resolution details on both the astronaut and the horse
- − The astronaut is notably small in scale compared to the horse
- − The anatomy of the back legs is slightly awkward
Stable Diffusion 3.5 Large
- + Naturalistic and seamless integration of the horse into a celestial environment
- + Dynamic sense of motion with the dust/nebula cloud trailing the horse
- + Perfect realistic scale between the rider and the animal
- − Failed the specific negative constraint 'horse on top, not vice versa'
- − The horse's face has some slight structural weirdness around the muzzle
Verdict: Both models failed the specific spatial logic instruction to place the horse on top of the astronaut, both opting for the traditional astronaut-on-horse composition. Bria FIBO is preferred for its striking visual style, creative neon details, and cleaner overall rendering, whereas Stable Diffusion 3.5 Large has a more realistic but slightly more generic 'stock photo' 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 complex multi-subject prompt including the passenger.
- + The capybara's hands/paws are realistically holding the steering wheel.
- + High level of background detail including rain on the window and a recognizable NYC skyline.
- − The anatomy of the capybara's lower body merging into the car seat is a bit messy.
- − The perspective of the dashboard is slightly warped.
Stable Diffusion 3.5 Large
- + High image sharpness and vibrant lighting effects.
- + The textures of the jacket and fur are very detailed.
- − Completely failed to include the businesswoman passenger in the back seat.
- − The capybara's paws are not holding the steering wheel correctly.
- − The driver is wearing a baseball cap instead of a taxi driver cap.
Verdict: Bria FIBO was the only model to successfully follow the prompt's instructions for a two-character scene, accurately depicting the bored businesswoman in the back. While Stable Diffusion 3.5 Large has high textural detail, it completely ignored the passenger and failed the specific interaction of the paws on the steering wheel.
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 renders the large central jack-o-lantern requested.
- + Excellent moody, cinematic lighting with realistic fog effects.
- + Includes the specific thorns and spiderweb border mentioned in the prompt.
- − Text rendering for the event details is incoherent nonsense.
- − Failed to correctly transcribe the phrase 'night of frights', writing 'night of nights' instead.
Stable Diffusion 3.5 Large
- + Near-perfect text rendering for the primary titles and the scroll banner.
- + Strong vintage parchment aesthetic with burnt, irregular edges.
- + Good artistic composition using a large moon to frame the scene.
- − Completely missed the specific event details (Date, Time, Location) at the bottom.
- − The layout is quite cluttered at the bottom, making it less functional as an invitation.
- − The jack-o-lanterns are small and secondary rather than 'central' as requested.
Verdict: Bria FIBO captures the cinematic atmosphere and specific visual elements like the thorns and central jack-o-lantern much better, but fails significantly on text legibility. Stable Diffusion 3.5 Large produces much cleaner, accurate text for the main headings but fails to include the requested event details and ignores the 'central' placement of the pumpkin. Bria FIBO is the better visual match for a 'poster', while Stable Diffusion 3.5 Large is better for clean typography.
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 typography rendering that follows the placement instructions perfectly.
- + Highly polished 3D isometric aesthetic with clean PBR textures.
- + Very clean composition that matches the 'ultra-clean' requirement.
- − Includes some unnecessary watermarking/text artifacts in the bottom corners.
- − The flag icon is a simple red circle rather than a full flag representation.
Stable Diffusion 3.5 Large
- + More variety in the sushi types shown.
- + Includes a physical miniature flag which matches the 'miniature scene' theme.
- + Good rendering of textures like rice and salmon.
- − Failed the instruction to place the text at 'top-center', placing it on a small card instead.
- − The background has a textured paper look rather than being a 'solid' light blue.
- − The scene feels more cluttered compared to the 'minimal' request.
Verdict: Bria FIBO followed the stylistic and layout instructions much more accurately, particularly regarding the text placement and the clean, isometric aesthetic. While Stable Diffusion 3.5 Large produced high-quality textures, it failed to follow the specific spatial instructions for the 'JAPAN SUSHI' text and created a busier scene than requested.
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 inclusion of all four specific animal species
- + Vibrant colors with a very high density of wildflowers
- + Clearer, sharper focus on all subjects across the frame
- − The fox's pose is physically awkward as if it is floating
- − The lighting feels a bit more illustrative and less photorealistic
Stable Diffusion 3.5 Large
- + Sublime lighting with realistic bokeh and dew-glimmer effects
- + Captures the 'playful tumbling' motion better than Image A
- + Extremely soft and detailed fur textures
- − The fox kit is significantly blurred in the background
- − One of the animals (the kitten) looks more like a desert cat or fox-hybrid than a traditional tabby kitten
Verdict: Bria FIBO followed the specific species requirements more accurately, clearly showing a distinct tabby kitten and red fox. However, Stable Diffusion 3.5 Large achieved a much higher level of photorealism with its superior handling of golden hour lighting, depth of field, and natural-looking motion.
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 illustration style
- + Good execution of the steam effect inside the dome
- + Balanced use of warm brown and cream tones
- − Incorrect text spelling for both the name and the date
- − Typography feels a bit heavy for the minimalist request
Stable Diffusion 3.5 Large
- + Accurate text rendering for the brand name and the specific date
- + Strong adherence to the vintage texture and minimalist vector aesthetic
- + Excellent composition with decorative corner elements
- − Small typo in 'Cafféé' (double 'e' at the end)
- − The steam above the dome handle is a bit stylistically detached from the rest of the icon
Verdict: Stable Diffusion 3.5 Large is the clear winner as it followed the complex text instructions much better than Bria FIBO, which failed on the specific date and brand name spelling. Stable Diffusion 3.5 Large also captured the requested vintage texture and minimalist logo style more effectively, despite a minor double-letter typo in the primary text.
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
- + Stronger adherence to the flat-vector infographic style.
- + Clear, logical flow representing the stages of the mission.
- + Excellent palette usage following the NASA-inspired theme.
- − Text consists entirely of illegible gibberish.
- − The Saturn V icon is slightly stylized toward a space shuttle hybrid.
Stable Diffusion 3.5 Large
- + Features more detailed planetary textures.
- + Includes recognizable, albeit misspelled, names like Collins and Armstrong.
- + Captures the 'Launch' stage with a more accurate rocket silhouette.
- − Composition is cluttered and lacks a clear 'step-by-step' infographic flow.
- − Inconsistent style with realistic planets mixed with abstract lines.
- − Fails to follow the specific 'trajectory arc' and 'orbit ring' icon requests.
Verdict: Bria FIBO far better understands the requested 'flat-vector infographic' format, creating a clean and readable layout that logically follows the mission steps from launch to landing. While Stable Diffusion 3.5 Large has better text rendering and more detailed textures, its composition is chaotic and fails to meet the stylistic requirements of a modern vector poster.
Explore each model
Stability AI's 8.1-billion parameter Multimodal Diffusion Transformer (MMDiT) text-to-image model featuring improved image quality, typography, complex prompt understanding, and resource-efficiency