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 Turbo
#61 of 62 in Text-to-Image
Where the votes landed
Bria FIBO
0%
win rate
Ties
0%
Stable Diffusion 3.5 Large Turbo
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 complex spatial arrangement requested.
- + Realistic material rendering of thick glass and soft window lighting.
- + Accurate placement of the red book on top and the plant behind.
- − The plant stem appears to merge slightly with the glass interior.
- − The perspective of the table edges is a bit sharp compared to the blurred background.
Stable Diffusion 3.5 Large Turbo
- + Clean, minimalist aesthetic with sharp focus.
- + Good lighting and shadow interplay on the table surface.
- − Failed the spatial prompt: the red book is inside the cube rather than on top.
- − Inconsistent glass framing; the black edges look more like a display case than a solid glass cube.
- − The blue sphere is sitting on the book, which was not requested.
Verdict: Bria FIBO followed the spatial instructions perfectly, accurately placing the sphere inside, the book on top, and the plant behind the glass cube. Stable Diffusion 3.5 Large Turbo failed to follow the positional logic, placing the red book inside the cube and the sphere on top of the book. Bria FIBO is the clear winner for its superior prompt adherence and realistic material interaction.
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 adherence to aesthetic prompts like shallow depth of field and bokeh.
- + Highly realistic skin textures and facial details on the subject.
- + Strong cinematic atmosphere with convincing rain and reflections.
- − Significant anatomical issues with the subject's hands and fingers.
- − The bicycle geometry is mangled, particularly where the frame meets the handlebars.
Stable Diffusion 3.5 Large Turbo
- + Successfully captures a more unique, 'imperfect' framing style as requested.
- + The bicycle structure is more coherent and logically assembled than Model A's.
- − Fails to produce the requested shallow depth of field, resulting in a flat image.
- − The subject's head and hair appear distorted and poorly defined.
- − Lacks the 'natural skin texture' and 'cinematic' lighting requested in the prompt.
Verdict: Bria FIBO captures the cinematic atmosphere, rain effects, and realistic skin texture much better than Stable Diffusion 3.5 Large Turbo, although it suffers from severe hand and bicycle artifacts. Stable Diffusion 3.5 Large Turbo produces a flatter, less detailed image that ignores the depth of field and lighting requirements of the prompt. Bria FIBO is the preferred choice for its superior photorealism and adherence to the emotional mood of the scene.
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 detailed engraving on the plate armor
- + Subtle and realistic skin texture with believable dirt and scars
- + Precise adherence to the braided hair with beads and bokeh sparks prompt
- − The lighting on the face is a bit flat compared to the dramatic back-lighting
Stable Diffusion 3.5 Large Turbo
- + Strong facial features and lifelike eye gaze
- + Good use of color contrast with the green cloth underlayer
- − The 'scars' look more like fresh blood or red paint than faint battle scars
- − The armor engraving lacks the fine detail and metallic realistic sheen found in the other image
- − The hair braids look somewhat plastic and lack the requested beads
Verdict: Bria FIBO significantly outperformed Stable Diffusion 3.5 Large Turbo in this comparison, particularly in the quality of the armor texture and the realism of the battle-worn details. While both models captured the basic composition, Bria FIBO's attention to the fine details like the beads in the hair and the intricate engraving on the metal made it much more successful.
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 rendering with almost perfectly legible headers
- + Professional layout structure that resembles a real tri-fold or multi-column menu
- + Clean use of white space and consistent graphic accents
- − Food images lack clarity and look like messy digital paintings
- − Sub-text and pricing characters are gibberish upon close inspection
Stable Diffusion 3.5 Large Turbo
- + High saturation and vibrant food photography
- + Crisp, clean rendering of bowl and plate objects
- + Good use of shadows to create a high-end feel
- − Poor layout logic where food takes up most of the page and text is secondary
- − Misspelled headers such as 'Mians' for 'Mains'
- − Lack of the requested 'sections for appetizers' within the text area
Verdict: Bria FIBO captures the essence of a graphic design task much better, providing a realistic menu structure, legible headers, and a clean professional layout that fits the request. While Stable Diffusion 3.5 Large Turbo has superior image quality for the food items themselves, it fails as a menu design by misspelling categories and prioritizing a chaotic grid of photos over a functional document layout.
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, vegetables, and bun.
- + Successfully included all required text elements with the requested glowing fiery effect.
- + Accurately depicted the 'exploded' view with suspended components.
- − Missing the Euro symbol (€) in the price, displaying only '6.99'.
- − Text placement of 'LIMITED TIME ONLY' is a bit plain compared to the other elements.
Stable Diffusion 3.5 Large Turbo
- + Strong vibrant colors and high contrast background.
- + Good use of embers and smoke to create atmosphere.
- − Failed to include any of the requested text elements.
- − Did not follow the 'exploded' instruction, showing a mostly assembled burger instead.
- − The image has a more plastic, CGI look rather than the requested photorealism.
Verdict: Bria FIBO is the clear winner as it followed all prompt instructions, including the complex request for specific text and an exploded view. Stable Diffusion 3.5 Large Turbo failed to include any text and ignored the primary structural requirement of the 'exploded' burger, resulting in a generic product shot.
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
- + Authentic café atmosphere with shallow depth of field
- + Text varies in size and slant naturally as requested
- − Text contains major spelling errors (e.g., 'Trutle Mumssotro')
- − Failed to include the specific year and date correctly
Stable Diffusion 3.5 Large Turbo
- + Cleaner layout and composition
- + More attempts at formatting the menu items requested
- − The text style looks like a digital font rather than natural chalk handwriting
- − Significant spelling and gibberish errors in the body text
- − The date is cut off and incorrect
Verdict: Bria FIBO captures the requested chalk texture and handwriting style much more effectively than Stable Diffusion 3.5 Large Turbo, which produces text that looks like a digital typeface. While both models struggled significantly with the specific text strings and spelling, Bria FIBO is the preferred choice for its superior artistic execution of the 'handwritten chalkboard' aesthetic.
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 with vibrant nebulae and glowing details.
- + Highly detailed texture on the astronaut suit and horse's coat.
- + Strong surreal atmosphere with glowing hooves and neon reins.
- − Failed the negative constraint: the astronaut is on top, not the horse.
- − The composition is somewhat standard for 'astronaut riding horse' despite the specific prompt instruction.
Stable Diffusion 3.5 Large Turbo
- + Clean, sharp lighting that feels cinematic and cohesive.
- + Good anatomical consistency for the horse and astronaut gear.
- + Dramatic angle and composition.
- − Failed the negative constraint: the astronaut is on top, not the horse.
- − The Earth in the background appears slightly distorted or poorly rendered.
Verdict: Both models completely failed the specific spatial logic of the prompt ('horse on top, not vice versa'), instead providing the common interpretation of an astronaut riding a horse. Bria FIBO is preferred because it leans more into the 'surreal' and 'highly detailed' keywords with its vibrant galaxy background and glowing accents, whereas Stable Diffusion 3.5 Large Turbo provides a more grounded, literal interpretation of the space theme.
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 all prompt elements, including the passenger and her phone.
- + Highly detailed and realistic taxi interior and city background.
- + Clearer depiction of the capybara's professional expression and clothing.
- − The capybara's hands look more like monkey paws than capybara paws.
- − Minor perspective inconsistencies with the taxi door frame and roof.
Stable Diffusion 3.5 Large Turbo
- + Natural bokeh effects on the city lights through the windows.
- + Clean texture on the capybara's fur and the taxi driver cap.
- − Completely missed the passenger's action of looking at a phone.
- − The passenger is out of focus and lacks detail.
- − The capybara's anatomy around the neck/collar area is somewhat disjointed.
Verdict: Bria FIBO followed the prompt much more accurately, successfully including the businesswoman looking at her phone as requested. Stable Diffusion 3.5 Large Turbo failed to depict the passenger's activities and lost a significant amount of detail in the background, whereas Bria FIBO captured the 'bored' atmosphere and busy New York night perfectly.
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
- + Excellent cinematic lighting and atmospheric fog effects.
- + Includes nearly all requested text elements, including a scroll banner.
- + The border of thorns and webs is intricately detailed and fits the gothic theme.
- − The small text at the bottom is largely illegible and contains typos like 'Lootion' and 'Impm'.
- − The text on the scroll banner changed 'frights' to 'nights'.
Stable Diffusion 3.5 Large Turbo
- + Clean and legible central title text.
- + Strong graphic design elements for the border and frame.
- − Failed to include the specific event details (Date, Time, Location).
- − Missing the scroll banner and the full title phrase requested.
- − The lighting is flat and cartoony rather than cinematically moody.
Verdict: Bria FIBO captures the cinematic, moody atmosphere of a gothic invitation much better than Stable Diffusion 3.5 Large Turbo, and it attempts all the requested text fields. While Bria FIBO struggles with the legibility of the fine print at the bottom, Stable Diffusion 3.5 Large Turbo completely ignores several lines of requested text and delivers a much simpler, more generic graphic style.
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 with the word 'JAPAN' and 'SUSHI' spelled perfectly.
- + Realistic PBR-like textures on the fish and wasabi that balance cartoon and realism well.
- + Perfect adherence to the requested isometric perspective and light blue background.
Stable Diffusion 3.5 Large Turbo
- + Creative use of a 3D signpost for the text elements.
- + Clean miniature diorama aesthetic with a distinct raised wooden base.
- + Well-defined isometric angle.
- − Spelling error in the text ('SIIHI' instead of 'SUSHI').
- − The flag icon is generic and not recognizable as the Japanese flag.
- − The background is a grey-blue gradient rather than the requested solid light blue.
Verdict: Bria FIBO followed every instruction perfectly, including complex text rendering and specific background colors, resulting in a professional-grade graphic. Stable Diffusion 3.5 Large Turbo failed on the spelling of 'SUSHI', provided an incorrect flag, and ignored the solid background request. Bria FIBO is the clear winner for its technical precision and adherence to prompt details.
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 animals: puppy, kitten, bunny, and fox kit.
- + Excellent lighting with visible god rays and a warm sunrise color palette.
- + Dynamic composition that captures the 'tumbling' and 'chasing' aspect of the prompt.
- − The fox's anatomy is slightly distorted, specifically the placement of its front legs.
- − Some butterflies appear to be floating without realistic movement or depth.
Stable Diffusion 3.5 Large Turbo
- + High clarity on the fur textures and facial details of the primary subjects.
- + Colors are vibrant with a pleasant bokeh background.
- − Misses multiple requested animals, failing to include the bunny and red fox kit.
- − The animals are posing rather than 'tumbling together' or 'chasing' as requested.
- − The puppy's ears have unnatural, needle-like fur artifacts.
Verdict: Bria FIBO is the clear winner as it followed the complex prompt requirements, successfully rendering all four specific baby animals in a dynamic, action-oriented scene. While Stable Diffusion 3.5 Large Turbo has clean textures, it failed significantly on prompt adherence by omitting half of the requested subjects and ignoring the 'tumbling' action.
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 aesthetic suitable for a modern-minimalist logo
- + Accurate depiction of a glass cloche dome with internal steam
- + Excellent color palette consistency with warm brown and cream tones
- − Failed the spelling of the restaurant name significantly (Froaian)
- − Incorrect foundation date provided (1320 instead of 1720)
Stable Diffusion 3.5 Large Turbo
- + Accurate date text in the banner
- + Strong vintage texture and classic woodcut engraving style
- + More sophisticated banner design with detailed cross-hatching
- − Minor spelling error in the name (Caffee Florin instead of Caffè Florian)
- − The cloche dome is merged awkwardly with a coffee mug handle
- − Less minimalist than requested, leaning more towards a complex illustration
Verdict: Bria FIBO captures the minimalist vector emblem style perfectly but fails completely on text accuracy for both the name and the date. Stable Diffusion 3.5 Large Turbo provides a 훨씬 richer vintage feel and gets the date correct, though it makes a minor spelling error and creates a confusing hybrid object (cloche-mug). Stable Diffusion 3.5 Large Turbo is the winner for its superior text rendering and artistic depth, despite the slight anatomical confusion of the logo icon.
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 NASA-inspired color palette.
- + Includes most of the requested icons like the Saturn V, Earth orbit, and trajectories.
- + Very clean, modern vector aesthetic that matches the infographic request.
- − Text is largely gibberish despite attempting specific names like Armstrong and Aldrin.
- − The logical flow of the infographic steps is a bit cluttered and hard to follow.
Stable Diffusion 3.5 Large Turbo
- + Stronger layout for a poster with a clear header and categorized sections.
- + Better overall composition and artistic style.
- + Text rendering is slightly more legible in the headings compared to the competition.
- − Missed several specific icon requests like the Saturn V launch and the sequential trajectory arc.
- − Composition feels more like a generic space illustration than a functional step-by-step infographic.
Verdict: Bria FIBO followed the specific icon requirements of the infographic much more closely, including the Saturn V and the specific trajectory steps requested. However, Stable Diffusion 3.5 Large Turbo produced a more aesthetically pleasing poster with a better layout, despite missing the technical step-by-step details of the prompt. Bria FIBO is the winner for better instruction following regarding the specific mission phases.
Explore each model
Distilled version of SD 3.5 Large that generates high-quality images in just 4 steps, offering faster inference and reduced costs