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
17.1
arena score
#54 of 62 in Text-to-Image
Skill signature
· Text-to-Image
DALL-E 3
20.1
arena score
#42 of 62 in Text-to-Image
Vote tally
Where the votes landed
Bria FIBO
100.0%
win rate
Ties
0.0%
DALL-E 3
0.0%
win rate
100.0%
0.0% ties
0.0%
Shared challenges
13
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.”
Bria FIBO
DALL-E 3
AI Judge Analysis
Bria FIBO
- + Excellent adherence to the spatial arrangement requested in the prompt
- + Accurately places the red book on top of the glass cube
- + Features realistic glass refractions and lighting from the left
- − The plant stem appears to merge into the glass rather than logically sitting behind it
DALL-E 3
- + High visual quality with intricate details inside the sphere
- − Failed to follow spatial instructions; the red book is inside the cube instead of on top
- − The cube design features a wooden frame not requested in the prompt
- − The sphere is on top of the book rather than just being inside the cube
Verdict: Bria FIBO followed every spatial instruction in the prompt, correctly placing the sphere inside the cube and the book on top. DALL-E 3 struggled with the object relationships, placing the book inside the cube and adding an unrequested wooden frame. Bria FIBO is the clear winner for its precise prompt adherence.
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.”
Bria FIBO
DALL-E 3
AI Judge Analysis
Bria FIBO
- + Natural skin textures and realistic lighting
- + Excellent centered composition following the subject
- + Detailed rendering of the bicycle frame and mechanical parts
- − Anatomical errors in the hands with extra/fused fingers
- − Noticeable AI artifacting where the man's shoes meet the pavement
- − Lacks the motion blur from cars requested in the prompt
DALL-E 3
- + Strong composition using out-of-focus foreground elements for a 'candid' feel
- + Clearer inclusion of requested elements like motion blur and rain puddles
- + Better adherence to the 'imperfect framing' and 'candid' aesthetic
- − Skin texture appears somewhat plastic or smoothed compared to Model A
- − Anatomical issues with the man's feet and the connection of his legs to his torso
- − The bicycle geometry is distorted and lacks realistic mechanical structure
Verdict: Bria FIBO captures the 'natural skin texture' and '50mm' look much better, but fails on several specific prompt instructions like motion blur. DALL-E 3 creates a more cinematic and candid scene with better adherence to the environmental requests, though it suffers from significant anatomical distortion and a more 'generated' skin finish. Bria FIBO is the likely winner for its superior realism in lighting and texture, despite the hand artifacts.
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.”
Bria FIBO
DALL-E 3
AI Judge Analysis
Bria FIBO
- + Excellent depiction of the requested beaded braids.
- + Highly intricate and realistic metal engraving textures.
- + Accurate representation of the cloth underlayer and leather straps.
- − The 'faint scars' look more like surface dirt or smudges than actual skin texture.
- − Lighting feels a bit flat compared to the dramatic request.
DALL-E 3
- + Stronger lighting and atmosphere with a more dramatic 'torchlight' effect.
- + More defined 'battle-worn' appearance with deep scars.
- + Excellent shallow depth of field and bokeh.
- − Missed the 'braids with small beads' requirement in the hair.
- − Skin texture feels slightly over-sharpened or hyper-digital in certain areas.
Verdict: Bria FIBO followed the technical prompt more accurately by including the specific beaded braids and better cloth/leather detailing. However, DALL-E 3 captured the dramatic lighting and battle-worn scars much more effectively, even though it ignored the specific hairstyle requested. Bria FIBO is preferred for its superior adherence to the specific character description and realistic material rendering.
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.”
Bria FIBO
DALL-E 3
AI Judge Analysis
Bria FIBO
- + Strong typography with bold, clear headers that are easily legible.
- + Effective use of vibrant accent colors to separate sections.
- + Excellent layout that balances photos and text in a professional grid.
- − The food photos are repetitive and somewhat abstract rather than distinct menu items.
- − Contains gibberish text in the smaller body copy.
DALL-E 3
- + Provides multiple variations of a square-format menu design.
- + High-quality, distinct food photography including clear pizzas and salads.
- + Sophisticated use of negative space and clean color blocking.
- − The typography is less readable and appears more as decorative symbols than words.
- − Small text is completely illegible even at a distance.
- − Shows four separate variations rather than one clear, high-resolution design.
Verdict: Bria FIBO produces a superior layout that feels like a finished professional graphic design, featuring strong bold headers and a clean vertical structure. While DALL-E 3 offers much higher quality and more realistic food photography, its failure to generate legible text or a single focused design makes Bria FIBO the more useful output for a menu design task.
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.”
Bria FIBO
DALL-E 3
AI Judge Analysis
Bria FIBO
- + Excellent photorealistic texture on the burger patty and fresh vegetables
- + Perfect adherence to the fiery glowing text requirement for all requested strings
- + Strong dynamic composition that feels like a professional food advertisement
- − The '€' symbol is missing from the 6.99 price tag
- − Secondary text 'LIMITED TIME ONLY' is slightly plain compared to the main title
DALL-E 3
- + Creative use of a central impact crater to emphasize the 'exploded' motion
- + Includes all requested symbols including the '€' sign and starburst element
- + Highly imaginative lighting with blue and orange contrast
- − Spelling errors in text: 'BURGR' instead of 'BURGER' and 'Limiited' instead of 'Limited'
- − The food components look more like CGI/illustrations than photorealistic food photography
- − The cheese and pickles look slightly artificial or plasticky
Verdict: Bria FIBO is the clear winner as it produces a professional, photorealistic advertisement with correct spelling and high-quality food textures. While DALL-E 3 captures the 'exploded' concept with more creative debris, its failure to spell the primary title ('BURGR') and secondary message correctly makes it unusable for its intended purpose.
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.”
Bria FIBO
DALL-E 3
AI Judge Analysis
Bria FIBO
- + Natural-looking chalk texture on the individual letters.
- + Authentic blackboard smudge and erased texture in the background.
- + Simple and realistic café-style composition.
- − Very poor text accuracy with many misspellings and gibberish words.
- − Incorrect date (April 3 instead of April 30).
- − Failed to render most of the specific menu items requested.
DALL-E 3
- + Excellent visual composition with warm lighting and decorative flourishes.
- + Better spelling of the requested menu items, including 'Truffle Mushroom' and 'Grilled Octopus'.
- + High level of detail and artistic flair.
- − Text layout is cluttered and contains many hallucinations like '$234'.
- − Used several font-like styles rather than a single consistent handwriting style.
- − Misspelled several words like 'Occtus' and 'Cokies'.
Verdict: DALL-E 3 is the clear winner as it successfully rendered several portions of the complex prompt text, including the specific date and most of the menu items. While Bria FIBO captured a more authentic 'messy' chalk texture, its inability to spell nearly any of the words correctly makes it much less useful than DALL-E 3's more coherent, albeit still imperfect, output.
The Reversed Rodeo
Text-to-Image“Horse riding astronaut in space — horse on top, not vice versa. Surreal, highly detailed, cinematic.”
Bria FIBO
DALL-E 3
AI Judge Analysis
Bria FIBO
- + Excellent detail on the horse's coat and equipment.
- + Creative use of neon/light elements for the reins and hooves.
- + Sharp, cinematic lighting and vibrant color palette.
- − Failed the specific spatial orientation constraint ('horse on top, not vice versa').
DALL-E 3
- + Atmospheric composition with clouds and a vast starfield.
- + Clean silhouette and perspective.
- + Accurate astronaut suit details.
- − Failed the specific spatial orientation constraint ('horse on top, not vice versa').
- − The horse's anatomical rendering is slightly simplified compared to Image A.
Verdict: Both models failed the negative/compositional constraint to have the 'horse on top' of the astronaut, instead providing a standard 'astronaut riding horse' image. Bria FIBO is the preferred choice as it offers significantly higher detail, better textures, and more creative sci-fi aesthetics through the glowing hooves and reins.
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.”
Bria FIBO
DALL-E 3
AI Judge Analysis
Bria FIBO
- + Excellent adherence to the inclusion of the businesswoman in the backseat.
- + Very high level of photorealism and skin/fur textures.
- + Well-composed scene showing both the driver and the passenger as requested.
- − The taxi door geometry seems warped or impossible in the top left corner.
- − The capybara's 'hands' are a bit humanoid and unsettling.
DALL-E 3
- + Beautiful lighting and cinematic atmosphere.
- + Clean rendering of the taxi's dashboard and steering wheel.
- − Completely failed to include the human businesswoman sitting in the back seat.
- − The capybara's hat is black instead of the requested yellow.
- − The background text 'CAPYBARA' on a building is a bit too literal/on-the-nose.
Verdict: Bria FIBO is the clear winner as it fulfilled the complex requirements of the prompt, specifically including the businesswoman passenger which DALL-E 3 completely omitted. While DALL-E 3 has nice lighting, it failed on multiple prompt adherence points including the passenger and the hat color.
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.”
Bria FIBO
DALL-E 3
AI Judge Analysis
Bria FIBO
- + Strong clear typography for the title and banner
- + Excellent cinematic lighting on the jack-o-lantern
- + Composition feels balanced and readable for an invitation
- − Event details at the bottom are garbled and inaccurate (e.g., 'night of nights' and 'Lootion')
- − The border design is a bit simplistic compared to a 'vintage gothic' aesthetic
DALL-E 3
- + Ornate and intricate gothic frame and border elements
- + Captures the 'vintage gothic' mood very effectively with high detail
- + Creative use of 3D layered elements and textures
- − Failed significantly on text rendering, with most words being illegible or nonsensical
- − The jack-o-lantern is very small relative to the composition
- − Does not follow the specific text instructions for the banner or location
Verdict: Bria FIBO is much more functional as an invitation because its primary title text is legible and follows the prompt's instructions, despite struggling with the smaller event details. DALL-E 3 creates a much more atmospheric and artistically detailed gothic scene, but it fails completely at the text-rendering requirements of the prompt.
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.”
Bria FIBO
DALL-E 3
AI Judge Analysis
Bria FIBO
- + Excellent typography rendering with the requested 'JAPAN' and 'SUSHI' text
- + High visual clarity and realistic PBR texture on the fish and rice
- + Accurate 45-degree isometric projection and clean solid background
- − Includes small artifact text and icons in the bottom corners
- − The diorama base is a bit plain compared to the subject
DALL-E 3
- + Great 'miniature cartoon' aesthetic with soft, rounded 3D shapes
- + Very clean composition with no peripheral artifacts
- + Creative integration of the flag as a physical topper
- − Completely failed the text placement requirement ('JAPAN' is at the bottom, 'SUSHI' is missing)
- − The sushi anatomy is more abstract and less recognizable as a standard dish
Verdict: Bria FIBO followed the text instructions perfectly, placing the correct words in the requested top-center position with a clean font. While DALL-E 3 captured the 'cartoon miniature' aesthetic more vibrantly, its failure to include the word 'SUSHI' and its displacement of 'JAPAN' makes Bria FIBO the 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.”
Bria FIBO
DALL-E 3
100% wins
0% ties
0% wins
AI Judge Analysis
Bria FIBO
- + Successfully includes all four requested animal species clearly.
- + Dynamic composition with animals jumping and interacting.
- + Vibrant lighting with clear god rays and a lush meadow environment.
- − Anatomy on the fox kit is slightly awkward, specifically the paw placement.
- − Has a slightly generic 'AI stock photo' aesthetic.
DALL-E 3
- + Excellent fur texture and extremely expressive, 'big' eyes as requested.
- + Stronger implementation of god rays and warm sunrise lighting.
- + High level of artistic charm and whimsical mood.
- − Includes bizarre 'butterfly-bird' hybrids with furry bodies and beaked heads.
- − The kitten is very small and lacks distinct tabby markings compared to Model A.
- − Less 'hyper-photorealistic' and more '3D animated movie' style.
Verdict: Bria FIBO followed the specific list of animals more accurately and provided a more dynamic scene, whereas DALL-E 3 took liberties with the butterfly anatomy, creating strange hybrid creatures. While DALL-E 3 has superior lighting and fur rendering, Bria FIBO is the preferred choice for adhering to the prompt's count and species requirements without bizarre artifacts.
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.”
Bria FIBO
DALL-E 3
AI Judge Analysis
Bria FIBO
- + Clean vector-style execution
- + Accurate representation of a cloche dome
- + Adheres to the color palette requested
- − Significant spelling errors in the main name
- − Incorrect date 'Est. 1320' contrary to the prompt
- − Cloche appears transparent rather than metallic
DALL-E 3
- + Excellent vintage texture and artistic style
- + Correct date 'Est. 1720'
- + Highly sophisticated typography and spacing
- − Failed to include the specific name 'Caffè Florian'
- − More complex than 'minimalist' request
- − Steam is stylized as swirls rather than subtle vapours
Verdict: Bria FIBO followed the vector logo style well but failed significantly on text accuracy and the specific date requested. DALL-E 3 produced a much more visually appealing and professional vintage brand identity with the correct date, although it hallucinated the text as 'Coffee House' instead of the requested name. DALL-E 3 is the preferred choice for its superior aesthetic quality and adherence to the date constraint.
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.”
Bria FIBO
DALL-E 3
AI Judge Analysis
Bria FIBO
- + Excellent adherence to the modern vector infographic style with clean, flat illustrations.
- + Accurately represents the specific steps requested, such as the translunar arc and the lunar lander icons.
- + Uses the requested NASA-inspired color palette effectively and builds a cohesive layout.
- − Text consists entirely of gibberish characters.
- − The Earth icon has some slight perspective inconsistency with the rings.
DALL-E 3
- + Very stylistic and artistic interpretation with high visual density.
- + Contains semi-legible English text for the title 'Apollo 11'.
- + Captures the muted vintage color scheme well.
- − Failed the request for a single poster, providing a three-panel triptych instead.
- − Does not follow the 6-step logical flow requested in the prompt.
- − Contains repetitive icons (many moons) that do not represent specific mission phases clearly.
Verdict: Bria FIBO followed the detailed structural requirements of the prompt much better than DALL-E 3, providing a clear 6-step sequence with the specific icons requested in a clean infographic layout. DALL-E 3 produced a more artistic and complex visual, but it ignored the layout instructions and failed to logically map out the mission steps as requested.
Next steps
Explore each model
OpenAI's previous generation image model with higher quality than DALL-E 2 and support for larger resolutions