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
GPT Image 1.5
#7 of 62 in Text-to-Image
Where the votes landed
Bria FIBO
0%
win rate
Ties
0%
GPT Image 1.5
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 handling of glass refraction and light play.
- + Clean, modern aesthetic with sharp details.
- + Great adherence to lighting cues from the window.
- − The plant appears to be growing inside/through the cube rather than strictly behind it.
- − The blue sphere is floating, which might seem physically unnatural.
GPT Image 1.5
- + Successfully places the plant behind the cube as requested.
- + The sphere rests realistically on the bottom surface.
- + The glass cube has realistic thickness and internal reflections.
- − The lighting is a bit flat compared to Model A.
- − The glass edges and surface textures are slightly less crisp.
Verdict: Both models followed the prompt instructions accurately. Bria FIBO produced a more visually striking image with superior light refraction and a cleaner finish, though the plant's placement is ambiguous. GPT Image 1.5 adhered more strictly to the spatial arrangement of the plant being behind the glass, making it the more accurate interpretation of the scene's layout.
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
- + Striking cinematic lighting and reflections
- + High-quality skin texture and facial details
- − Physical logic errors with the bicycle including a single-sided fork and missing rear triangle
- − The man's hand is fused awkwardly with the handlebars
GPT Image 1.5
- + Strong adherence to the 'candid' and 'imperfect framing' prompt attributes
- + Realistic interaction between the man, the tools, and the bicycle mechanics
- + Natural environmental storytelling with the utility basket and tool tray
- − The passing car lacks the requested motion blur
- − The bicycle seat and rear fender have some minor structural clipping issues
Verdict: While Bria FIBO produces a beautiful, high-contrast cinematic image, it fails significantly on the structural anatomy of the bicycle and hand interactions. GPT Image 1.5 captures the 'candid street photo' aesthetic much more effectively with realistic posing, a logical mechanical scene, and better adherence to the mundane, unstylized realism requested.
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 intricate engraving on the plate armor
- + Clean composition with nice bokeh effects
- + Follows the beaded hair prompt with subtle pearls
- − The scars look like superficial surface marks rather than battle wounds
- − The lighting on the face feels a bit flat compared to the dramatic armor highlights
GPT Image 1.5
- + Superb realism in skin texture and 'battle-worn' scars
- + Strong adherence to the requested warm torchlight, creating rich highlights and shadows
- + Highly detailed leather straps and weathered cloth textures
- − The hair is somewhat messy, making the braids and beads harder to distinguish than in Model A
Verdict: While Bria FIBO produces a very clean and detailed armor set, GPT Image 1.5 wins due to its superior photographic realism and better interpretation of 'battle-worn'. GPT Image 1.5 better captures the grit, dramatic lighting, and weathered textures required by the prompt.
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
- + Strong geometric layout with vibrant color accents
- + Effective use of white space for a modern aesthetic
- + Good adherence to the requested grid structure
- − Text is largely gibberish and unreadable
- − Food photography lacks realism and clarity
- − Composition feels cluttered and repetitive
GPT Image 1.5
- + Perfect text rendering with realistic menu items and pricing
- + High-quality, appetizing food photography
- + Clean, professional layout that accurately follows the prompt's sections
- − Layout is slightly more traditional than 'modern minimalist' grid
- − Small area of text overlapping at the very top
Verdict: GPT Image 1.5 is the clear winner as it produces a fully functional menu with legible text, realistic food imagery, and a clean professional layout. Bria FIBO captures the 'vibrant accents' well, but fails completely on text quality and image coherence, making it unusable as a design mockup.
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
- + Clean and modern typographic layout with a strong glowing text effect
- + High clarity and realistic textures on the lettuce and tomatoes
- − Failed to include the currency symbol (€) requested
- − Missed the specific starburst container for the price
- − The secondary text is plain and lacks the requested fiery effect
GPT Image 1.5
- + Perfect adherence to all text requirements including the € symbol and starburst
- + Superior sense of dynamic motion through flying particles and embers
- + Intense, cinematic lighting that integrates the burger into the background
- − The 'LIMITED TIME ONLY' text is slightly less polished than the main title
- − High saturation may slightly obscure some fine texture details in the meat
Verdict: While Bria FIBO produces a very clean image with readable text, GPT Image 1.5 followed the prompt much more accurately, including specific details like the Euro symbol and the starburst element. GPT Image 1.5 also captured a much stronger sense of motion and 'magic' through the explosion of embers and atmospheric lighting.
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 texture and smudging on the chalkboard surface
- + Captures an authentic handheld chalkboard aesthetic
- − Failed significantly on prompt adherence for text content
- − Text is mostly gibberish or misspelled beyond the title
- − Missed several specific menu items and prices requested
GPT Image 1.5
- + Perfect prompt adherence with accurate spelling for all requested text
- + Impressive chalk handwriting style that looks natural yet legible
- + Successfully interpreted the truncated 'Brown But...' prompt to 'Brown Butter Chocolate Chip Cookies'
- − Text is very clean, appearing slightly closer to a digital brush than physical chalk
- − The composition is a bit centered and sterile
Verdict: GPT Image 1.5 is the clear winner as it followed all complex text instructions perfectly, including the specific date, items, and prices, whereas Bria FIBO produced mostly illegible text. GPT Image 1.5 also intuitively completed the truncated menu item 'Brown But...' into a logical dessert option, demonstrating superior prompt understanding.
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
- + Vibrant, colorful space nebula effects
- + Creative interpretation with glowing hooves and reins
- + Clean, high-quality digital art style
- − Failed the primary logic prompt: the astronaut is on top of the horse
- − The horse's front leg lacks a clear anatomical joint
GPT Image 1.5
- + Excellent surface detail on the moon and space suit
- + High cinematic quality with realistic lighting
- + Dynamic composition with a sense of motion
- − Failed the primary logic prompt: the astronaut is on top of the horse
- − The scale of Saturn in the background is overly stylized compared to the moon surface
Verdict: Both Bria FIBO and GPT Image 1.5 failed the negative constraint to put the horse on top of the astronaut, instead providing the more common image of an astronaut riding a horse. GPT Image 1.5 is the preferred image due to its superior cinematic realism, detailed textures, and more complex background composition compared to the more simplistic digital art style of Bria FIBO.
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 city light reflections on windows
- + Creative inclusion of capybara's legs in the driver's seat
- + High level of texture detail in the capybara's fur
- − The driver's paws/hands look more like primate hands than capybara paws
- − Anatomical issues with the human passenger's hands and eyes
GPT Image 1.5
- + Paws look more consistent with a rodent/capybara
- + Excellent facial expression on the passenger matching the 'bored' requirement
- + Stronger composition that feels more cinematic and professionally framed
- − The capybara's right eye is slightly misaligned
- − Taxi cap text is slightly distorted
Verdict: GPT Image 1.5 is the winner as it perfectly captures the bored expression of the human passenger, which is a key narrative element of the prompt. While Bria FIBO has impressive environmental lighting, its human figure is poorly rendered and the capybara's hands are unsettlingly humanoid.
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 webs and thorns in the border
- + Good contrast on the central jack-o-lantern
- − Significant text hallucinations and spelling errors in the event details
- − The banner text says 'night of nights' instead of requested 'night of frights'
- − Composition feels slightly disjointed with text floating haphazardly
GPT Image 1.5
- + Excellent text rendering with near-perfect spelling for all requested details
- + Highly cohesive vintage gothic aesthetic with a warm, moody color palette
- + Superior border detail with intricate thorns and cobwebs
- − The jack-o-lantern's glow bleeds a bit heavily into the surrounding textures
Verdict: GPT Image 1.5 is the clear winner as it successfully rendered all requested text details with perfect accuracy, whereas Bria FIBO suffered from significant spelling errors and hallucinations in the fine print. GPT Image 1.5 also provided a much more polished and immersive 'vintage gothic' aesthetic that perfectly matches the cinematic lighting and parchment texture requested.
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 head of hair with stylized texture.
- + Maintained the general theme of the desert environment.
- − Completely replaced the identity of the person, changing facial features and bone structure.
- − Significantly altered the background, clothing, and overall lighting of the original image.
- − Failed at the source preservation requirement.
GPT Image 1.5
- + Excellent source preservation, keeping the original face, clothing, and background intact.
- + The hair texture perfectly matches the existing beard texture for a natural look.
- + Maintained the original lighting and image quality.
- − The hairline transition on the forehead is slightly abrupt, though realistic enough.
Verdict: GPT Image 1.5 performed a near-perfect edit by seamlessly adding hair that matches the subject's existing beard while preserving every other detail of the source image. Bria FIBO failed the specific task of editing, instead generating a completely new image of a different person that only vaguely resembles the original composition.
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 alignment and cleanliness
- + Perfectly smooth, refined 'cartoon 3D' texture aesthetic
- + Adheres strictly to the requested light blue background and minimal garnish
- − Includes undesirable watermark-like icons in the bottom corners
- − Isometric angle is slightly flatter than 45 degrees
GPT Image 1.5
- + Rich, realistic PBR materials with high-quality textures on wood and ceramics
- + Perfect isometric composition on a clear diorama base
- + Excellent text rendering and flag icon placement
- − Slightly more objects than 'minimal garnish' implies
- − Mild repetitive patterns visually in the sushi rice
Verdict: Both models followed the complex prompt very well, but GPT Image 1.5 delivered a more professional and visually interesting diorama without the distracting watermarks found in Bria FIBO's output. While Bria FIBO achieved a smoother 'cartoon' look, GPT Image 1.5's superior material rendering and perfect 45-degree perspective make it the more compelling image.
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
- + Strongly exaggerates facial features for a classic caricature style.
- + Includes a clear news anchor setting and a dog.
- + Humorous, vibrant color palette.
- − Completely fails to include the hockey element requested.
- − The subject's face loses almost all resemblance to the source image.
- − Messy composition with floating objects and artifacts in the background.
GPT Image 1.5
- + Incorporates all requested elements: tv anchor, dogs, and hockey.
- + Maintains a much better likeness to the woman in the source image while still being a caricature.
- + High visual quality with legible text and a cohesive theme.
- − The hockey player in the background has slightly distorted proportions.
- − The hair volume is very large, though this fits the caricature style.
Verdict: GPT Image 1.5 is the clear winner as it successfully incorporated every element of the prompt, including the hockey reference which Bria FIBO missed entirely. Furthermore, GPT Image 1.5 maintained the subject's identity from the source image much more effectively while still delivering a fun, polished caricature.
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 animal types.
- + Vibrant colors and clear, sharp details on the butterflies.
- + Good use of compositional depth with the animals spread across the meadow.
- − The fox kit's leg anatomy appears slightly distorted and floating.
- − The lighting feels more like a digital painting than hyper-photorealistic.
- − The eyes of the animals look slightly flat and lacks realistic depth.
GPT Image 1.5
- + Excellent realization of 'god rays' and sparkling dew as requested in the prompt.
- + The 'tumbling together' action is much more natural and expressive than in Image A.
- + High level of fur detail and realistic lighting integration.
- − The fox kit has three ears, which is a significant anatomical error.
- − The rabbit is partially merged into the kitten and fox, losing its distinct silhouette.
Verdict: Both models followed the complex prompt well, but GPT Image 1.5 captured the atmospheric elements—like god rays and dew sparkles—with much higher fidelity and a more realistic photographic feel. Although GPT Image 1.5 suffered from a notable anatomical glitch (three ears on the fox), its superior composition and portrayal of the 'tumbling' interaction make it a more joyful and visually compelling masterpiece compared to the flatter, more static interpretation of Bria FIBO.
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 a dreamy, floral background typical of Ghibli-inspired art.
- + Maintains clean character lines and consistent color palettes for the outfits.
- − Loses the core composition of the 'Distracted Boyfriend' meme by having all characters walk forward.
- − Changes the man's pose and expression so he is no longer looking back in a recognizable way.
GPT Image 1.5
- + Excellent preservation of the original image's composition, poses, and expressions.
- + Perfectly captures the hand-painted, soft gouache texture requested in the prompt.
- + Maintains the specific depth of field from the source image.
- − The man's right hand has slight anatomical oddities.
- − The lighting is perhaps a bit too hazy, masking some fine facial details.
Verdict: GPT Image 1.5 is the clear winner as it successfully translates the famous 'Distracted Boyfriend' meme into the requested style while keeping the iconic pose and composition perfectly intact. Bria FIBO fails as an edit because it reinterprets the scene into a generic group walk, losing the specific dynamic that makes the source image recognizable.
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
- + Excellent depiction of dynamic movement, changing the pose of the woman and dog into a trot.
- + Successfully rendered wind-blown hair with high height and energy.
- + Dramatic use of autumn leaves to frame the shot.
- − Low source preservation as it completely regenerates the background, woman's face, and overall color grading.
- − The dog's leash is broken and floating in the air.
GPT Image 1.5
- + Perfectly preserves the woman's face, the dog, and the background from the source image.
- + Effectively adds blowing hair and leaves while maintaining the original lighting and composition.
- + Maintains the structural integrity of objects like the leash and harness.
- − The wind effects look slightly more like a static layer on top of a still photo rather than a captured moment of action.
- − The hair rendering is slightly less realistic compared to the original hair texture.
Verdict: Bria FIBO captures the 'energetic and lively' instruction better by changing the posture of the subjects to a run, but it fails significantly as an image editor by completely ignoring the source image's specific details and facial features. GPT Image 1.5 is the superior editor here, as it seamlessly integrates the requested wind and leaf effects while keeping the woman, the dog, and the environment exactly as they were in the original photo.
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 (warm brown and cream) on a light background
- − Failed significantly on text spelling for 'Florian'
- − Generated the wrong establishment date ('1320' instead of '1720')
- − Steam effect is faint and poorly integrated
GPT Image 1.5
- + Perfect text rendering for both the name and the date
- + Stronger retro/vintage aesthetic with nice grit texture
- + Excellent composition and balance of elements
- − Failed the 'light background' prompt requirement by using a black background
- − The cloche is a bit dark, making some detail hard to see
Verdict: GPT Image 1.5 is the clear winner because it correctly rendered all written text, including the specific name 'Caffè Florian' and the correct establishment date. While it missed the request for a light background, Bria FIBO's failure to spell the primary brand name and historical date makes it unusable for a logo project.
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
- + Features a more unified poster layout with a path-based infographic style.
- + Captures the clean vector aesthetic and subtle transitions well.
- − Text is entirely illegible gibberish.
- − The iconography is messy and does not clearly represent the specific steps requested in the prompt.
- − The layout is confusing and lacks a logical flow for the mission steps.
GPT Image 1.5
- + Excellent typography with perfectly legible text for all categories.
- + Strong adherence to the requested sequence, clearly illustrating each of the six requested steps.
- + Very clean vector style with a consistent color palette and distinct icons.
- − The layout is more of a grid of tiles than a single cohesive 'infographic poster' composition.
Verdict: GPT Image 1.5 is the clear winner as it successfully rendered all six mission steps with legible labels and accurate iconography. Bria FIBO failed significantly on text rendering and did not provide a clear visual narrative for the steps of the Apollo 11 mission.
Explore each model
OpenAI's state-of-the-art image generation model with better instruction following and adherence to prompts