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
FLUX.1 [schnell]
#48 of 62 in Text-to-Image
Where the votes landed
Bria FIBO
0%
win rate
Ties
0%
FLUX.1 [schnell]
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 spatial relationships in the prompt
- + High-quality glass refraction showing the plant through the cube
- + Realistic soft lighting and shadows
- − The blue sphere appears slightly flattened horizontally instead of being perfectly spherical
- − Small artifact/distortion on the right edge of the glass cube
FLUX.1 [schnell]
- + Impressive realistic plant textures and lighting
- + Very clear and sharp glass edges
- − Failed the spatial prompt by placing an extra blue sphere on top of the book
- − The plant does not look like it is behind the cube but rather offset to the side
- − The large sphere inside the cube is massive rather than 'small' as requested
Verdict: Bria FIBO followed all prompt instructions perfectly, including the placement of objects and the visibility of the plant through the glass. FLUX.1 [schnell] struggled with the prompt's logic, adding a second sphere on top of the book and failing to properly place the plant behind the glass cube.
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 depiction of rainy textures and reflections on the pavement.
- + Captures a strong cinematic, shallow depth of field feel.
- + The facial expression and skin texture appear more natural and detailed.
- − The bicycle anatomy is physically impossible, with a pedal detached from the frame and floating in space.
- − The hand interaction with the handle bars is anatomically garbled.
- − The composition is very centered, missing the 'imperfect framing' request.
FLUX.1 [schnell]
- + Successfully includes the motion blur from cars requested in the prompt.
- + The 'imperfect framing' is better represented by the off-center subject and street layout.
- + The bicycle structure is significantly more coherent and realistic than the competitor.
- − The skin texture appears slightly smoothed or 'plastic' compared to the other model.
- − The transition between the man's hands and the handlebars is blurry and lacks detail.
- − The car in the background looks slightly distorted.
Verdict: FLUX.1 [schnell] is the winner because it successfully incorporates almost all prompt elements, including motion blur and imperfect framing, while maintaining a functional bicycle structure. Bria FIBO produces a beautiful atmosphere but suffers from catastrophic failures in object logic, such as a floating pedal and malformed hands.
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 engraving details on the plate armor
- + Accurately represents the braided hair with beads as requested
- + Strong sense of cinematic scale and composition
- − The scars and dirt look somewhat like surface stamps rather than integrated skin texture
- − The lighting on the face is a bit flat compared to the armor
FLUX.1 [schnell]
- + Extreme facial detail and realistic skin texture
- + Intense, lifelike eye rendering
- + Strong implementation of warm lighting and shallow depth of field
- − Missed the request for hair beads
- − The armor is mostly out of frame and lacks the 'ornate engraved' prominence requested
- − Composition is an extreme close-up that sacrifices the armor and clothing details
Verdict: Bria FIBO followed the prompt instructions more comprehensively, particularly with the ornate armor and hair beads. While FLUX.1 [schnell] produced a more striking and realistic face, it failed on several specific prompt details and cropped the image too tightly to see the requested leather and cloth 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
- + Excellent use of vibrant secondary colors and accents as requested
- + High-quality, appetizing food photography
- + Strongly adheres to the grid layout requirement
- − Text is largely gibberish and poorly rendered
- − The layout is a bit cluttered for a 'minimalist' prompt
FLUX.1 [schnell]
- + Superior text legibility for headers
- + Clean, minimalist aesthetic that fits the prompt's 'professional' requirement
- + Provides a realistic white space balance for a modern design
- − Food photos are less vibrant and somewhat repetitive
- − The small body text is still muddy and illegible
Verdict: FLUX.1 [schnell] captures the 'minimalist' and 'professional' aspect of the prompt much better, offering a clean layout with legible headers. While Bria FIBO has more vibrant food photography, its layout is overly busy and the text rendering is significantly lower quality than FLUX.1 [schnell].
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 the 'exploded' layout showing all layers clearly.
- + High-quality rendering of food textures like the sesame bun and juicy tomatoes.
- + Integrated text with a consistent fiery glow effect that matches the prompt.
- − Missing the Euro symbol (€) in the price starburst.
- − The starburst effect behind the price is somewhat messy and blends into the background sparks.
FLUX.1 [schnell]
- + Dynamic composition with smaller floating pieces adding to the 'exploded' feel.
- + Included a clear starburst graphic for the price.
- + Sharp, clean lighting on the burger patty and cheese.
- − Failed to render the main title correctly, spelling it 'AGIC BURGER'.
- − The burger is largely assembled rather than a deconstructed 'exploded' view of all components.
- − The price text is redundant and includes an error (€699) inside the starburst.
Verdict: Bria FIBO followed the layout instructions much better, providing a clear deconstructed view of the burger with professional-looking text integration. While FLUX.1 [schnell] had interesting smaller debris, it failed on basic text rendering and did not accurately represent an 'exploded' burger with visible suspended layers.
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 with grainy details
- + Consistent handwriting slant and style across the entire board
- − Text is highly garbled and unreadable beyond the header
- − Failed to include the specific date of April 30, only rendering April 3
FLUX.1 [schnell]
- + Text is significantly more legible than the competitor's
- + Included the full date and mostly accurate numbers for the prices
- − Chalk texture looks a bit too clean and digital compared to actual chalk
- − Writing lacks the 'elegant cursive' style requested for the title
Verdict: While Bria FIBO captures the aesthetic of real chalk texture and natural handwriting variations much better, it fails completely at text rendering and prompt adherence regarding content. FLUX.1 [schnell] is much more successful at rendering readable words and following the specific date and price details in the prompt, despite having a slightly flatter visual style.
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 visual clarity and vibrant colors.
- + Creative use of glowing elements like the hooves and reins.
- + High cinematic quality with a balanced background composition.
- − Completely failed the semantic prompt to have the horse on top of the astronaut.
FLUX.1 [schnell]
- + Successfully followed the difficult spatial instruction of 'horse on top'.
- + Unique and surreal interpretation of the prompt.
- + Consistent lighting between the horse and the astronaut against the planet backdrop.
- − Anatomical errors with the horse having two heads/torsos merged together.
- − The astronaut's posture is awkward and lacks clear definition.
Verdict: Bria FIBO produced a much more visually polished and beautiful image, but it failed the primary challenge of the prompt by placing the astronaut on the horse. FLUX.1 [schnell] followed the spatial instructions perfectly, but suffered from significant anatomical artifacts like the two-headed horse, making it a tie between aesthetic quality and prompt adherence.
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 full-body composition that shows the entire taxi interior layout.
- + The capybara's professional pose and 'hands' on the wheel are very well-executed.
- + High level of detail in the background city lights and interior car textures.
- − The passenger's hands and phone interaction are slightly distorted.
- − The yellow hat looks more like a formal chauffeur cap than a standard taxi driver cap.
FLUX.1 [schnell]
- + Natural composition with a more modern 'TAXI' branded cap.
- + The passenger's expression and interaction with the phone are very realistic.
- + Strong adherence to the 'bored' expression prompt for the human character.
- − The capybara only has one paw near the wheel, and it isn't actually gripping it.
- − The capybara's face looks slightly more like a bear/groundhog hybrid than a distinct capybara.
- − The 'TAXI' text on the sun visor is garbled.
Verdict: Bria FIBO is the winner for its superior adherence to the physical requirements of the prompt, successfully placing both of the capybara's paws on the steering wheel while maintaining a professional profile. While FLUX.1 [schnell] captures a better 'normal' expression for the passenger, it fails on the specific paw placement and has significant text artifacts in the background.
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 photographic realism in the jack-o-lantern and backdrop
- + The parchment paper texture and border elements are very high quality
- + Effective cinematic lighting and atmosphere
- − The text at the bottom is largely garbled and nonsensical
- − Incorrect date and time formatting in the bottom text
- − Misspelled 'frights' as 'nights' on the banner
FLUX.1 [schnell]
- + Closer adherence to the requested event details including the correct date and location
- + Graphic design layout is clean and easy to read
- + Includes the thorn border as requested
- − The text contains several stuttered repetitions like 'a a night' and 'Time: Tive'
- − The art style is a bit more 2D/flat compared to the cinematic request
- − The 'Halloween' title is split across two lines/elements awkwardly
Verdict: While Bria FIBO creates a much more visually stunning and atmospheric image with high-quality textures, its inability to render the specific event text makes it a poor invitation. FLUX.1 [schnell] captures almost all of the textual data correctly (date, location, time), though the aesthetic is more of a digital illustration than the cinematic parchment requested. FLUX.1 [schnell] is the winner for better overall prompt adherence regarding the specific informational requirements.
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 adherence to lighting and PBR material requests
- + Accurately rendered both 'JAPAN' and 'SUSHI' text
- + High variety of 3D sushi models with great texture
- − Includes stray UI-like artifacts in the bottom corners
- − The 'JAPAN' text is slightly off-center compared to the sushi plate
FLUX.1 [schnell]
- + Perfectly centered and clean composition
- + Minimalist aesthetic fits the 'diorama' and 'cartoon scene' prompt well
- − Failed to include the word 'SUSHI' in the text
- − The sushi roll/nigiri hybrid looks slightly anatomically incorrect
- − The lighting and materials feel flatter compared to Model A
Verdict: Bria FIBO followed the text prompts much more effectively, rendering all requested words and providing a rich variety of sushi textures that feel like high-quality 3D assets. While FLUX.1 [schnell] produced a very clean and centered image, it missed a key text element and the sushi model itself was less impressive than the collection in Bria FIBO.
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 adherence to the list of animals requested
- + Strong sense of motion and 'tumbling' as requested in the prompt
- + Vibrant colors and clear god rays in the top-left
- − The fox's anatomy is slightly distorted in its midsection
- − The butterfly on the bottom right appears merged with the bunny
FLUX.1 [schnell]
- + High quality textures and lighting on the animals' fur
- + Clean composition with a beautiful bokeh effect
- + Soft, professional photography aesthetic
- − Failed to include a rabbit, providing a second cat-like creature instead
- − The animals are sitting relatively still rather than chasing or tumbling
Verdict: Bria FIBO followed the complex prompt more accurately by including all four distinct animal types and depicting them in active, playful motion. While FLUX.1 [schnell] produced a more aesthetically pleasing and high-quality image with softer lighting, it failed on prompt adherence by omitting the baby bunny and showing static poses.
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
- + Successfully included the steam effect inside the cloche as requested.
- + Clean lines and a balanced vector-style layout.
- + The cloche dome is clearly recognizable and well-rendered.
- − Significant spelling errors in the brand name ('Caffé Froaian') and date ('1320').
- − The accent mark on 'Caffè' is oriented incorrectly and stylized strangely.
FLUX.1 [schnell]
- + Professional vector emblem composition with a cohesive circular frame.
- + High visual quality and a very clean minimalist aesthetic.
- + Typography is sharp and well-integrated into the design.
- − Failed to include the requested steam effect.
- − Incorrect spelling of both the name ('Framilan') and the date ('7720').
- − The cloche dome looks more like a hard hat or helmet than a food dome.
Verdict: Both models struggled significantly with the text requirements, particularly the brand name and the specific date. Bria FIBO followed the prompt instructions more closely by including the 'steam' inside the dome, whereas FLUX.1 [schnell] produced a more polished and professional-looking vector emblem that missed the steam and changed the year to 7720.
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 color palette and flat-vector style.
- + Clear, high-quality iconography for the Earth, Moon, and spacecraft.
- + Well-structured poster layout that looks like a high-end infographic design.
- − The sequence of steps is somewhat jumbled and doesn't follow a clear 1-6 numerical linear path.
- − Nonsense text throughout the layout.
FLUX.1 [schnell]
- + Slightly better text legibility including identifiable words like 'STEPS' and 'LANDING'.
- + Simple, focused composition that is easy to read at a glance.
- − Misses several required icons like the specific Saturn V and landing module.
- − The central graphic of the rocket is messy with overlapping parts and poor anatomy.
- − Does not effectively visualize the requested 6-step trajectory.
Verdict: Bria FIBO produces a much more professional-looking infographic that perfectly captures the requested NASA aesthetic and vector style, even though the text is gibberish. FLUX.1 [schnell] creates a simpler layout with slightly more readable words, but fails significantly on the technical execution of the spacecraft and the specific step-by-step icons requested.
Explore each model
Black Forest Labs' 12 billion parameter distilled image generation model optimized for speed, capable of generating high-quality images in just 4 inference steps