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
FLUX.2 [dev] Flash
#5 of 62 in Text-to-Image
Where the votes landed
Bria FIBO
0%
win rate
Ties
0%
FLUX.2 [dev] Flash
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 photographic quality and sharp focus
- + Correct placement of all objects according to the prompt
- + Beautiful lighting and clean glass reflections
- − The sphere appears more like a matte ball than a marble
- − The plant looks somewhat artificial and illustrative compared to the background
FLUX.2 [dev] Flash
- + Very realistic, believable materials and textures
- + The sphere looks like genuine blue glass
- + Natural plant integration with a depth of field effect
- − The blue sphere is quite small relative to the cube
- − Minor distortion on the left edge of the glass cube
Verdict: Both models followed the complex spatial instructions perfectly. Bria FIBO produced a very clean, high-impact image with a large, centered sphere, while FLUX.2 [dev] Flash reached a higher level of photographic realism with more natural textures and lighting. FLUX.2 is slightly preferred for its realistic depiction of glass and the plant's placement.
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
- + Features vibrant red reflections on the wet pavement that enhance the cinematic mood.
- + Good use of shallow depth of field to isolate the subject from the background.
- − Anatomical errors in the hands, particularly the right hand which blends into the bicycle frame.
- − The bicycle geometry is nonsensical, with no visible seat post connected to the frame and a floating pedal.
FLUX.2 [dev] Flash
- + Excellent adherence to the 'motion blur from passing cars' prompt, creating a dynamic background.
- + Superior realism in the man's face and hands, showing detailed skin texture and believable tool usage.
- + The bicycle feels like a real, functional object with scattered parts on the ground adding to the narrative.
- − The transition between the man's right leg and the bicycle kickstand area is slightly cluttered and visually confusing.
Verdict: FLUX.2 [dev] Flash significantly outperformed Bria FIBO by accurately capturing the requested motion blur and providing a much more coherent and realistic depiction of the bicycle and the man's anatomy. While Bria FIBO captured the lighting and color well, the severe structural issues with the bicycle and the distorted hands made the image feel less realistic.
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 rendering of ornate engraved plate armor with high-contrast metallic highlights.
- + Warm, dramatic lighting that closely follows the torchlight requirement.
- + Very detailed skin texture and subtle scars that feel realistic.
- − The hair beads are less distinct and numerous than requested.
- − Some lighting artifacts around the ear and hair transitions.
FLUX.2 [dev] Flash
- + Perfect adherence to the hair braids with small beads requirement, showing colorful variety.
- + Outstanding texture on leather straps, buckles, and the cloth underlayer.
- + Balanced composition with clear bokeh sparks and visible torch light sources.
- − The lighting on the face feels a bit flat compared to the dramatic armor highlights.
- − The scars appear more like fresh bloody cuts rather than 'faint scars'.
Verdict: Both models performed exceptionally well on this complex prompt. Bria FIBO captures a more dramatic, cinematic atmosphere with superior metallic reflections and skin lighting, while FLUX.2 [dev] Flash excels in technical prompt adherence, particularly regarding the specific textures of the leather and the intricate details of the beads in the hair. FLUX.2 [dev] Flash is slightly preferred for its comprehensive inclusion of every requested detail, including the cloth and strap 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 adherence to the 'grid' prompt for food photos
- + Modern and professional typographic hierarchy
- + Includes all requested sections (Appetizers, Pizza, Mains) clearly
- − Text consists entirely of gibberish characters
- − Image quality on the food photos is slightly painterly/abstract
FLUX.2 [dev] Flash
- + Higher realism in food photography
- + Includes price points which adds to the menu realism
- + Better rendering of Latin-based characters, though still misspelled
- − Layout is repetitive, showing only pizza regardless of the section title
- − Fails to create a diverse food photo grid
- − Confusing 'Appetizers' heading placed above pizza photos
Verdict: Bria FIBO followed the layout instructions more effectively, providing a distinct grid and correctly categorizing the menu sections for Appetizers, Pizza, and Mains with varied imagery. FLUX.2 [dev] Flash produced higher-quality individual images but failed on the content variety, displaying only pizzas for every section, which undermined the logical flow of a restaurant menu.
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 patty and vegetables
- + Vibrant, high-contrast colors and dynamic fire effect
- − Failed to include the Euro symbol (€) as requested
- − Text integration lacks the specific fiery 'starburst' shape for the price point
- − Missing the core secondary message glow effect on 'LIMITED TIME ONLY'
FLUX.2 [dev] Flash
- + Perfect adherence to all text requirements, including the Euro symbol and starburst shape
- + Strong sense of motion with sauce droplets and flying embers
- + Sophisticated fiery typography that blends perfectly with the background
- − The bottom bun looks slightly flat compared to the realism of Model A
- − Lighting on the burger is a bit more muted than the background intensity
Verdict: While Bria FIBO offers a more appetizing and slightly more detailed rendering of the burger itself, FLUX.2 [dev] Flash followed the complex prompt instructions much more accurately. FLUX.2 successfully included all requested text elements, the starburst graphic, and the specific currency symbol, making it the superior choice for an advertisement layout.
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
- + Natural chalk texture on the lettering
- + Captures the slant and variation requested in the prompt
- − Text is largely illegible gibberish
- − Incorrect date rendered as April 3 2026
- − Fails to render the specific menu items requested
FLUX.2 [dev] Flash
- + Flawless text rendering of the specific menu items requested
- + Accurate date and pricing as per the prompt
- + Excellent composition with realistic chalk smudges and café background
- − Layout is slightly cramped at the bottom
- − Handwriting is very consistent, bordering on a font-like appearance
Verdict: FLUX.2 [dev] Flash significantly outperformed Bria FIBO by accurately rendering all the specific text requested in the prompt, including complex dish names and the specific date. While Bria FIBO captured the 'messy' chalk texture well, the content of the text was illegible and failed to follow the prompt instructions.
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 lighting with glowing hooves and reins.
- + Highly detailed texture on the horse's coat and mane.
- + Strong cinematic and surreal atmosphere.
- − The horse's neck and chest anatomy appears slightly distorted and overly thick.
- − The galaxy in the background looks a bit flat and like a standard filter.
FLUX.2 [dev] Flash
- + Naturalistic and realistic rendering of the horse and astronaut equipment.
- + Dynamic pose suggesting movement through space.
- + Excellent lighting integration between the subjects and the planetary background.
- − The composition is a bit more conventional despite the surreal subject matter.
- − Less emphasis on 'surreal' elements compared to the artistic flair of Model A.
Verdict: Both models failed the negative constraint to put the horse on top of the astronaut, instead providing the standard astronaut-on-horse interpretation. FLUX.2 [dev] Flash is the likely winner due to its superior anatomical accuracy, better sense of scale with the planets, and more realistic space suit textures compared to Bria FIBO's more digital-art style.
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 interior lighting and color saturation typical of a New York night.
- + The capybara's fur texture and lighting are highly detailed and realistic.
- + Good depth of field showing a vibrant, rainy Manhattan streetscape.
- − The capybara's hands are rendered as primate-like or human-like fingers rather than capybara paws.
- − The businesswoman's face and hands are slightly distorted with uncanny valley artifacts.
FLUX.2 [dev] Flash
- + Captures the bored, mundane expression of the passenger perfectly.
- + More anatomically accurate capybara paws on the steering wheel.
- + Strong narrative composition from the front-on 'windshield' perspective.
- − Overall image texture is slightly soft and less 'crisp' than the competitor.
- − The interior details are a bit more generic compared to the first image.
Verdict: Both models followed the complex prompt very well. Bria FIBO produces a more visually striking image with superior lighting and sharp details, but fails on the anatomy of the capybara's hands. FLUX.2 [dev] Flash captures the specific 'bored' emotion of the human passenger much better and handles the capybara's features more realistically, making it the better conceptual match despite being slightly less sharp.
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
- + Strong atmospheric lighting with realistic smoke and texture
- + Follows the prompt for thorns and spiderwebs effectively
- − Text at the bottom is largely unintelligible and hallucinates dates
- − Scroll banner text says 'night of nights' instead of 'night of frights'
FLUX.2 [dev] Flash
- + Excellent text rendering with almost perfect adherence to the requested details
- + Cohesive gothic art style that feels like a polished illustration
- + Correctly captures all prompt elements including thorns, webs, and specific event info
- − Small amount of hallucinated text/symbols near the 'Time' section
- − Lighting on the pumpkin is slightly flatter compared to Image A
Verdict: FLUX.2 [dev] Flash is the clear winner because it successfully renders almost all of the specific text requested, including the date, time, and location accurately. While Bria FIBO has a very spooky and cinematic atmosphere, its inability to generate readable event details makes it unsuccessful as an invitation.
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
- + High visual quality and clear details
- + Creates a cohesive head of hair
- − Failed to preserve the subject's identity, completely changing his face and age
- − Regenerated the entire image, losing the background and jacket details from the source
FLUX.2 [dev] Flash
- + Excellent source preservation, keeping the face, clothing, and background identical
- + Perfectly maintains the lighting and texture of the original image
- + Followed the edit instruction while respecting the original subject
- − The afro hair texture looks slightly pasted on at the very top edge of the forehead
Verdict: Bria FIBO failed the basic requirement of an image edit by completely regenerating a new person and scene, losing the original subject's identity entirely. FLUX.2 [dev] Flash successfully performed a precise edit, adding the requested hair while perfectly preserving the person's facial features and the original environment.
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 variety of sushi types (nigiri, maki, California roll)
- + Beautifully rendered textures on the fish and wasabi
- + Clean typography and decorative diorama base
- − Includes some strange watermarks/UI elements in the corners
- − Shadows on the base are slightly disconnected from the plate
FLUX.2 [dev] Flash
- + Perfect adherence to the isometric perspective
- + Extremely clean, professional layout without distracting watermarks
- + Accurate and bold text rendering
- − Lower variety of sushi pieces compared to the other model
- − The sushi logic is slightly off, with toppings draped over a sliced roll
Verdict: Both models followed the prompt exceptionally well, producing clean 3D isometric designs. Bria FIBO offers more visual interest and variety in the sushi itself, but it is marred by unsightly AI-generated watermarks in the corners. FLUX.2 [dev] Flash is the winner for its professional finish, superior text clarity, and overall cleaner composition which perfectly matches the 'ultra-clean' requirement.
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
- + Successfully captures a highly exaggerated, classic 'caricature' style with an expressive face.
- + Includes the TV anchor profession and a large, friendly dog clearly.
- + The studio lighting and busy background contribute to the 'job' theme.
- − Completely misses the 'hockey' requirement of the prompt.
- − The subjects are floating/merged in a nonsensical way, with a dog head growing out of her shoulder.
- − The face bears very little resemblance to the source image provided.
FLUX.2 [dev] Flash
- + Perfectly incorporates all three elements: TV anchor, dogs, and hockey.
- + Maintains a strong facial resemblance to the woman in the source image while applying a caricature style.
- + Excellent composition that merges a news desk with a hockey rink and various dogs.
- − The scale of the head is significantly larger than traditional caricatures, bordering on 'big head' mode rather than an artistic exaggeration.
- − Slightly less 'humorous' and more 'cute' in its interpretation.
Verdict: FLUX.2 [dev] Flash is the clear winner as it successfully incorporated every element of the prompt, including the specific request for hockey which Bria FIBO completely ignored. FLUX.2 [dev] Flash also did a much better job of preserving the likeness of the person from the source image while still creating a fun, stylized illustration.
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 distinct animals requested.
- + Vibrant coloration and dynamic composition showing movement.
- + Effective use of god rays and sunlight effects.
- − Anatomy issues, particularly with the fox's floating front leg.
- − Fur texture looks somewhat plastic and lacks the requested hyper-photorealistic detail.
- − The kitten's facial structure is slightly distorted.
FLUX.2 [dev] Flash
- + Superior fur texture and lighting realism.
- + Excellent inclusion of dew sparkles on the grass as requested.
- + Expressive and endearing facial features on the animals.
- − Failed to include exactly one of each animal, instead duplicating the fox and bunny.
- − The composition is static and 'posed' rather than showing the animals tumbling and playing.
- − The kitten is largely obscured in the center.
Verdict: Bria FIBO followed the specific count of the prompt more accurately by including exactly one of each animal, but suffered from anatomical artifacts and a less realistic finish. FLUX.2 [dev] Flash produced a significantly more beautiful and polished image with superior textures and lighting, despite doubling up on species and missing the chaotic 'tumbling' energy requested.
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, 'shoujo' aesthetic with warm lighting
- + Maintains the central narrative of the original meme perfectly
- + High level of detail in the background flower elements
- − The art style is generic modern anime rather than specifically Studio Ghibli
- − Significant structural changes to the characters' faces compared to the source
FLUX.2 [dev] Flash
- + Perfectly captures the Studio Ghibli 'watercolor and ink' art style
- + Preserves the facial features and expressions of the people in the original photo
- + Excellent use of soft pastel colors and hand-painted textures as requested
- − The background is a bit generic and lacks the architectural detail of the source
Verdict: While Bria FIBO creates a beautiful anime-style image, it fails to capture the specific 'Studio Ghibli' style requested, leaning more toward modern digital illustration. FLUX.2 [dev] Flash perfectly captures the requested Ghibli aesthetic while maintaining an impressive level of source preservation, keeping the faces and poses nearly identical to the original 'Distracted Boyfriend' meme.
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 addition of dynamic motion through running poses and hair flow.
- + Strong autumnal atmosphere with many blurred, falling leaves.
- + High overall image quality and energetic feel.
- − Poor source preservation; the model, dog, and background are significantly altered.
- − Changed the season from summer to autumn, which wasn't specifically requested.
FLUX.2 [dev] Flash
- + Perfect source preservation; the original person, dog, and background are kept exactly as they were.
- + Successfully added wind-blown hair and leaves as requested.
- + Maintains the original lighting and color palette.
- − The 'dynamic motion' is somewhat static, appearing more like a filter than a change in momentum.
- − The leaves look a bit like they are floating rather than blowing.
Verdict: Bria FIBO followed the 'energetic' instruction much better by repositioning the characters into a running pose, but it failed the core requirement of image editing by essentially generating a new image that only loosely resembles the source. FLUX.2 [dev] Flash successfully added the requested elements (blowing hair and leaves) while perfectly preserving the identity of the woman, the dog, and the background details, making it the superior editing tool.
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 lines
- + Uses warm brown and cream tones as requested
- − Major spelling errors in both the restaurant name and the date
- − Steam effect is visually weak and lacks clarity
- − Unbalanced composition with the banner at the top
FLUX.2 [dev] Flash
- + Perfect text rendering for both the name and the established date
- + Excellent vintage texture and 'vector emblem' aesthetic
- + Clear and stylish illustration of the cloche and steam
- − The steam is coming from the top of the handle rather than from within the cloche
- − The banner construction is slightly complex for a 'minimalist' prompt
Verdict: FLUX.2 [dev] Flash significantly outperformed Bria FIBO by accurately rendering all requested text, including the specific date '1720'. While Bria FIBO struggled with spelling and date accuracy, FLUX.2 [dev] Flash delivered a professionally balanced logo with superior texture and vintage appeal.
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 'flat-vector' aesthetic with consistent line weights.
- + Elegant, balanced composition and layout that feels like a professional poster.
- − Text is entirely gibberish and unreadable.
- − The infographic flow is confusing and doesn't explicitly follow the 1-6 numbered steps requested.
FLUX.2 [dev] Flash
- + Successfully renders legible text for all major mission stages and astronaut names.
- + Directly addresses all numbered steps in a logical sequence.
- + Great use of the specific NASA-inspired color palette.
- − The visual style is a bit inconsistent, mixing 2D Earths/Moon with detailed 3D-shaded landing modules.
- − The layout is a bit cluttered compared to Model A.
Verdict: While Bria FIBO produces a much more visually cohesive and aesthetically pleasing 'modern vector' piece, it fails completely on information delivery with nonsensical text. FLUX.2 [dev] Flash is the clear winner for an infographic task because it accurately labels every stage of the mission, renders the requested text correctly, and provides a logical flow, despite having a slightly less polished artistic style.
Explore each model
Fast distilled version of Black Forest Labs' FLUX.2 [dev] optimized for speed and cost efficiency.