FP8 quantized variant of Black Forest Labs' FLUX.1 [schnell] model, offering ~2x faster inference with reduced precision while maintaining high-quality image generation in 4 steps
Settled by community votes across 13 shared challenges, with an AI judge weighing in on each.
FLUX.1 [schnell] FP8
#47 of 62 in Text-to-Image
Nano Banana Pro
#2 of 62 in Text-to-Image
Where the votes landed
FLUX.1 [schnell] FP8
0.0%
win rate
Ties
50.0%
Nano Banana Pro
50.0%
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
FLUX.1 [schnell] FP8
- + Expertly rendered caustics and refractions within the glass.
- + Vibrant color palette with a clean, modern aesthetic.
- + Perfect adherence to lighting and placement prompts.
- − The glass enclosure has an internal shelf that wasn't requested.
- − The blue sphere looks more like a decorative marble/globe than a simple sphere.
Nano Banana Pro
- + Highly realistic photographic texture on the wooden table and red book.
- + Accurate interpretation of a simple glass cube and small blue sphere.
- + Natural, convincing lighting that feels like a real photograph.
- − The glass cube has dark edges that make it look a bit like an aquarium.
- − The composition feels slightly less balanced compared to the other model.
Verdict: Both models followed the prompt instructions perfectly, including the specific spatial relationships between the objects. FLUX.1 [schnell] FP8 produced a cleaner, more stylized image with impressive refraction effects, while Nano Banana Pro achieved a much higher level of photorealism, particularly in the textures of the wood and the vintage book.
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
FLUX.1 [schnell] FP8
- + Excellent handling of wet pavement reflections and light bokeh
- + High central sharpness on the subject
- + Vibrant color rendering of the red bicycle
- − Subject appears more generic than Japanese
- − Cars in background are static and lack the requested motion blur
- − Composition feels like a standard portrait rather than a candid street photo
Nano Banana Pro
- + Perfectly captures the 'imperfect framing' and 'candid' aesthetic of a 50mm lens
- + Authentic Japanese street setting with appropriate signage and vehicle types
- + Visible rain droplets and realistic skin texture on the subject
- − The transition between the man and the bicycle seat has some minor clipping artifacts
- − Missing significant motion blur on the passing cars
Verdict: Nano Banana Pro significantly outperforms FLUX.1 [schnell] in terms of atmosphere and cultural accuracy, creating a scene that feels like a genuine candid photograph from a Japanese city. While FLUX.1 has a cleaner, more 'rendered' look, Nano Banana Pro better follows the prompt's specific stylistic requests for imperfect framing and a non-stylized, realistic feel.
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
FLUX.1 [schnell] FP8
- + Intense, high-contrast lighting that creates a dramatic mood
- + Extremely sharp facial details and lifelike eye iris texture
- − Missed several prompt elements including the braids and clear dirt/scars
- − The plate armor is barely visible in the frame compared to the face
Nano Banana Pro
- + Excellent adherence to all prompt elements including braids with beads, scars, and dirt
- + Superb intricate engraving details on the plate armor
- + Effective use of bokeh sparks and torchlight to create depth
- − The lighting on the face is a bit flat compared to the dramatic shadows of Image A
- − Slightly less 'hyper-realistic' skin pores when compared to the sharpness of the first image
Verdict: Nano Banana Pro followed the prompt instructions much more accurately, successfully incorporating the braided hair, beads, scars, and ornate armor. FLUX.1 [schnell] FP8 produced a visually striking portrait with incredible sharpness, but it ignored many of the Specific descriptive requirements like the braids and the battle-worn texture.
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
FLUX.1 [schnell] FP8
- + Features a comprehensive multi-page layout with extensive item listings
- + Captures a clean, professional minimalist aesthetic
- + Good use of high-key lighting for food photography
- − Text is largely nonsensical gibberish or badly garbled
- − Headers are misspelled ('SECCER' instead of 'Mains' or 'Desserts', 'APPTIZERS')
- − Inconsistent alignment in the text blocks
Nano Banana Pro
- + Excellent text legibility and font choice in accordance with the prompt
- + Superior food photography realism with high-quality textures
- + Strong color-coded grid structure that improves visual hierarchy
- − Single-page layout is less comprehensive than a full menu
- − Relatively large text for a menu design, bordering on a flyer aesthetic
Verdict: Nano Banana Pro is the clear winner as it produces legible, professional-grade typography and realistic food images that align perfectly with the modern minimalist brief. While FLUX.1 [schnell] FP8 offers a more expansive layout, its severe issues with spelling, text rendering, and item repetition make it unusable for design purposes.
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
FLUX.1 [schnell] FP8
- + High resolution image with vibrant colors.
- + Realistic texture on the burger bun and lettuce.
- − Major text errors including 'LIIMITED' and 'NEEY'.
- − Missing the requested 'exploded' effect as the burger is mostly assembled.
- − Failed the pricing request, showing €69 instead of €6.99.
Nano Banana Pro
- + Perfect adherence to the 'exploded' burger layout with separated components.
- + Flawless text rendering with the requested glowing/fiery effect.
- + Accurate pricing of €6.99 in the starburst as requested.
- − Liquid sauce splash looks slightly more digital than photorealistic.
- − The tomato slice is a bit thicker than a standard commercial food shot.
Verdict: Nano Banana Pro followed the prompt instructions perfectly, providing an exploded view of the burger and accurate, glowing text. FLUX.1 [schnell] FP8 failed significantly on the text rendering, with multiple typos and incorrect pricing, and did not achieve the requested exploded 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
FLUX.1 [schnell] FP8
- + Features a clear, well-framed close-up of the chalkboard.
- + Captures a realistic chalk texture on some of the larger letters.
- − Severely failed to render the requested text accurately, resulting in gibberish and repeats.
- − The handwriting style is blocky and inconsistent rather than the requested elegant cursive.
Nano Banana Pro
- + Excellent typography rendering with zero spelling errors for all requested items.
- + Perfectly captures the 'cozy café' atmosphere with realistic background depth and lighting.
- + Followed the handwriting style instructions perfectly, including the cursive title and chalk texture.
- − The pricing for the 'Brown Butter' item was inferred as it was cut off in the prompt, but it fits logically.
Verdict: Nano Banana Pro is the clear winner as it followed every instruction perfectly, including rendering complex menu text without a single spelling error and capturing the exact aesthetic requested. FLUX.1 [schnell] FP8 struggled significantly with text coherence, producing repetitive lines of misspelled words and failing to deliver the elegant cursive style requested for the title.
The Reversed Rodeo
Text-to-Image“Horse riding astronaut in space — horse on top, not vice versa. Surreal, highly detailed, cinematic.”
AI Judge Analysis
FLUX.1 [schnell] FP8
- + Excellent high-resolution textures on the horse fur
- + Dramatic cinematic lighting and composition
- + Dynamic sense of motion
- − Completely failed the reversal prompt requirement
- − The astronaut is represented as mechanical luggage rather than a person
- − Anatomical issues with the horse limbs
Nano Banana Pro
- + Successfully followed the specific instruction for the horse to be on top
- + Coherent surreal concept with the astronaut holding the horse
- + Balanced composition with multiple space elements
- − The horse's hooves are oddly merged with the astronaut's hands
- − The scale of the Earth in the background is quite small compared to the foreground
Verdict: Nano Banana Pro is the clear winner as it successfully interpreted the difficult 'horse on top' spatial instruction, whereas FLUX.1 [schnell] FP8 produced a standard horse-riding-something image. Nano Banana Pro also captured the surreal requirement more effectively with its creative interpretation of an astronaut carrying a horse like a weightlifter.
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
FLUX.1 [schnell] FP8
- + Excellent fur texture and lighting on the capybara.
- + Logical placement of the woman and clear rendering of the 'taxi' text on the hat.
- + Strong cinematic composition with a narrow depth of field.
- − The passenger is holding two phones simultaneously, which is illogical.
- − The capybara's paw placement on the steering wheel is anatomically awkward and lacks grip.
Nano Banana Pro
- + Highly photorealistic and gritty atmosphere that looks like a real photo.
- + Excellent adherence to the 'bored' expression for the passenger and 'both front paws on the wheel' for the capybara.
- + Authentic taxi interior details like the meter and dashboard.
- − The passenger's face is slightly blurry compared to the foreground.
- − The capybara's hat is more of a generic newsboy cap than a specific taxi driver uniform hat.
Verdict: Nano Banana Pro wins by creating a much more believable and photorealistic scene that perfectly captures the requested 'bored' expression and 'paws on wheel' instruction. While FLUX.1 [schnell] FP8 has higher clarity and more vibrant colors, it fails logically by giving the passenger two phones and having less realistic interaction between the animal and the car controls.
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
FLUX.1 [schnell] FP8
- + Features a bold and clear main title
- + Good use of negative space for readability of the bottom text
- − Significant spelling errors in the scroll banner and event details
- − The border feels more like a fabric frame than a gothic parchment border with webs
- − Jack-o-lantern has an overly digital, synthetic appearance
Nano Banana Pro
- + Excellent text rendering with near-perfect spelling across all fields
- + Highly detailed gothic border incorporating webs and thorns as requested
- + Atmospheric, cinematic lighting on the jack-o-lantern and background
- − The 'Arches' text in the location is slightly stylized/distorted but remains legible
Verdict: Nano Banana Pro is the clear winner as it successfully rendered almost all the requested text with high accuracy, whereas FLUX.1 [schnell] FP8 struggled with significant typos. Nano Banana Pro also provided a much more cohesive gothic aesthetic, with intricate borders and better integrated background elements.
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
FLUX.1 [schnell] FP8
- + Excellent 3D miniature aesthetic with soft, clean lighting.
- + High-quality material rendering for the sushi toppings.
- + Clean isometric composition.
- − Failed to render the word 'SUSHI'.
- − Text 'JAPAN' is repeated incorrectly and distorted.
- − Plating is less realistic compared to Model B.
Nano Banana Pro
- + Successful rendering of both 'JAPAN' and 'SUSHI' text.
- + Perfect adherence to the 'small raised diorama base' with moss and cherry blossoms.
- + Includes the requested flag icon clearly.
- − The text is slightly off-center compared to the miniature base.
- − The plate texture is a bit grainy compared to the 'ultra-clean' request.
Verdict: Nano Banana Pro is the clear winner as it followed every part of the complex prompt, including specific text and diorama elements that FLUX.1 [schnell] FP8 missed. While FLUX.1 [schnell] FP8 has high visual clarity, its failure to render the correct text and its messy typography significantly detracts from the result.
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
FLUX.1 [schnell] FP8
- + Excellent use of warm backlight and glowing 'god rays'
- + Creative and highly expressive facial features on the kittens
- + High color saturation that enhances the 'joyful' vibe
- − Failed to include the baby bunny
- − Included redundant subjects (two kittens/foxes instead of the specified four unique animals)
- − Anatomical issues where characters blend into each other
Nano Banana Pro
- + Perfect prompt adherence, including the puppy, kitten, bunny, and fox kit
- + Captures the 'chasing' and 'tumbling' movement much better than the static pose of Model A
- + Clearer distinction between subjects and better anatomical accuracy
- − The kitten is much smaller and less detailed than the other animals
- − Background trees slightly distract from the meadow focus
Verdict: Nano Banana Pro is the clear winner as it successfully included all four requested animals (golden retriever, kitten, bunny, and fox) and captured the dynamic action of chasing. FLUX.1 [schnell] FP8 failed to generate the bunny and instead created a group of five animals where many shared features and blended together, despite having superior lighting and texture.
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
FLUX.1 [schnell] FP8
- + Clean vector-style emblem
- + Effective use of warm brown and cream tones
- − Significant text spelling errors (AFe FLAMILAN)
- − Cloche design resembles a building dome rather than a food cover
Nano Banana Pro
- + Perfect text rendering for 'Caffè Florian' and 'Est. 1720'
- + Highly accurate interpretation of a retro cloche dome with steam
- + Beautiful subtle texture on the background
- − None notable
Verdict: Nano Banana Pro followed the prompt perfectly, delivering accurate text and a clear 'cloche dome' illustration. FLUX.1 [schnell] FP8 failed significantly on the typography, misspelling the main name, and produced a more abstract architectural-style dome rather than the requested restaurant cloche.
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
FLUX.1 [schnell] FP8
- + Stronger adherence to the flat-vector aesthetic with simple shapes
- + Captures the requested navy and gray color palette accurately
- − Nonsense text for almost all labels and descriptions
- − Poor layout that doesn't clearly convey a sequential timeline
- − Missing the specific Saturn V rocket icon requested for the launch step
Nano Banana Pro
- + Excellent text rendering with clear, legible titles and labels
- + Superior composition that follows the mission steps in a clear logical flow
- + Detailed and accurate iconography for each mission phase including the Saturn V and Lunar Module
- − Slightly more complex than the requested 'flat-vector' style, leaning into detailed illustration
Verdict: Nano Banana Pro is the clear winner as it successfully follows all instructions, including the specific mission steps and iconography, while maintaining high legibility and professional design standards. FLUX.1 [schnell] FP8 fails on text rendering and fails to create a coherent flow for the infographic despite having a nice minimalist color palette.
Explore each model
Gemini 3 Pro with image generation capabilities. Combines advanced reasoning with the ability to generate and edit images.