Black Forest Labs' premium multimodal flow transformer with greatly improved prompt adherence and typography generation for in-context image generation and editing without compromise on speed
Settled by community votes across 17 shared challenges, with an AI judge weighing in on each.
FLUX.1 Kontext [max]
#23 of 62 in Text-to-Image
Nano Banana 2
#1 of 62 in Text-to-Image
Where the votes landed
FLUX.1 Kontext [max]
0%
win rate
Ties
0%
Nano Banana 2
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 Kontext [max]
- + Excellent handling of light and shadows across the table surface.
- + Very realistic material texture on the small blue sphere.
- + High visual quality and depth of field.
- − The plant is mostly above/behind the cube rather than visible through the glass panels.
- − Text on the book is garbled and nonsensical.
Nano Banana 2
- + Perfect adherence to all spatial instructions in the prompt.
- + Clear and legible text on the book spine that adds thematic depth.
- + Accurate representation of window light and plant visibility through the glass.
- − The glass cube appears slightly more like an aquarium due to the thickness of the edges.
- − The scale of the 'small' sphere is slightly larger than anticipated compared to the cube.
Verdict: Nano Banana 2 followed the prompt's spatial instructions more accurately, particularly regarding the visibility of the plant through the glass. While FLUX.1 Kontext [max] produced a more aesthetically pleasing lighting environment, it failed on the text rendering and the specific requirement of the plant's placement relative to the glass.
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 Kontext [max]
- + Exceptional handling of rain and wet surface reflections
- + Very high technical photorealism in skin textures and clothing
- + Strong adherence to the shallow depth of field and 50mm lens look
- − The chain of the bicycle is disconnected and floating in an impossible way
- − The rain effect looks somewhat like a digital overlay due to uniform vertical streaks
Nano Banana 2
- + Captures a much more convincing 'Japanese street' atmosphere with legible signage and architecture
- + Includes specific tools like a wrench and toolbox which enhances the storytelling
- + The bicycle kickstand and chain are more physically grounded in reality
- − The man is holding the wrench by the open end while attempting to pull the chain, which is illogical
- − Lower fidelity on skin textures and fine details compared to the other model
Verdict: Both models followed the prompt well, but Nano Banana 2 captured a more authentic Japanese street atmosphere with environmental details and tools. However, FLUX.1 Kontext [max] produced a much higher quality image in terms of texture and lighting, even though it suffered from a nonsensical bicycle chain assembly.
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 Kontext [max]
- + Excellent close-up composition with lifelike, amber-flecked eyes
- + Superior rendering of ornate floral engraving on the plate armor
- + Impressive skin texture showing sweat and fine pores
- − The braids are somewhat loose and less defined with the requested beads
- − Lighting is very warm, almost to the point of oversaturation on the skin
Nano Banana 2
- + Highly detailed hair braiding with clearly visible beads as requested
- + Detailed clothing layers including chainmail and leather straps
- + Strong narrative atmosphere with a battle-worn aesthetic
- − Distorted hand merging into the hilt of the sword
- − The character's eyes lack the 'lifelike' depth seen in the competition
- − Deep shadows obscure some of the armor engravings compared to Model A
Verdict: FLUX.1 Kontext [max] produces a more visually stunning portrait with incredible skin and eye realism, but it slightly misses the mark on specific hair beads. Nano Banana 2 follows the complex clothing and hair instructions more closely but fails on technical anatomy with a significant hand-to-sword artifact. FLUX.1 Kontext [max] is the preferred choice for its superior photorealistic quality and cleaner composition.
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 Kontext [max]
- + Features a very clean, minimalist aesthetic suitable for high-end casual dining
- + Professional logo integration at the top
- + Consistent image style with unified white backgrounds for food
- − Text consists of gibberish characters and placeholder symbols
- − Fails to clearly delineate the requested sections (Appetizers/Pizza/Mains)
- − The food variety is poor, showing almost exclusively pizza.
Nano Banana 2
- + Excellent text rendering with legible names, descriptions, and prices
- + Perfectly organizes the layout into the requested sections (Appetizers, Pizza, Mains)
- + Vibrant color palette with strong visual accents and clear labeling
- − Some minor food artifacts, such as the fries in the bottom right corner
- − The surrounding tabletop elements are slightly cropped out at the edges
Verdict: Nano Banana 2 is the clear winner here as it actually produces a functional, legible menu with the requested sections and realistic text. While FLUX.1 Kontext [max] has a pleasant aesthetic, its inability to generate intelligible text or diverse food items for different categories makes it less useful for this specific prompt.
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 Kontext [max]
- + Excellent font legibility and clean text rendering.
- + Highly photorealistic textures on the burger bun and meat patty.
- − Fails to follow the 'exploded view' instruction, showing a mostly assembled burger.
- − Misses the specific starburst requirement for the price tag.
Nano Banana 2
- + Perfectly adheres to the 'exploded burger' layout with clear vertical separation.
- + Successfully integrates all requested elements including the starburst and fiery text effects.
- + Strong sense of motion with sauce splashes and flying ingredients.
- − Minor text artifacts where '€6.99' looks slightly like '€6.99' with a dash.
- − The lighting is slightly more 'illustrative' than purely photorealistic compared to Model A.
Verdict: Nano Banana 2 is the clear winner as it followed every complex instruction in the prompt, particularly the 'exploded' layout and the specific starburst UI element. While FLUX.1 Kontext [max] produced a more realistic-looking single burger, it failed to meet the core compositional requirements of the creative brief.
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 Kontext [max]
- + Excellent text legibility and accuracy
- + Realistic chalk smudges and texture on the board surface
- + Consistently applied handwriting style across all menu items
- − The 'elegant cursive' request for the title was not fully met, as it appears in block capitals
- − The composition is a tight crop that offers less environmental context than requested
Nano Banana 2
- + Beautiful cursive handwriting for the top title as requested
- + Excellent composition showing the cozy café background for context
- + Highly realistic chalk texture with dusty smears and various chalk pieces visible
- − The pricing text format deviates slightly from the prompt's layout
- − Slightly less crisp character rendering compared to Model A
Verdict: Both models followed the prompt excellently, accurately rendering the difficult menu text and date. Nano Banana 2 is the winner because it successfully followed the stylistic instruction for 'elegant cursive' in the title and provided a much more atmospheric 'cozy café' background, whereas FLUX.1 Kontext [max] used block lettering for the title and a very tight crop.
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 Kontext [max]
- + Excellent photorealistic texture and lighting
- + Cinematic composition with realistic space atmosphere
- − Failed the core prompt instruction of placing the horse on top of the astronaut
- − Standard interpretation lacking the requested surrealism
Nano Banana 2
- + Successfully followed the specific instruction of having the horse on top of the astronaut
- + Strong surreal atmosphere with vibrant colors
- + Detailed harness and space suit elements
- − Anatomical issues where the astronaut's legs merge awkwardly into the horse's back
- − Visual clutter makes the orientation slightly confusing
Verdict: While FLUX.1 Kontext [max] produced a much higher quality, photorealistic image, it completely ignored the negative constraint of 'horse on top, not vice versa.' Nano Banana 2 successfully followed the difficult spatial prompt, creating a truly surreal image where the horse is riding the astronaut, making it the winner for prompt adherence despite lower technical polish.
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 Kontext [max]
- + Excellent photorealistic texture on the capybara fur.
- + Creative yellow taxi cap design matching the prompt.
- + Atmospheric lighting with realistic bokeh effects.
- − The passenger is on a call rather than looking at her phone as requested.
- − The perspective hides much of the taxi interior details requested.
Nano Banana 2
- + Highly detailed interior including a meter, hack license, and partition.
- + Captures the bored expression and specific activity of the passenger perfectly.
- + Humorous and creative extra details like the 'Captain Cappy' license.
- − The capybara's paws look slightly like human hands covered in fur.
- − The black cap deviates from the 'yellow' cap requested in the prompt.
Verdict: Nano Banana 2 is the superior choice because it provides a much more comprehensive interpretation of the prompt, including the specific bored expression of the passenger and a rich, realistic taxi interior. While FLUX.1 Kontext [max] has slightly better fur rendering/lighting, it misses several narrative cues and the wider context of the scene.
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 Kontext [max]
- + Excellent typography style that feels genuinely gothic.
- + Clean layout with a spooky, centered lighting focus.
- − Repetitive text in the location details at the bottom.
- − The date format used commas instead of dots as requested.
Nano Banana 2
- + Perfect adherence to all requested text, including the scroll banner.
- + Rich, detailed composition with added elements like skulls and gothic arches.
- + Correct date formatting and clear hierarchy of information.
- − The layout is slightly more crowded than Model A.
- − A few extra spiders dangling that weren't specific requested, though they fit the theme.
Verdict: Nano Banana 2 is the clear winner for its superior composition and perfect adherence to the prompt's text requirements. While FLUX.1 Kontext [max] produced a clean gothic aesthetic, it failed on the specific date formatting and repeated the location text unnecessarily. Nano Banana 2 successfully incorporated all elements like the scroll banner and detailed background imagery while maintaining legible, accurate text.
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
FLUX.1 Kontext [max]
- + Successfully added high-density hair
- + Maintains original lighting and background
- − Significantly altered facial proportions and bone structure
- − Hair texture looks slightly digitized and overly voluminous
Nano Banana 2
- + Excellent preservation of original facial features
- + Hair integrates naturally with the existing beard and skin tone
- − Hair density is slightly thinner than 'full, thick' request
Verdict: Nano Banana 2 is the superior choice because it adds a realistic head of hair while perfectly preserving the identity of the person from the source image. FLUX.1 Kontext [max] provides more hair volume but fundamentally changes the man's face, resulting in a less accurate edit.
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 Kontext [max]
- + Excellent 3D cartoon style with soft, rounded textures.
- + Very clean typography that matches the aesthetic.
- + Perfectly captures the 'miniature 3D cartoon scene' request.
- − Failed to include the requested flag icon.
- − The text color is a bit dull compared to the vibrant food.
Nano Banana 2
- + High level of variety in the sushi types.
- + Successfully included the requested flag icon.
- + Strong realistic PBR materials and lighting.
- − Missed the 'cartoon' aesthetic for a more photorealistic look.
- − The diorama base is cluttered with moss/rocks, contradicting the 'minimal garnish' request.
- − Layout feels slightly flat compared to the requested 45° isometric depth.
Verdict: FLUX.1 Kontext [max] much better captured the requested 3D cartoon isometric style, providing a clean and charming miniature scene. While Nano Banana 2 included the flag icon and more sushi varieties, it leaned too far into photorealism and ignored the 'minimal' and 'cartoon' instructions.
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 unavailable for this challenge.
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 Kontext [max]
- + Excellent character expressions and eye contact.
- + Beautifully soft, diffused golden hour lighting with god rays.
- + Clean and consistent fur textures.
- − The animals are sitting still rather than 'playfully chasing' as requested.
- − The bunny has slightly unnatural, human-like facial features.
Nano Banana 2
- + Perfect adherence to the 'playfully chasing' and 'tumbling' aspects of the prompt.
- + Superior environmental detail with visible dew sparkles on the grass.
- + Excellent anatomical accuracy for all four diverse animal species.
- − The butterfly on the left is floating without clear wing structure.
- − Slightly less 'masterpiece' feel in the distant background compared to the foreground.
Verdict: Nano Banana 2 is the clear winner as it captures the dynamic action requested in the prompt ('playfully chasing' and 'tumbling') while FLUX.1 Kontext [max] opted for a static, posed composition. Nano Banana 2 also managed to render all four distinct animals with high anatomical accuracy and better integrated the environmental details like dew sparkles.
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
FLUX.1 Kontext [max]
- + Expertly captures the Ghibli facial aesthetic and linework.
- + Preserves the original framing and bokeh effect of the foreground woman.
- + Maintains the exact colors and patterns of the original clothing.
- − The background is a bit washed out and lacks the detailed 'painterly' scenery typical of Ghibli films.
Nano Banana 2
- + Excellent hand-painted textures and watercolor-style coloring.
- + Beautifully detailed background that honors the Ghibli world-building style including flowers and foliage.
- + Accurately translates the expressions of the original subjects into illustration.
- − The out-of-focus effect on the woman in red is a bit muddy compared to the source.
Verdict: Both models performed exceptionally well at translating a popular meme into a new art style. FLUX.1 Kontext [max] creates more authentic Ghibli character designs, but Nano Banana 2 better captures the iconic Ghibli environmental aesthetic with its lush, detailed, hand-painted background scenery.
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
FLUX.1 Kontext [max]
- + Subtle, natural wind effect on hair
- + Preserves the subject's face and expression perfectly
- − Leaves look like static stickers rather than being 'in motion'
- − Introduces a strange third hand/arm reaching toward the dog
- − Alters the dog's pose slightly and loses some paw detail
Nano Banana 2
- + Excellent interpretation of 'dynamic motion' with blurred flying leaves
- + Hair movement is more pronounced and realistic for a windy day
- + Captures an 'energetic and lively feel' through a more exuberant facial expression
- − Changes the facial features significantly from the source image
- − Background elements like the bridge are slightly less sharp than in the original
Verdict: Nano Banana 2 and FLUX.1 Kontext [max] take different approaches to the edit. FLUX.1 Kontext [max] stays closer to the source image's identity but adds a disturbing anatomical glitch (an extra hand) and very static-looking leaves. Nano Banana 2 successfully captures the 'dynamic' request with motion-blurred leaves and wind-swept hair, though it alters the woman's face more than expected.
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 Kontext [max]
- + Excellent typography with correct accents and alignment.
- + Captures a gritty woodblock-style texture that fits the vintage aesthetic.
- + Clean, minimalist composition that works well as a modern-retro logo.
- − The steam element is very simple and less dynamic compared to the cloche.
- − The 'Est. 1720' font is a bit generic compared to the main title.
Nano Banana 2
- + Sophisticated vector emblem style with intricate detailing and circular framing.
- + Great use of shading and line work on the cloche and banner.
- + Dynamic steam illustration adds a sense of warmth and movement.
- − The accent mark on 'Caffè' is backwards (grave instead of acute/grave used incorrectly for Italian).
- − Less 'minimalist' than requested due to the high amount of decorative line work.
Verdict: Both models followed the prompt exceptionally well, but FLUX.1 Kontext [max] produced a more authentic 'minimalist' logo with correct Italian orthography for 'Caffè'. Nano Banana 2 created a more visually complex and aesthetically pleasing emblem, though it slightly missed the 'minimalist' mark and had minor typographical errors in the accentuation.
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 Kontext [max]
- + Strong typography for the main title
- + Clean silhouettes of the crew members
- + Good use of the requested color palette
- − Confused logical flow with arrows pointing to incorrect labels
- − Included gibberish text in the center and incorrect rocket design
- − Failed to include all 6 requested steps
Nano Banana 2
- + Excellent adherence to all 6 requested steps in the correct order
- + Consistent flat-vector icon style throughout the infographic
- + Perfect adherence to the NASA-inspired color palette and text rendering
- − Small artifact adding a fourth unnamed astronaut silhouette
- − The 'Tranquility' label is slightly redundant given the landing icon
Verdict: Nano Banana 2 is the clear winner as it followed the complex instructional prompt perfectly, including all six specific mission steps with corresponding icons. FLUX.1 Kontext [max] produced a visually striking image but failed the core task of creating a functional infographic, with arrows pointing to the wrong labels and missing several steps.
Explore each model
Gemini 3.1 Flash with image generation capabilities. High-efficiency image generation model with support for text rendering, reference images, search grounding, and thinking mode. The efficient counterpart to Gemini 3 Pro Image.