Black Forest Labs' open-weights multimodal flow transformer for in-context image generation and editing, available for non-commercial use with character consistency and style transfer capabilities
Settled by community votes across 16 shared challenges, with an AI judge weighing in on each.
FLUX.1 Kontext [dev]
#54 of 62 in Text-to-Image
Nano Banana
#21 of 62 in Text-to-Image
Where the votes landed
FLUX.1 Kontext [dev]
0.0%
win rate
Ties
0.0%
Nano Banana
100.0%
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 [dev]
- + Excellent adherence to lighting instructions with a clear window light source
- + Highly realistic textures on the wood grain and glass reflections
- + Good spatial arrangement of all components including the plant behind the glass
- − The glass cube looks more like an open-sided box or container than a solid-walled cube
Nano Banana
- + Successfully placed the small sphere in the center of the cube
- + Captures a moody, atmospheric lighting with visible dust motes
- + Followed all object placement instructions correctly
- − The sphere appears to be floating unnaturally in the air inside the cube
- − Image clarity is slightly lower with a hazy or soft-focus quality overall
Verdict: FLUX.1 Kontext [dev] produced a much more realistic image with superior lighting and texture, although the cube's structure is slightly ambiguous. Nano Banana followed the prompt well but the floating sphere and softer image quality make it look less grounded and realistic compared to the sharp detail of FLUX.1 Kontext [dev].
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 [dev]
- + High resolution and clear rendering of the elderly man's face
- + Good color saturation on the red bicycle
- + Excellent light reflection on the wet asphalt
- − The subject is posing with the bike rather than repairing it
- − Missing the requested motion blur from passing cars
- − The rain effect looks like static vertical lines overlaying the image
Nano Banana
- + Stronger adherence to 'repairing' action in the prompt
- + Captures a more authentic 'candid' street photography aesthetic
- + Beautifully rendered wet pavement and atmospheric depth of field
- − Anatomical issues with the man's hands and fingers while touching the bike
- − Structural issues with the bicycle frame and kickstand
- − The background cars look somewhat static despite the motion blur request
Verdict: Nano Banana captures the essence of the prompt much better, showcasing an actual 'repair' scene with a more convincing candid, cinematic street photography style. While FLUX.1 Kontext [dev] has higher technical clarity in the face, the image feels staged as the man is simply sitting on the bike in the middle of a road rather than repairing it.
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 [dev]
- + Excellent dramatic lighting that realistically reflects off the chest plate
- + Strong facial detail and lifelike expression
- + Very high-quality engraving texture on the armor
- − Missed the request for braided hair
- − Scars look more like surface paint or fresh blood rather than battle-worn skin texture
- − Less emphasis on leather and cloth layers
Nano Banana
- + Perfect adherence to specific hair braids and beads instruction
- + Superior skin texture showing battle wear and believable scarring
- + Clearer representation of multiple layers including leather straps and cloth
- − The eyes look slightly less lifelike and more stylized than Model A
- − Back-lighting is a bit generic and less integrated into the foreground
Verdict: Nano Banana is the clear winner for its meticulous adherence to the prompt, specifically capturing the braided hair, beads, and leather strap details that FLUX.1 Kontext [dev] ignored. While FLUX.1 Kontext [dev] has impressive lighting and armor engravings, Nano Banana better captures the 'battle-worn' aesthetic with superior skin texturing.
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 [dev]
- + High resolution food photography with great color saturation.
- + Bold, modern typography that fits the minimalist aesthetic.
- + Asymmetrical grid layout that feels contemporary and professional.
- − Text is largely gibberish and contains visual artifacts inside the letters.
- − Failed to create distinct, readable sections for 'Appetizers', 'Pizza', and 'Mains'.
Nano Banana
- + Perfectly adhered to the request for specific sections (Appetizers, Pizza, Mains).
- + Text is highly legible and remarkably accurate with only minor spelling errors.
- + Clean, professional layout that looks like a finished product.
- − The food images in the grid are a bit small and lack some of the detail seen in the competitor.
- − The placement of a menu on a wooden background was not explicitly requested, though it looks clean.
Verdict: Nano Banana is the clear winner as it successfully implemented the structural requirements of the prompt, creating distinct and readable sections for different food categories. While FLUX.1 Kontext [dev] produced more artistic food photography, its inability to generate coherent text or logical menu sections makes it less functional for this specific design challenge.
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 [dev]
- + Excellent text legibility and clean graphic design
- + Crisp, appetizing rendering of the central burger
- + High-quality fire effects at the base of the image
- − Failed the 'exploded burger' prompt by showing whole burgers flying instead of components
- − Incorrect currency symbol used (Pound/combination vs Euro)
Nano Banana
- + Perfectly followed the 'exploded burger' layout with suspended components
- + Strong sense of motion and dynamic energy
- + Accurate currency symbol used in the starburst effect
- − The 'LIMITED TIME ONLY' text is smaller and slightly less impactful than in the other version
- − Slightly less clarity on the 'Magic Burger' outline compared to the solid font in Image A
Verdict: Nano Banana followed the core concept of an 'exploded' burger with suspended components perfectly, creating a much more dynamic and professional-looking food advertisement. FLUX.1 Kontext [dev] produced high-quality visuals and clean text but failed to interpret the mechanics of an exploded burger, instead showing several whole burgers flying through the air.
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 [dev]
- + Excellent chalk texture and realistic handwriting variations.
- + High legibility for the main heading text.
- − Numerous spelling errors including 'Mashroom', 'Risoktso', and 'Octpus'.
- − Major text repetition and artifacts in the middle section.
- − Failed to provide the specific month 'April' in the date.
Nano Banana
- + Perfect text accuracy and spelling for all menu items and the date.
- + Much better environment context with the café background and brick wall.
- + Cleaner, more professional composition that follows the layout instructions.
- − The 'elegant cursive' request for the title was interpreted more as a standard tall print.
- − The chalk texture is a bit uniform compared to the gritty feel of Model A.
Verdict: Nano Banana is the clear winner as it successfully rendered all requested text with 100% accuracy, including difficult words like 'Risotto' and 'Octopus'. In contrast, FLUX.1 Kontext [dev] suffered from significant spelling hallucinations, repeated words, and failed to correctly render the specified date.
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 [dev]
- + Excellent texture on the capybara fur and clothing.
- + The woman's bored expression perfectly matches the prompt.
- + Superior lighting and bokeh effects in the background.
- − The capybara only has one hand on the steering wheel while the prompt asked for both.
- − The capybara's head is turned oddly toward the camera rather than the road.
Nano Banana
- + Successfully placed both paws on the steering wheel as requested.
- + The side profile composition feels very cinematic and professional.
- + Captures the 'taxi driver cap' style very effectively.
- − The woman in the back seat appears to have three hands/multiple limbs merged with the phone.
- − The capybara's fur texture is slightly less defined compared to the other model.
Verdict: FLUX.1 Kontext [dev] produced a much higher quality image in terms of textures, facial expressions, and overall realism, though it failed the specific 'both paws' instruction. Nano Banana followed the pose instructions better and offered a great composition, but suffered from significant anatomical errors in the rendering of the passenger's hands.
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 [dev]
- + Strong, legible main header
- + Clean border with thorn and web motifs
- + High contrast jack-o-lantern lighting
- − Significant text errors in the sub-text and location details
- − Composition feels a bit flat and graphic rather than cinematic
- − Background lacks the requested moody sky and twisted tree depth
Nano Banana
- + Perfect text rendering for all requested fields
- + Excellent atmospheric lighting and composition with depth
- + Highly detailed border combining webs, thorns, and parchment textures
- − The jack-o-lantern is slightly smaller in proportion to the frame
Verdict: Nano Banana significantly outperforms FLUX.1 Kontext [dev] by accurately rendering every line of requested text without spelling errors. Nano Banana also creates a much more cinematic and atmospheric image that perfectly captures the gothic, vintage aesthetic requested in the prompt.
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 [dev]
- + Successfully added thick hair that blends relatively well with the beard color.
- + Maintains the overall desert lighting and environment.
- − Significantly altered the facial features and glasses, making the subject look like a different person.
- − The hairline and hair texture look slightly artificial and stiff.
Nano Banana
- + Excellent preservation of the original facial features, skin texture, and eyewear.
- + The hair has a very natural, messy texture that realistically matches the subject's age and style.
- + Maintains the exact lighting and background of the source image.
- − The hair on the far left side (near the ear) has a slight transparency issue where the background shows through.
Verdict: Nano Banana is the clear winner as it successfully added the requested hair while perfectly preserving the identity of the person in the source image. FLUX.1 Kontext [dev] added the hair but failed the 'preserve facial features' instruction, resulting in a face that looks significantly younger and stylistically different from the original.
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 [dev]
- + Excellent 3D toy-like textures and soft lighting
- + Clean, balanced layout with bold, readable typography
- + Perfectly centered and minimalist aesthetic
- − The flag icon is stylized to the point of being unrecognizable as Japan's flag
- − The sushi design is overly simplified, lacking realistic rice texture
Nano Banana
- + Features a correct Japanese flag icon
- + Rich variety of sushi types with clear, appealing textures
- + Excellent use of the 'diorama base' with stone-like details
- − The text is slightly small and less integrated into the composition than model A
- − Minor lighting clipping on the white rice grains
Verdict: Nano Banana followed the prompt much more accurately by providing a variety of sushi on a detailed diorama base and including a correct Japanese flag. While FLUX.1 Kontext [dev] had superior typographic design and a cleaner aesthetic, its failure to render a recognizable flag and its extremely simplified sushi model makes it less successful for this specific prompt.
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
FLUX.1 Kontext [dev]
- + Maintains the original clothing and 'selfie' pose of the source image.
- + Captures the subject's likeness well in a comic style.
- − Completely fails to include the requested hockey theme.
- − The 'TV show anchor' element is very basic, just a small TV in the background.
- − The word 'JOB' is literal and uncreative.
Nano Banana
- + Excellent adherence to all prompt elements including hockey, dogs, and TV anchoring.
- + Creative and humorous integration of dogs into the hockey arena background and newspaper.
- + High-quality caricature style with great detail and specific props like the headset and Stanley Cup.
- − Changes the subject's outfit from the source denim shirt to a news anchor suit.
- − A slight loss of original facial likeness compared to the source, though typical for a caricature.
Verdict: Nano Banana is the clear winner as it successfully incorporated every element of the prompt (TV anchor, dogs, and hockey) into a cohesive and humorous caricature. FLUX.1 Kontext [dev] completely missed the hockey requirement and provided a much less creative interpretation, despite doing a better job of preserving the source image's clothing.
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 [dev]
- + Dynamic action with the animals mid-run
- + High-quality lighting and depth of field
- + Sharp, distinct butterfly renders
- − Missed prompt requirements for a baby bunny and a red fox kit
- − Included two cats and one dog instead of the requested variety
- − Lacks the 'god rays' specified in the prompt
Nano Banana
- + Perfect prompt adherence, including all four specific animals
- + Beautiful 'god ray' lighting effects and dew sparkles
- + Highly detailed textures for fur and whiskers
- − The fox kit has a slightly anthropomorphic paw gesture
- − Composition is a bit crowded with many butterflies
Verdict: Nano Banana is the clear winner as it followed all specific prompt instructions, including the list of four different animals and the atmospheric 'god rays' lighting. FLUX.1 Kontext [dev] produced a high-quality image but failed significantly on prompt adherence by omitting the bunny and fox entirely.
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 [dev]
- + Excellent adherence to the Studio Ghibli art style with clean line work and appropriate shading.
- + Preserves the composition and poses of the original meme perfectly.
- + The color palette is bright and evocative of an anime production.
- − The character faces are generalized anime faces rather than maintaining the likeness of the original subjects.
Nano Banana
- + Near-perfect preservation of the original photographic elements and identity of the subjects.
- − Completely failed the edit instruction to transform the image into a Studio Ghibli-inspired illustration.
- − The image remains a photograph with almost no visible stylistic changes.
Verdict: FLUX.1 Kontext [dev] successfully transformed the meme into a high-quality illustration that captures the requested Studio Ghibli aesthetic while maintaining the recognizable scene layout. Nano Banana failed to apply any significant stylistic changes, returning what essentially looks like the original photo with very minor lighting adjustments.
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 [dev]
- + Excellent preservation of the original subjects and background.
- + Subtle, natural-looking hair motion that follows the wind direction.
- − The 'flying leaves' are barely noticeable and look like small green specks.
- − Overall energy remains quite static compared to the prompt requirements.
Nano Banana
- + Successfully added a large number of colorful flying leaves as requested.
- + Created a more dynamic and wind-swept look for the woman's hair.
- − The leaf assets are a bit sharp and lack motion blur, making them look 'pasted on'.
- − Slightly altered the woman's facial features and the dog's expression.
Verdict: Nano Banana followed the instruction for the 'energetic feel' much more effectively by adding prominent leaves and significant hair movement, though it lost some of the original image's facial details. FLUX.1 Kontext [dev] preserved the source image almost perfectly but failed to provide a meaningful impact on the 'flying leaves' requirement, resulting in a very subtle change.
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 [dev]
- + Perfect text rendering with high readability
- + Clean, minimalist vector aesthetic
- + Accurate inclusion of the cloche dome and steam
- − Missed the 'banner' requirement for the Est. 1720 text
- − Typography feels a bit too modern and bold for a 'vintage' style
Nano Banana
- + Excellent adherence to 'vintage' and 'classic typography' through ornate script
- + Correctly included the decorative banner for the founded date
- + Beautiful texture and emblem-style composition
- − The 'steam' is interpreted as abstract decorative swirls
- − Slightly less 'minimalist' than the prompt requested
Verdict: Nano Banana followed the prompt's stylistic cues for 'vintage' and 'banner' much more effectively than FLUX.1 Kontext [dev], which produced a very modern, bold logo that ignored the banner requirement. While FLUX.1 Kontext [dev] has cleaner vector lines, Nano Banana better captures the requested heritage and elegance of the historic Caffè Florian.
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 [dev]
- + Adheres well to the requested color palette.
- + Includes a variety of icon shapes.
- − Numerous spelling errors in text (e.g., 'APOLO', 'DESCNT').
- − Iconography is messy and lacks the 'crisp lines' requested.
- − Text is garbled and unreadable in many sections.
Nano Banana
- + Excellent adherence to the 'modern vector' and 'flat-vector' style requirements.
- + Very clear and legible typography with mostly correct spelling.
- + Well-organized layout that follows the logical sequence of launch to landing.
- − Skips step 5 (Descent) in the numbered sequence.
- − Spelling error in 'ARMSRONG' in the crew section.
Verdict: Nano Banana is the clear winner as it successfully captures the aesthetic of a clean, professional vector infographic with crisp lines and consistent icons. While FLUX.1 Kontext [dev] struggled with messy, distorted graphics and severe text garbling, Nano Banana produced a highly usable and visually appealing poster that followed the prompt's stylistic instructions closely.
Explore each model
Gemini 2.5 Flash Image is optimized for image understanding and generation, offering a balance of price and performance with fast and efficient image generation and editing capabilities.