Black Forest Labs' 12-billion parameter flow transformer for high-quality text-to-image generation, suitable for personal and commercial use with streaming support
Settled by community votes across 13 shared challenges, with an AI judge weighing in on each.
FLUX.1 [dev]
#16 of 62 in Text-to-Image
FLUX.1 Kontext [max]
#23 of 62 in Text-to-Image
Where the votes landed
FLUX.1 [dev]
0.0%
win rate
Ties
0.0%
FLUX.1 Kontext [max]
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 [dev]
- + Excellent material rendering of the glass and sphere reflection.
- + Realistic leather texture on the red book.
- + Soft, naturalistic depth of field with the plant.
- − The glass object is structured more like a frame or stand than a solid cube.
- − The blue sphere is quite large, bordering on not being 'small' relative to the cube.
FLUX.1 Kontext [max]
- + Perfectly adheres to the spatial prompt by placing the sphere clearly 'inside' a defined cube.
- + Captures the 'small' scale of the sphere more accurately.
- + Dramatic, high-quality lighting that creates convincing shadows on the table.
- − The glass cube appears slightly distorted where it meets the book.
- − The text on the book spine is nonsensical gibberish.
Verdict: FLUX.1 Kontext [max] followed the prompt more literally by creating a fully enclosed glass cube with a small sphere inside, whereas FLUX.1 [dev] created a glass structure that felt more architectural and open. While FLUX.1 [dev] has slightly better surface textures, FLUX.1 Kontext [max] is the winner for its superior composition, lighting, and spatial accuracy.
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 [dev]
- + Excellent handling of motion blur from background traffic.
- + Effective shallow depth of field with realistic bokeh.
- − The subject is standing and holding the bike rather than actively repairing it.
- − The rain effect is very subtle and barely visible against the light background.
FLUX.1 Kontext [max]
- + Successfully captures the specific action of repairing the bicycle chain.
- + Stronger adherence to 'imperfect framing' with the bicycle being cut off in the foreground.
- + Rich reflections on the wet pavement.
- − The rain streaks look a bit like a vertical filter rather than integrated environmental elements.
- − Very little motion blur from the cars compared to the prompt's request.
Verdict: FLUX.1 Kontext [max] captures a much more authentic moment of 'repairing' the bicycle with a candid, crouched posture and imperfect composition. While FLUX.1 [dev] handles the background motion blur and lighting more naturally, it feels more like a staged portrait of a man standing with a bike, failing the internal logic of the repair task.
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 [dev]
- + Excellent photographic quality and depth of field.
- + Very realistic skin texture with subtle freckles.
- + Good interpretation of the bokeh sparks in the background.
- − Largely fails the 'battle-worn' prompt as the subject looks pristine and like a model.
- − Missed the requirement for beads in the hair.
- − The armor lacks the specific 'engraved ornate' detail requested compared to the competitor.
FLUX.1 Kontext [max]
- + Perfect adherence to 'battle-worn' with dirt, sweat, and a prominent forehead scar.
- + Beautifully detailed ornate engraving on the plate armor.
- + Strong lighting that better captures the 'warm torchlight' atmosphere.
- − The eyes look slightly oversaturated/unnatural for a realistic portrait.
- − The bokeh sparks appear as streaks rather than circular bokeh points.
Verdict: FLUX.1 Kontext [max] wins by significantly better prompt adherence, capturing the gritty, battle-worn aesthetic and the ornate armor details that FLUX.1 [dev] omitted. While FLUX.1 [dev] produced a high-quality portrait, it lacks the character depth and specific elements like the hair beads and engraved armor requested in the prompt.
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 [dev]
- + Excellent typography rendering with very readable fonts.
- + Clean, professional white-space management and layout.
- + Includes distinct Appetizers and Mains sections as requested.
- − Missed the request for a grid layout for the photos.
- − Missing a dedicated 'Pizza' section header.
FLUX.1 Kontext [max]
- + Successfully followed the 'grid' layout instruction for photos.
- + Vibrant food colors and high-contrast titles.
- + Accurately captured the requested bold sans-serif font for the header.
- − The text content is largely gibberish/hallucinated characters.
- − Missing clear section headers for 'Appetizers' and 'Mains'.
- − Layout feels a bit cluttered compared to the minimalist request.
Verdict: FLUX.1 [dev] produced a much more professional and realistic menu layout with readable text, though it missed the grid requirement for images. FLUX.1 Kontext [max] followed the grid instruction perfectly but failed to include the specific text sections requested and produced messy, illegible typography. FLUX.1 [dev] is the preferred choice for a usable design template.
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 [dev]
- + Clean vertical composition suitable for social media
- + Accurate rendering of the price and currency
- + Good photorealistic texture on the burger patties and buns
- − Completely failed to include the primary title 'MAGIC BURGER'
- − Lacks the requested 'starburst' for the price
- − The 'exploded' effect is static and stacked rather than dynamic
FLUX.1 Kontext [max]
- + Excellent typography with a glowing, fiery effect that matches the prompt style
- + Dynamic use of debris and embers creates a strong sense of motion
- + Successfully includes a starburst element for the price and the primary title
- − Uses a comma instead of a period in the price formatting (€6,99)
- − The central burger is mostly assembled rather than fully exploded into components
Verdict: FLUX.1 Kontext [max] is the clear winner as it followed the complex text integration and styling instructions, providing the title and starburst that FLUX.1 [dev] omitted. While FLUX.1 [dev] produced a clean, stacked burger, it failed the core branding requirements of the prompt.
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 [dev]
- + Excellent adherence to the 'elegant cursive' requirement for the title.
- + Creates a more aesthetic, boutique café atmosphere with better vertical spacing.
- + Text rendering is clear with very few spelling glitches.
- − The 'chalk' looks a bit like thick paint or a digital brush rather than dry chalk powder.
- − Some slight character artifacts in the bottom-most lines of text.
FLUX.1 Kontext [max]
- + Superb chalk texture with realistic smudges and dusty residue on the board.
- + Flawless spelling and very natural handwriting variations.
- + Layout feels very authentic to a real-world bistro menu.
- − Missed the 'elegant cursive' requirement for the title, using a blockier script instead.
- − The composition is a bit crowded at the bottom edge of the frame.
Verdict: Both models displayed exceptional text rendering capabilities. FLUX.1 [dev] followed the stylistic prompt for cursive more closely and achieved a more professional layout, while FLUX.1 Kontext [max] produced a much more convincing chalk texture and realistic handwriting feel despite missing the cursive instruction for the heading.
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 [dev]
- + Strong cinematic lighting with a back-lit glow
- + Physically plausible horse anatomy for a surreal concept
- + Effective use of negative space in the composition
- − Failed the negative constraint; the astronaut is on top of the horse
- − The harness/bridle has some structural inconsistencies
- − Low-frequency background detail compared to the other model
FLUX.1 Kontext [max]
- + Extreme level of detail in the astronaut suit and horse hair
- + Very crisp rendering with excellent starfield and lens flare effects
- + Detailed textures on the horse's coat and equipment
- − Failed the negative constraint; depicting an astronaut riding a horse instead of a horse riding an astronaut
- − The horse's front-right leg has an anatomical glitch at the joint
Verdict: Both models failed the specific spatial logic requested in the prompt (horse on top of the astronaut), instead defaulting to the common trope of an astronaut riding a horse. FLUX.1 Kontext [max] is the winner because it provides significantly higher visual fidelity, better textures, and a more complex, cinematic background compared to FLUX.1 [dev].
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 [dev]
- + Excellent character placement with the passenger clearly in the back seat.
- + High detail on the capybara's fur and the woman's facial expression.
- + Captures the bored, non-chalant expression of the passenger perfectly.
- − The composition has the woman sitting in the front passenger seat instead of the back seat.
- − The interior scale feels slightly off, making it look like a very small car.
FLUX.1 Kontext [max]
- + High quality texture on the capybara and its clothing.
- + Good depth of field with the city lights in the background.
- + Follows the instruction for a professional expression well.
- − The passenger is located in the front seat, directly next to the driver, violating the 'back seat' instruction.
- − The steering wheel appears to be emerging from the passenger side or is duplicated, creating a confusing layout.
- − The capybara only has one paw visible on the steering wheel.
Verdict: FLUX.1 [dev] followed the character interactions much better, although both models failed to place the passenger in the actual back seat, opting instead for a side-by-side front seat arrangement. FLUX.1 [dev] is the winner because the passenger's expression more accurately reflects the 'bored' prompt and the overall interior layout is less cluttered and more coherent than FLUX.1 Kontext [max].
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 [dev]
- + Features a very clean and intricate thorn border.
- + Strong cinematic lighting with a vibrant central glow.
- − Major text hallucinations including 'Lalloween Rantcy' and 'You Tre'.
- − Redundant and messy event details with repetitive time entry.
- − Did not properly include the gothic title in the layout.
FLUX.1 Kontext [max]
- + Excellent text rendering with accurate spelling and elegant gothic fonts.
- + Perfect adherence to all border elements including webs and thorns.
- + Superior composition that balances the title, banner, and details effectively.
- − Slightly repetitive location line at the bottom.
- − The background trees are a bit darker and less defined than in the other image.
Verdict: FLUX.1 Kontext [max] is the clear winner as it successfully rendered all the requested text with high accuracy, whereas FLUX.1 [dev] suffered from significant spelling errors and hallucinations. FLUX.1 Kontext [max] also better captured the atmospheric details of the prompt like the spiderweb borders and dark parchment texture.
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 [dev]
- + Excellent miniature diorama aesthetic with realistic soft textures.
- + Includes the requested flag icon.
- + Higher quality lighting and depth of field.
- − Text rendering is poor with spelling errors like 'SUSH CATON'.
- − Perspective feels slightly more elevated than a true 45-degree isometric view.
FLUX.1 Kontext [max]
- + Perfectly rendered, bold text that follows the prompt instructions exactly.
- + Clean, vibrant isometric composition adhering to the 45-degree angle.
- + Excellent 3D cartoon style with high clarity.
- − Missed the flag icon requested in the prompt.
- − The texture of the rice looks a bit like large beads rather than realistic soft miniature grain textures.
Verdict: FLUX.1 Kontext [max] is the winner for its superior text rendering and adherence to the layout instructions, providing a much cleaner and more professional-looking graphic. While FLUX.1 [dev] captured the 'miniature' and 'garnish' details better, it failed significantly on the text element which was a core part of the prompt.
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 [dev]
- + Features a vibrant, warm color palette
- + Clean and cute art style suitable for children's books
- − Fails the 'hyper-photorealistic' part of the prompt by being 3D stylized
- − Failed to include the tabby kitten
- − Repeated the puppy/dog-like character twice instead of unique animal types
- − Lacks the requested 'god rays' effect
FLUX.1 Kontext [max]
- + Excellent adherence to all requested animals including the kitten
- + Achieves a high level of photorealism with detailed fur textures
- + Successfully rendered god rays and a lush meadow environment
- + Composition feels natural and dynamic
- − Very minor anatomy issues on the bunny's paws
- − Some butterflies look slightly low-detail compared to the animals
Verdict: FLUX.1 Kontext [max] far outperforms FLUX.1 [dev] in this challenge by strictly adhering to the prompt requirements, including all specified animals (kitten, fox, puppy, bunny) in a photorealistic style. FLUX.1 [dev] opted for a 3D-animation aesthetic and failed to include the kitten, repeating canine-like characters instead.
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 [dev]
- + Elegant banner and cloche design.
- + Great use of vintage script typography.
- + Color palette is perfectly balanced and warm.
- − Spelling error in the main text ('Flariláan' instead of 'Florian').
- − Spelling error in secondary text ('Reseaurant').
- − Random numbers '11011' and '1941' added without prompt.
FLUX.1 Kontext [max]
- + Perfect text rendering with the correct spelling.
- + Excellent textured 'subtle paper' background effect.
- + Strong adherence to the 'minimalist vector emblem' style.
- − The accent mark on 'CAFFÊ' is technically incorrect (should be 'Caffè').
- − Composition is slightly more vertical than typical flat logos.
Verdict: While FLUX.1 [dev] produced a very aesthetically pleasing design, it failed significantly on text accuracy by misspelling the main brand name and adding random extra numbers. FLUX.1 Kontext [max] adhered much better to the prompt, providing accurate text, the requested banner, and a superior subtle texture.
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 [dev]
- + Successfully follows the requested flat-vector style with crisp lines.
- + Captures the NASA-inspired color palette perfectly.
- + Includes a bottom icon bar that attempts to cover the specific steps requested.
- − The text is largely illegible gibberish.
- − The diagram logic is confusing, featuring two Saturn-like planets which do not relate to the Apollo missions.
FLUX.1 Kontext [max]
- + Excellent text rendering for the main titles and crew names.
- + Better iconography for the Lunar Module and the crew silhouettes.
- + The layout is cleaner and more intuitive as a logical flow.
- − The 'Translunar' step shows a moon-to-moon transition which is inaccurate.
- − Includes stylized rocket exhaust that leans more toward illustration than a minimalist vector icon.
Verdict: FLUX.1 Kontext [max] is the winner because it provides legible, relevant text and a much clearer layout that feels like a professional infographic. While FLUX.1 [dev] has a nice aesthetic, its content is nonsensical, including random ringed planets and unreadable text that fails the functional requirements of an infographic.
Explore each model
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