Fast distilled version of Black Forest Labs' FLUX.2 [dev] optimized for speed and cost efficiency.
Settled by community votes across 13 shared challenges, with an AI judge weighing in on each.
FLUX.2 [dev] Flash
#5 of 62 in Text-to-Image
FLUX1.1 [pro] Ultra
#51 of 62 in Text-to-Image
Where the votes landed
FLUX.2 [dev] Flash
0%
win rate
Ties
0%
FLUX1.1 [pro] Ultra
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.2 [dev] Flash
- + Excellent realism in the glass texture and thickness
- + Realistic shadowing and reflections on the sphere and table
- + Natural photographic lighting and depth of field
- − The glass cube has thick visible seams reminiscent of a tank rather than a solid piece
FLUX1.1 [pro] Ultra
- + Sharp, clean lines on the glass cube
- + Bright and well-defined colors for the book and sphere
- + Good placement of the plant behind the glass
- − The blue sphere appears to be floating unnaturally in the center
- − The wood grain on the table looks slightly repetitive
- − Lighting feels more synthetic than the first image
Verdict: FLUX.2 [dev] Flash produces a much more convincing and realistic photographic result, with the sphere correctly resting on the base of the cube. FLUX1.1 [pro] Ultra has very clean geometry, but the floating placement of the sphere makes the scene feel less grounded and realistic.
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.2 [dev] Flash
- + Excellent skin texture and facial details
- + Authentic 'candid' feel with realistic clutter and tools
- + Highly detailed bicycle and basket rendering
- − The car in the background lacks the requested motion blur
- − The framing feels a bit more intentional than 'imperfect'
FLUX1.1 [pro] Ultra
- + Successfully captures long-exposure motion blur on passing cars
- + Good reflection work on the wet pavement
- + Stronger adherence to the requested shallow depth of field
- − The man looks less like he is 'repairing' and more like he is just holding the bike
- − Slightly cleaner, more 'stock photo' look compared to the requested gritty realism
- − The bike geometry is a bit simplified
Verdict: FLUX.2 [dev] Flash produces a much more convincing and detailed subject with realistic skin and tools, fitting the 'candid' request perfectly, though it fails on the motion blur. FLUX1.1 [pro] Ultra captures the technical camera effects like motion blur and shallow depth of field more accurately, but the actual scene feels more staged. FLUX.2 [dev] Flash is the preferred choice for its superior texture and authentic atmosphere.
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.2 [dev] Flash
- + Excellent adherence to all prompt details including braided hair with beads, ornate engraving, and leather straps.
- + Very high texture detail on the skin, fabric, and metal surfaces.
- + Effective lighting and atmosphere with bokeh sparks and warm torchlight.
- − The blood on the face looks slightly more like face paint than realistic battle wounds.
- − The symmetry of the torches in the background feels a bit staged.
FLUX1.1 [pro] Ultra
- − Image failed to load or is a solid black frame.
Verdict: FLUX.2 [dev] Flash delivered a high-quality, detailed portrait that perfectly followed the complex prompt, showcasing impressive textures on the armor and character features. FLUX1.1 [pro] Ultra failed to provide a viewable image, resulting in a black frame. Therefore, FLUX.2 [dev] Flash is the winner by default.
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.2 [dev] Flash
- + Excellent photographic quality and consistency across the food images
- + Clean, professional grid layout that follows the 'modern minimalist' prompt well
- + Clear hierarchy with distinct sections for Appetizers, Pizza, and Mains
- − Text rendering is poor with many gibberish characters and misspellings
- − Sections are mislabeled (e.g., pizzas are shown under Appetizers)
FLUX1.1 [pro] Ultra
- + Dynamic and interesting layout with good use of white space
- + Better text legibility overall, though still containing some AI artifacts
- + Effective use of mock-up perspective for a professional presentation
- − Food photos lack the realistic 'clean' look requested, appearing slightly messy
- − The grid follows a less structured, more chaotic pattern than the prompt suggests
Verdict: FLUX.2 [dev] Flash produces a more traditional and balanced menu grid with superior food photography, but struggles significantly with text accuracy and logical categorization of images. FLUX1.1 [pro] Ultra provides a more creative mock-up feel with slightly better text rendering, though the food photos themselves are less appetizing. FLUX.2 [dev] Flash is the preferred choice for a layout that feels like a real graphic design document.
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.2 [dev] Flash
- + Excellent typography integrated naturally into the fiery atmosphere.
- + Highly realistic food textures and physics-accurate dripping sauce.
- + The fiery starburst for the price perfectly matches the prompt's stylistic requirement.
- − The 'exploded' effect is a bit conservative compared to the highly dynamic 'magic' theme.
FLUX1.1 [pro] Ultra
- + Intense, high-contrast lighting with a strong sense of drama.
- + Complex burger construction with multiple patties and flying debris.
- + Good clarity on the secondary text footer.
- − Failed to include the requested starburst for the price.
- − The background contains hallucinated gibberish text at the bottom corners.
- − The 'exploded' components feel more like a stack than individual suspended ingredients.
Verdict: FLUX.2 [dev] Flash follows the prompt much more accurately, successfully including all requested text elements, the fiery starburst, and maintaining a cohesive 'fiery' style across the typography. FLUX1.1 [pro] Ultra has a more cinematic lighting style but fails on specific layout requirements and introduces distracting artifact text at the bottom.
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.2 [dev] Flash
- + Excellent text rendering with perfect spelling and grammar.
- + Captures the realistic chalk texture and 'dusty' chalkboard look very effectively.
- + Maintains a consistent, elegant handwriting style throughout the entire board.
- − The date is slightly larger than the title, which is a minor compositional oddity.
FLUX1.1 [pro] Ultra
- + Natural variation in letter sizing and spacing reflects a hand-drawn feel.
- + High contrast and sharp focus on the chalkboard.
- − Significant spelling errors and repetitive text (e.g., 'mushroomm', 'riistratnisnios', and repeating the cookies line).
- − Misses the possessive apostrophe in 'TODAY'S'.
- − Handwriting style is noticeably messy and inconsistent compared to the prompt's request for an elegant style.
Verdict: FLUX.2 [dev] Flash significantly outperforms FLUX1.1 [pro] Ultra by following every textual detail of the prompt with perfect spelling and a sophisticated chalk aesthetic. While FLUX1.1 [pro] Ultra attempts the requested variation in handwriting, it fails on basic legibility and accuracy, resulting in repeated words and gibberish.
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.2 [dev] Flash
- + Excellent cinematic lighting and atmospheric depth.
- + High level of detail on the space suit and horse's fur.
- + Consistent and sharp rendering across the entire scene.
- − Failed the spatial logic instruction 'horse on top, not vice versa'.
- − Standard composition that lacks the requested surrealism.
FLUX1.1 [pro] Ultra
- + Dynamic composition with a more dramatic angle.
- + Great clarity in the planet surface and space background.
- + Includes additional sci-fi details like satellites.
- − Failed the spatial logic instruction 'horse on top, not vice versa'.
- − Anatomically strange leg positioning for a horse.
- − Minor artifacts on the horse's back where the astronaut sits.
Verdict: Both models failed the specific instruction to place the 'horse on top' of the astronaut, both defaulting to the common trope of an astronaut riding a horse. FLUX.2 [dev] Flash produced a much more cinematic and technically detailed image, whereas FLUX1.1 [pro] Ultra felt slightly more generic in its lighting and had minor anatomical issues.
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.2 [dev] Flash
- + Excellent adherence to the requested seating arrangement with the capybara in the driver's seat and the human in the back.
- + Highly realistic fur texture and capybara facial features.
- + Accurately depicts the bored, normal expression of the businesswoman as requested.
FLUX1.1 [pro] Ultra
- + Higher overall image clarity and vibrant lighting.
- + Good depiction of Manhattan city lights through the window.
- + Creative interpretation of the capybara's professional jacket.
- − Fails the prompt instructions by placing the businesswoman in the passenger/driver seat area instead of the back seat.
- − The capybara's anatomy is slightly confused with its paws appearing to originate from the side rather than the driver position.
- − The businesswoman appears to be holding a steering wheel, contradicting the prompt.
Verdict: FLUX.2 [dev] Flash followed the spatial and narrative instructions much more accurately, correctly placing the capybara at the wheel and the human in the back seat. FLUX1.1 [pro] Ultra produced a higher quality render but failed fundamentally on the layout, resulting in the businesswoman appearing to drive or sit in the front seat alongside the capybara.
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.2 [dev] Flash
- + Excellent text rendering with no spelling errors.
- + Highly atmospheric and cinematic lighting that fits the 'moody night sky' prompt.
- + Intricate and aesthetically pleasing border with thorns and webs.
- − Includes one extra line of gibberish text ('Hurk: 0369C') not requested in the prompt.
FLUX1.1 [pro] Ultra
- + Strong use of the scroll and parchment metaphor as a central design element.
- + Very clear and legible typography for the event details.
- − Major text hallucination and repetition ('You are invited to a noickt or a night of frights').
- − Missing 'Party' from the main title 'Halloween Party Invitation'.
- − The lighting feels flatter and more like a 2D graphic compared to model A's cinematic depth.
Verdict: FLUX.2 [dev] Flash is the clear winner as it followed the text prompt precisely and captured a much more atmospheric, cinematic quality. While it added one line of decorative gibberish, FLUX1.1 [pro] Ultra failed more significantly by missing words in the title and having a severe text repetition error in the body.
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.2 [dev] Flash
- + Excellent PBR material rendering on the sushi and wood grain.
- + Clean, bold, and perfectly placed typography.
- + Accurate adherence to the 'minimal garnish' and 45-degree isometric prompt.
- − The sushi roll construction is a bit physically illogical where the fish overlaps.
FLUX1.1 [pro] Ultra
- + Beautiful soft-light aesthetic with a charming miniature style.
- + Creative diorama composition with multiple elements.
- + Dynamic font styling that fits the 'cartoon scene' description well.
- − Ignored the 'minimal garnish' request by adding a plant, steaming food, and extra dishes.
- − The text 'SUSHI' is significantly smaller and less balanced than requested.
Verdict: FLUX.2 [dev] Flash adhered much more closely to the specific layout and simplicity requirements of the prompt, producing a very clean and professional asset. FLUX1.1 [pro] Ultra created a more visually complex and charming illustration, but it failed to follow the 'minimal' constraint and the specific text hierarchy requested.
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.2 [dev] Flash
- + Successfully included all requested animal types (puppy, kitten, bunny, fox).
- + High level of detail in fur textures and dew sparkles in the grass.
- + Effective use of 'god rays' and backlighting as requested.
- − Generated duplicates of some animals (two foxes, two bunnies).
- − The butterflies look slightly pasted on and less integrated with the lighting.
FLUX1.1 [pro] Ultra
- + Exquisite bokeh and soft, artistic lighting that fits the 'wholesome' vibe.
- + Excellent composition with consistent eye-lines of animals looking at the butterflies.
- + Superior fur rendering that looks exceptionally soft and realistic.
- − The bunny is partially obscured behind the kitten, making it less distinct.
- − Less emphasis on the 'dew sparkles' mentioned in the prompt.
Verdict: FLUX.2 [dev] Flash adhered better to the count of animals but suffered from doubling up (two foxes and two bunnies), whereas FLUX1.1 [pro] Ultra produced a much more cohesive and aesthetically pleasing composition. FLUX1.1 [pro] Ultra's lighting and soft-focus effects created a more emotional and high-quality 'masterpiece' feel despite the bunny being slightly hidden.
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.2 [dev] Flash
- + Excellent adherence to all text requirements including the grave accent in 'Caffè'.
- + Clean vector emblem style that feels truly minimalist and professional.
- + Perfectly captures the requested 'subtle texture' on the background.
- − The placement of 'Est. 1720' is below the banner rather than inside it as a primary design element.
FLUX1.1 [pro] Ultra
- + Strong vintage roundel composition with good depth.
- + Accurately represents the warm brown and cream color palette.
- − Major spelling error in the primary brand name: 'Framilian' instead of 'Florian'.
- − The composition is quite busy, leaning away from the requested 'minimalist' style.
Verdict: FLUX.2 [dev] Flash followed the prompt's text and style requirements much more accurately, producing a clean and professional logo with perfect spelling. FLUX1.1 [pro] Ultra failed on the text rendering, hallucinating 'Framilian' and creating a more cluttered design than the requested minimalist vector aesthetic.
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.2 [dev] Flash
- + Successfully followed the requested 1-6 step sequence with clear labels.
- + Included excellent secondary details like the crew names and portraits.
- + Better adherence to the 'NASA-inspired' color palette with navy, red, and white.
- − Text rendering is messy with several misspelled words like 'LIAUNUCLON' and 'MEON'.
- − The layout is somewhat cluttered and lacks a logical directional flow.
FLUX1.1 [pro] Ultra
- + Achieved a more professional 'modern vector' aesthetic with clean icons and layout.
- + High-quality typography and composition that feels like a real infographic.
- + Consistent iconography and flat design elements.
- − Failed the specific step instructions, grouping icons in a confusing order (1, 2, 6).
- − Most of the body text is illegible 'lorem ipsum' style gibberish.
- − Included a rocket landing vertically like a SpaceX rocket instead of the requested Lunar Module.
Verdict: FLUX.2 [dev] Flash followed the thematic instructions and specific steps much better, including specific mission details like the crew names, whereas FLUX1.1 [pro] Ultra failed the logical sequence and depicted incorrect spacecraft for the era. However, FLUX1.1 [pro] Ultra produced a significantly more professional-looking vector art style, while FLUX.2 [dev] Flash had severe issues with text spelling and layout clarity.
Explore each model
Black Forest Labs' ultra-high resolution image generation model, an enhanced version of FLUX1.1 [pro] optimized for premium quality output