Black Forest Labs' enhanced 12-billion parameter flow transformer with 6x faster generation than FLUX.1 [pro], delivering superior composition, detail, and artistic fidelity
Settled by community votes across 13 shared challenges, with an AI judge weighing in on each.
FLUX1.1 [pro]
#50 of 62 in Text-to-Image
Stable Diffusion 3.5 Large Turbo
#61 of 62 in Text-to-Image
Where the votes landed
FLUX1.1 [pro]
100.0%
win rate
Ties
0.0%
Stable Diffusion 3.5 Large Turbo
0.0%
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
FLUX1.1 [pro]
- + Excellent adherence to the spatial requirements of the prompt.
- + Highly realistic textures, especially the thick glass edges and book cover.
- + Beautiful soft lighting and a natural depth of field.
- − The glass enclosure is technically a cuboid rather than a perfect cube.
Stable Diffusion 3.5 Large Turbo
- + Clean, sharp rendering and modern aesthetic.
- + Correct placement of the plant behind the glass.
- − Failed the spatial cue; the book is inside the glass rather than on top of it.
- − The glass frame has black metal borders which weren't requested, making it look like a terrarium.
- − The lighting on the table looks somewhat synthetic compared to Model A.
Verdict: FLUX1.1 [pro] followed the complex spatial instructions perfectly, placing the sphere inside and the book correctly on top. Stable Diffusion 3.5 Large Turbo failed the spatial arrangement by placing both the book and the sphere inside the glass, while also adding unrequested black frames to the cube.
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
FLUX1.1 [pro]
- + Excellent atmospheric lighting and wet pavement reflections.
- + Realistic skin texture and age-appropriate details on the man.
- + Captured the 'candid street photo' aesthetic with cinematic depth of field.
- − The bicycle structure is warped and physically impossible.
- − A strange, detached metallic object appears on the ground behind the man's feet.
Stable Diffusion 3.5 Large Turbo
- + The bicycle frame and components are much more coherent and recognizable.
- + Follows the 'red bicycle' requirement clearly.
- − The 'rain' looks like vertical white lines and lacks environmental integration.
- − Skin texture and lighting look flat and digital compared to Model A.
- − Fails the motion blur and candid aesthetic requirements.
Verdict: FLUX1.1 [pro] significantly outperforms Stable Diffusion 3.5 Large Turbo in terms of atmosphere, lighting, and realistic texture, perfectly capturing the cinematic street photo vibe requested. While the bicycle in FLUX1.1 [pro] is structurally messy, Stable Diffusion 3.5 Large Turbo produces a far more 'artificial' image with poor rain effects and a lack of depth.
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
FLUX1.1 [pro]
- + Outstanding skin texture with realistic pores and fine hair
- + Strong atmosphere with cinematic lighting and bokeh effects
- + Exquisite detail on the engraved armor and underlying textures
- − Small beads in the hair are present but could be more distinct
- − The dirt/scars lean more towards a freckled appearance in some areas
Stable Diffusion 3.5 Large Turbo
- + Clear representation of the braids requested in the prompt
- + Good color contrast between the green underlayer and the ornate metal armor
- + Distinct and identifiable scars on the face
- − Skin has a plastic, overly-smooth 'CG' look
- − Hair rendering is thick and lacks separate strands, looking rigid
- − Composition feels less 'close portrait' and more medium-shot
Verdict: FLUX1.1 [pro] significantly outperforms Stable Diffusion 3.5 Large Turbo in terms of realism and texture, delivering a truly lifelike portrait with cinematic depth. While Stable Diffusion 3.5 captures specific elements like the braids more clearly, it suffers from a dated, digital look with flat skin and hair rendering compared to the high-fidelity output of FLUX1.1 [pro].
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
FLUX1.1 [pro]
- + Excellent professional mock-up presentation with realistic cutlery and shadows.
- + Clean font choice and layout that maintains a consistent branding style.
- + Includes all requested sections with logical hierarchical organization.
- − The food photos in the grid are somewhat small and overlapping at the edges.
- − Some of the minor descriptive text is illegible gibberish.
Stable Diffusion 3.5 Large Turbo
- + Features a very clear and vibrant food photo grid as requested.
- + The typography for the category headers (Pizza, Mians) is bold and clear.
- + High saturation and contrast make the food items pop against the white background.
- − The 'Mians' header contains a typo (should be Mains).
- − The composition feels like a scattered collection of assets rather than a cohesive menu design.
- − The food items have an unnatural, plastic-like AI quality.
Verdict: FLUX1.1 [pro] produced a far more professional and usable design layout, successfully integrating the menu text and food photography into a realistic mock-up. Stable Diffusion 3.5 Large Turbo had better adherence to the 'grid' request for photos, but the composition was messy and the text contained spelling errors.
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
FLUX1.1 [pro]
- + Excellent text rendering with all requested phrases present and legible.
- + Photorealistic textures on the bun and meat patties.
- + Good interpretation of the glowing embers and fiery background.
- − The burger is not truly 'exploded' with all components suspended; it is mostly assembled.
- − The text style is neon and 2D white rather than the requested 'fiery, glowing effect'.
- − Missing the starburst element for the price.
Stable Diffusion 3.5 Large Turbo
- + Stronger sense of a fiery, dynamic atmosphere with smoke and flames.
- + Vibrant lighting and colors that fit the 'Magic Burger' theme.
- − Completely failed to include any of the requested text elements.
- − The burger components are not suspended in mid-air as requested; they are stacked.
- − The bottom of the burger appears to be melting or dripping in an unappealing way.
Verdict: FLUX1.1 [pro] is the clear winner as it successfully rendered all the complex text requirements, which Stable Diffusion 3.5 Large Turbo omitted entirely. While neither model fully achieved the 'exploded' view of individual components suspended in air, FLUX1.1 [pro] provided a much higher level of photorealistic detail and better adherence to the advertising 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
FLUX1.1 [pro]
- + Excellent text legibility and accuracy for most of the prompt.
- + Superior chalk texture and realistic handwriting variation.
- + Highly cohesive background atmosphere that matches the 'cozy cafe' description.
- − Introduced spelling errors like 'Herbss' and 'Chipkies'.
- − Failed to keep the octopus dish as a single item, splitting it into two separate lines with different prices.
Stable Diffusion 3.5 Large Turbo
- + Clean symmetrical layout with pleasant lighting.
- + Followed the instruction for the date fairly closely despite the year being cut off.
- − Significant spelling failures across all menu items (e.g., 'trulale', 'ocotpgs', 'risctto').
- − The text looks more like a digital font or vector art than actual chalk.
- − Layout is messy with lines of text overlapping or ending abruptly.
Verdict: FLUX1.1 [pro] significantly outperforms Stable Diffusion 3.5 Large Turbo in text rendering and stylistic adherence. While FLUX1.1 [pro] made minor spelling errors at the end of the menu, the texture is authentically chalk-like and the café environment is more realistic, whereas Stable Diffusion 3.5 Large Turbo struggled with basic legibility and failed to capture the requested chalk texture.
The Reversed Rodeo
Text-to-Image“Horse riding astronaut in space — horse on top, not vice versa. Surreal, highly detailed, cinematic.”
AI Judge Analysis
FLUX1.1 [pro]
- + Excellent cinematic lighting and atmospheric depth in the background.
- + Highly detailed texture on the spacesuit and horse's mane.
- + Dynamic composition with a sense of motion.
- − Failed the negative constraint to have the horse on top of the astronaut.
- − Anatomical issues with the horse's front legs appearing merged or strangely jointed.
Stable Diffusion 3.5 Large Turbo
- + Clean, graphic visual style.
- + Clear rendering of the astronaut's equipment.
- − Failed the negative constraint to have the horse on top of the astronaut.
- − Strong anatomical artifacts, particularly the horse having five or more legs/hooves at the bottom.
- − Composition feels flat and lacks the requested surreal/cinematic quality.
Verdict: Both FLUX1.1 [pro] and Stable Diffusion 3.5 Large Turbo failed the logic test of placing the 'horse on top' of the astronaut, instead opting for the cliche of an astronaut riding a horse. FLUX1.1 [pro] is the clear winner as it produced a much higher quality, cinematic image, whereas Stable Diffusion 3.5 Large Turbo suffered from significant anatomical errors, including extra legs.
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
FLUX1.1 [pro]
- + Excellent photographic lighting and depth of field
- + High resolution texture on the capybara's fur
- + Accurately captures the bored expression of the passenger
- − The capybara is not holding the steering wheel
- − Composition places the passenger in the front passenger seat rather than the back seat
Stable Diffusion 3.5 Large Turbo
- + Successfully shows the capybara with paws on the steering wheel
- + Better adherence to the 'back seat' positioning for the passenger
- + Sharp rendering of the capybara's face and jacket
- − The passenger's face is blurry and lacks detail
- − Text on the hat is slightly garbled compared to Model A
- − The capybara's paws look somewhat human-like/distorted
Verdict: FLUX1.1 [pro] produces a much more cinematically beautiful image with superior lighting and texture, though it fails on the spatial requirement of putting the passenger in the back seat and having the driver hold the wheel. Stable Diffusion 3.5 Large Turbo adheres better to the mechanical prompts (paws on wheel, passenger in back) but suffers from poor facial rendering on the human and a less realistic overall feel.
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
FLUX1.1 [pro]
- + Excellent cinematic lighting and atmospheric composition.
- + Correctly included all requested text elements, including date, time, and location.
- + High detail in the thorny border and twisted tree silhouettes.
- − The text contains several typos and repetitions at the bottom.
- − The image follows a portrait aspect ratio instead of the requested square format.
Stable Diffusion 3.5 Large Turbo
- + Correctly followed the square format request.
- + Clear rendering of the Central jack-o-lantern and bats.
- + Interesting gothic border incorporating spiderwebs and thorns.
- − Failed to include the specific event details (Date, Time, Location).
- − Missing the requested scroll banner.
- − The lighting is flat compared to the requested 'cinematic' style.
Verdict: FLUX1.1 [pro] significantly outperforms in artistic style and prompt adherence, capturing the moody, cinematic aesthetic and including all requested text, despite some typos. Stable Diffusion 3.5 Large Turbo followed the format requirement but failed to include more than half of the specific text content requested in the prompt.
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
FLUX1.1 [pro]
- + Excellent text rendering with clean 'JAPAN' and 'SUSHI' typography.
- + High-quality soft, refined 3D textures that perfectly match the cartoon-isometric style.
- + Clean adherence to the light blue background prompt.
- − Failed to include the requested small flag icon.
Stable Diffusion 3.5 Large Turbo
- + Included a flag icon as requested.
- + Good 3D isometric perspective and modeling.
- − Misspelled sushi as 'SIIHI' on the plate.
- − The text is floating and angled rather than clean and at the top-center as requested.
- − The background is a gradient and darker than the requested 'solid light blue'.
Verdict: FLUX1.1 [pro] followed the stylistic and composition instructions much better, producing a clean, professional-looking diorama with perfect text. Stable Diffusion 3.5 Large Turbo struggled with spelling, background color, and text placement, despite capturing the flag icon that FLUX1.1 missed.
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
FLUX1.1 [pro]
- + Excellent fur texture rendering with a soft, backlit glow.
- + Whimsical lighting and atmosphere that perfectly captures the 'god rays' and 'wholesome vibe'.
- + Better adherence to the 'golden retriever' and 'tabby' descriptions.
- − Missing the fourth animal (red fox kit) requested in the prompt.
- − The 'butterflies' look more like glowing sparks or petals than insects.
Stable Diffusion 3.5 Large Turbo
- + Higher contrast and vibrant colors that make the subjects pop.
- + Closer to the request for four animals, though the species identification is ambiguous.
- + Includes clear butterfly shapes with distinct wings.
- − Anatomical errors including a fused body between the dog and the kitten on the left.
- − The lighting feels artificial and lacks the requested hyper-photorealistic quality.
- − The fur texture looks more like digital painting/vector art than a photograph.
Verdict: FLUX1.1 [pro] produced a significantly more cohesive and visually pleasing image with superior lighting and texture, despite failing to include the fox kit. Stable Diffusion 3.5 Large Turbo struggled with anatomical coherence, resulting in a disturbing merge of the puppy and kitten's bodies, and failed to achieve a photorealistic look.
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
FLUX1.1 [pro]
- + Excellent vintage engraving style with fine cross-hatching
- + Sophisticated decorative border and balanced composition
- + Beautiful minimalist interpretation of the cloche dome
- − Significant spelling errors: 'Caufé' and 'FRATILIAN'
- − Steam detail is a bit thin and wispy compared to the solid lines
Stable Diffusion 3.5 Large Turbo
- + Near-perfect spelling of the name and establishment date
- + Strong vector-style execution with bold contrast
- + Effective use of the 'warm brown and cream' color palette
- − The cloche dome is merged awkwardly with a coffee mug handle
- − Less 'minimalist' than requested, feeling more like a heavy illustration
- − Minor artifact on the final 'n' of the name
Verdict: While FLUX1.1 [pro] captures a much more authentic vintage aesthetic and elegant composition, it fails completely on text accuracy, misspelling the primary brand name. Stable Diffusion 3.5 Large Turbo produces a functional logo with correct spelling and high clarity, though its design choice to merge a cloche with a mug is slightly literal and cluttered compared to the requested minimalism.
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
FLUX1.1 [pro]
- + Excellent adherence to the clean, flat-vector infographic style
- + Follows the sequenced steps more logically with numbered icons
- + Clearer text rendering for the main title and most subheaders
- − Step numbering is repetitive and confusing (multiple 1s and 2s)
- − Iconography for specific stages like Earth Orbit and Lunar Orbit is generic
Stable Diffusion 3.5 Large Turbo
- + Stronger NASA-inspired aesthetic with more complex compositions
- + Good use of the requested color palette
- + Includes a more detailed lunar surface illustration
- − Failed to include all 6 specific steps requested in the prompt
- − Text rendering is poor with many typos and placeholder-like jargon
- − Overall layout is cluttered and less functional as an informative infographic
Verdict: FLUX1.1 [pro] followed the structural requirements of the prompt much better, providing a clear infographic layout with distinct icons for the mission steps. Stable Diffusion 3.5 Large Turbo captured a more atmospheric vintage NASA aesthetic, but failed significantly on text legibility and the specific sequencing of the six mission phases.
Explore each model
Distilled version of SD 3.5 Large that generates high-quality images in just 4 steps, offering faster inference and reduced costs