Black Forest Labs' ultra-high resolution image generation model, an enhanced version of FLUX1.1 [pro] optimized for premium quality output
Settled by community votes across 13 shared challenges, with an AI judge weighing in on each.
FLUX1.1 [pro] Ultra
#49 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] Ultra
0%
win rate
Ties
0%
Stable Diffusion 3.5 Large Turbo
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] Ultra
- + Perfect adherence to spatial relationships, specifically the red book sitting on top of the cube.
- + Highly realistic rendering of glass refraction and reflections.
- + Exceptional photographic quality with natural lighting and depth of field.
- − The blue sphere appears to be floating inside the cube rather than resting on a surface.
Stable Diffusion 3.5 Large Turbo
- + Crisp, clean lighting and sharp details on the wooden texture.
- + Vibrant colors and a very clean graphic style.
- − Failed the spatial instruction by placing the red book inside the cube instead of on top.
- − The plant is positioned to the side rather than behind the cube, minimizing the intended refraction effect.
- − The glass construction with black framing was not requested and feels less like a simple glass cube.
Verdict: FLUX1.1 [pro] Ultra followed every instruction accurately, including the complex spatial arrangement of objects. Stable Diffusion 3.5 Large Turbo failed to place the book on top of the cube, putting it inside instead, which significantly impacted its prompt adherence. FLUX1.1 [pro] Ultra also provided a much more realistic, photographic aesthetic compared to the CG-like appearance of the other model.
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] Ultra
- + Excellent adherence to the 'motion blur' request with a realistic long exposure effect on the passing car.
- + Superior material realism, especially the wet pavement reflections and natural skin textures.
- + Highly coherent bicycle anatomy and proportional human anatomy.
- − The man appears to be standing or pushing the bike rather than actively 'repairing' it.
Stable Diffusion 3.5 Large Turbo
- + Successfully captures the pose of an elderly man leaning over to work on the bike.
- + Good focus on the red bicycle as the central element.
- − Fails the 'motion blur' requirement entirely, with static cars in the background.
- − Significant anatomical distortions, especially the man's hands and the attachment of his arm to his body.
- − Lacks the cinematic lighting and wet pavement reflections requested.
Verdict: FLUX1.1 [pro] Ultra is the clear winner as it successfully incorporates complex prompt elements like motion blur and wet pavement reflections while maintaining high photorealism. Stable Diffusion 3.5 Large Turbo suffers from significant anatomical errors and fails to execute the requested environmental effects and cinematic framing.
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] Ultra
- + Captures the cinematic torchlight effect perfectly with warm glints on the metal armor.
- + Highly realistic skin texture including fine pores, sweat, and subtle scars that look integrated.
- + Excellent adherence to all prompt details like the beads in the hair and the specific leather strap textures.
- − The composition is very tightly cropped, making the top of the head feel slightly cramped.
Stable Diffusion 3.5 Large Turbo
- + Solid interpretation of ornate engraved armor with clear patterns.
- + Good use of shallow depth of field for the background bokeh.
- − The skin and hair have a distinct 'AI plastic' look, lacking the requested lifelike texture.
- − The 'scars' look more like smeared red paint rather than realistic wounds or healed tissue.
- − Failed to include the requested beads in the braided hair.
Verdict: FLUX1.1 [pro] Ultra produced a significantly more realistic and technically superior image, excelling in skin texture and the interplay of torchlight on metal. Stable Diffusion 3.5 Large Turbo followed the general layout but failed to include specific details like hair beads and suffered from a flat, digital-looking finish that lacked the raw 'battle-worn' realism of the competitor.
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] Ultra
- + Excellent typography with legible headers and item descriptions
- + Clean professional layout that looks like a real-world menu mockup
- + Consistent photographic style for food items
- − Minor spelling errors (e.g., 'Pizzzans' and 'Mians')
- − The grid of images is a bit cluttered in the center section
Stable Diffusion 3.5 Large Turbo
- + Very vibrant and colorful food photography
- + High-contrast visual appeal
- + Clear grid-based organization for food photos
- − The food photos look more like abstract digital art than real food
- − Text is largely illegible/gibberish beyond the headers
- − The 'Mians' header is misspelled and the layout is less practical
Verdict: FLUX1.1 [pro] Ultra produces a highly professional and realistic menu design that follows the prompt's structural requirements for sections and professional typography. Stable Diffusion 3.5 Large Turbo creates a more vibrant, artistic layout, but fails on text legibility and practical menu organization. FLUX1.1 is the winner for its superior composition and realistic implementation of a graphic design task.
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] Ultra
- + Excellent text rendering and placement of all required phrases.
- + Highly detailed and realistic burger textures.
- + Followed the layout instructions perfectly, including the exploded view and charcoal background.
- − The floating brown chunks around the burger are slightly ambiguous in nature.
- − Small artifact text appeared at the very bottom corners.
Stable Diffusion 3.5 Large Turbo
- + Dynamic fire effects and glowing embers create a strong atmosphere.
- + Vibrant colors in the burger toppings.
- − Failed to include any of the requested text.
- − Did not provide an 'exploded' view; the burger is mostly assembled.
- − Lower level of photorealism, appearing more like a digital illustration.
Verdict: FLUX1.1 [pro] Ultra followed the prompt near-perfectly, successfully integrating the complex text requirements and the 'exploded' layout. Stable Diffusion 3.5 Large Turbo failed to include the requested text and did not adhere to the 'exploded' component instruction, resulting in a less accurate and less useful advertisement image.
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] Ultra
- + Excellent chalk texture and realistic handwritten style.
- + Adhered well to the requested text and pricing.
- + High composition realism with subtle chalk dust and authentic wooden frame.
- − Included significant repetitive gibberish at the bottom.
- − Misspelled 'Truffle' as 'Trufflle' and 'Mushroom' as 'mushroomm'.
Stable Diffusion 3.5 Large Turbo
- + Bright, clean, and balanced composition.
- + Correctly followed the cursive style for the header.
- + Captures the 'cozy café' atmosphere with surrounding plants and lighting.
- − Significant spelling errors throughout all menu items.
- − Text looks like a digital font rather than authentic hand-drawn chalk.
- − Failed to follow the requested date and price details.
Verdict: FLUX1.1 [pro] Ultra produced a far more realistic image that captured the soul of a chalkboard, including the physical texture of chalk and more accurate (though notably repetitive) text. Stable Diffusion 3.5 Large Turbo created a visually pleasing graphic, but the text was mostly illegible and felt like a digital overlay rather than a handwritten board.
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] Ultra
- + Excellent visual clarity and cinematic composition.
- + Highly detailed rendering of the horse's fur and the planet's atmosphere.
- + Complex background with satellites and depth.
- − Failed the logic constraint; the astronaut is riding the horse, not the other way around.
Stable Diffusion 3.5 Large Turbo
- + Sharp lighting and clean subject isolation.
- + Good textures on the spacesuit and horse hair.
- − Failed the logic constraint; the astronaut is riding the horse.
- − Unusual shadow/dust trail artifact under the horse that feels out of place for space.
- − Lower overall complexity and detail compared to the competitor.
Verdict: Both models failed the specific prompt instruction to place the horse on top of the astronaut, instead defaulting to the cliché of an astronaut riding a horse. FLUX1.1 [pro] Ultra is the clear winner for its superior cinematic quality, intricate background details, and more realistic rendering of the horse.
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] Ultra
- + Excellent fur texture and lighting on the capybara
- + High detail in the cityscape and reflective surfaces
- + Correct attire for both characters
- − Confused spatial composition with the passenger appearing to sit in front of the driver
- − The steering wheel and hands/paws are mangled and fused together
Stable Diffusion 3.5 Large Turbo
- + Natural and correct spatial arrangement with passenger in the back seat
- + Better grasp of the capybara's anatomy and paw placement on the wheel
- + Clean rendering of the taxi driver cap and jacket
- − The passenger's phone is not visible as requested
- − Lower texture detail on the passenger compared to the capybara
Verdict: While FLUX1.1 [pro] Ultra has superior texture and lighting, it fails the basic composition of the scene by placing the passenger in front of the driver and creating a mess of AI artifacts around the steering wheel. Stable Diffusion 3.5 Large Turbo correctly places the capybara in the driver's seat and the human in the back, making it the more coherent and usable image despite missing the phone detail.
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] Ultra
- + Excellent typography rendering with almost no spelling errors
- + Complex, detailed border composition using thorns and scrolls as requested
- + Stronger gothic aesthetic and moody atmosphere
- − Includes some redundant, garbled text below the main banner banner
- − The title text omitted the word 'Party'
Stable Diffusion 3.5 Large Turbo
- + Features a sharp, high-contrast jack-o-lantern
- + Follows the border theme with cobwebs and thorns
- − Missed the majority of the event details like date, time, and location
- − The title text is incomplete and ends with a typo ('Partyj')
- − Lacks the requested scroll banner and elegant gothic title style
Verdict: FLUX1.1 [pro] Ultra is the clear winner as it successfully rendered nearly the entire text content, including the specific date and location. While it had some minor text duplication, Stable Diffusion 3.5 Large Turbo failed to include any of the bottom event details and had significant typos in the main title.
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] Ultra
- + Excellent typography with perfect spelling and alignment.
- + High-quality subtle PBR textures, especially on the salmon and rice grains.
- + Captures a clean, professional isometric aesthetic with a soft color palette.
- − Includes excessive extra elements like the plant and small bug which were not requested.
- − The 'JAPAN' text is placed in the background rather than being a physical part of the miniature scene.
Stable Diffusion 3.5 Large Turbo
- + Successfully incorporates the text and flag as physical objects within the diorama base.
- + Good adherence to the 45-degree isometric perspective.
- − Spelling error in the text, displaying 'SIIHI' instead of 'SUSHI'.
- − The flag design is incorrect, looking more like a generic banner than the Japanese flag.
- − Texture quality is a bit flat and plastic-like compared to the other model.
Verdict: FLUX1.1 [pro] Ultra is the clear winner due to its superior rendering, refined textures, and perfect spelling, creating a highly professional-looking graphic. While Stable Diffusion 3.5 Large Turbo creatively integrated the text into the scene as 3D objects, the spelling error and lower fidelity of the materials make it less successful overall.
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] Ultra
- + Perfectly captures all four requested animals (dog, cat, bunny, fox).
- + Exceptional lighting with golden sunrise tones and visible god rays.
- + Superior fur texture and expressive, clear eyes that match the prompt exactly.
- − The animals look slightly too similar in facial structure, leaning toward a stylized 'adorable' look.
- − The butterflies are somewhat repetitive in color and shape.
Stable Diffusion 3.5 Large Turbo
- + Strong color contrast with vibrant butterflies.
- + Decent fur texture on the dog's head.
- − Failed to include the requested baby bunny and red fox kit, appearing to merge them into hybrid animals.
- − Anatomical glitches, such as the cat appearing to have extra paws or being fused into the dog.
- − Lacks the 'hyper-photorealistic' quality, looking more like a digital painting.
Verdict: FLUX1.1 [pro] Ultra followed the complex prompt perfectly, including all four specific animals with high-quality textures and beautiful atmospheric lighting. Stable Diffusion 3.5 Large Turbo failed on prompt adherence, missing two of the four animals and producing anatomical errors where the creatures overlap. FLUX1.1 is the clear winner for its superior composition, realism, and adherence to the character list.
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] Ultra
- + Excellent vector emblem style with professional balance
- + Highly legible typography that feels authentic to a vintage brand
- + Sophisticated use of the warm brown and cream color palette
- − Spelling error in the main name ('Framilian' instead of 'Florian')
Stable Diffusion 3.5 Large Turbo
- + Successfully spelled the name closer to the prompt, though with an extra 'e'
- + Strong vintage texture on the background
- + Creative interpretation of a coffee-mug cloche hybrid
- − Poor typography rendering with overlapping letters in 'Florian'
- − The banner and central icon are slightly off-center and asymmetrical
- − Vector style is less refined with inconsistent line weights
Verdict: FLUX1.1 [pro] Ultra produces a much more professional and aesthetically pleasing logo design that perfectly captures the vector emblem aesthetic requested, despite a spelling hallucination. Stable Diffusion 3.5 Large Turbo struggles with basic layout, symmetry, and text rendering, resulting in a cluttered and less polished appearance. FLUX's superior composition and clarity make it the more usable design overall.
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] Ultra
- + Excellent adherence to the chronological step-by-step layout requested
- + Clean, high-quality vector aesthetic with sharp lines
- + Accurately represents the requested NASA color palette
- − Nonsense filler text and spelling errors like 'The About Fing If'
- − Confused numbering and redundant labeling towards the landing stage
Stable Diffusion 3.5 Large Turbo
- + Strong retro NASA-inspired color grading
- + Pleasing graphic composition with a clear focal point
- + Readable, albeit slightly misspelled, main headers
- − Failed to follow the requested 6-step structure entirely
- − Illegible garbled text in the body sections
- − Stylistically feels more like a poster than a functional infographic
Verdict: FLUX1.1 [pro] Ultra followed the complex instructional prompt much better, providing all six requested stages of the mission in a logical layout. Stable Diffusion 3.5 Large Turbo produced a visually appealing retro poster but failed to include the specific icons and sequential steps requested, resulting in a less useful infographic.
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