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
#51 of 62 in Text-to-Image
Stable Diffusion 3.5 Medium
#58 of 62 in Text-to-Image
Where the votes landed
FLUX1.1 [pro] Ultra
0%
win rate
Ties
0%
Stable Diffusion 3.5 Medium
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
- + Excellent photorealism with realistic glass refraction and texture.
- + Perfect adherence to the lighting and placement instructions.
- + High-resolution details, including legible text on the book spine.
- − The sphere appears to be floating without a physical support, though this may be an intentional 'artistic' interpretation of being 'inside'.
Stable Diffusion 3.5 Medium
- + Successfully includes all requested elements in the correct configuration.
- + Captures the soft window light effectively.
- − The glass cube is poorly constructed with messy edges and inconsistent perspective.
- − Lower overall image quality with significant blurring and lack of fine detail.
Verdict: FLUX1.1 [pro] Ultra significantly outperforms Stable Diffusion 3.5 Medium in terms of realism, clarity, and spatial logic. While both models followed the prompt instructions, FLUX1.1 [pro] Ultra produced a professional-grade photograph with intricate glass details, whereas Stable Diffusion 3.5 Medium struggled with the geometry of the cube and textures of the book.
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 execution of motion blur from passing cars as requested.
- + Very high visual clarity and realistic skin and fabric textures.
- + Accurate bicycle anatomy and realistic rain reflections on the ground.
- − The framing is very clean and centered, lacking the 'imperfect framing' requested.
- − The lighting feels a bit too balanced, bordering on a professional studio look rather than a raw candid street photo.
Stable Diffusion 3.5 Medium
- + Strong adherence to the 'candid' and 'imperfect framing' prompt with a more naturalistic, raw street photography feel.
- + Effective use of shallow depth of field and a more convincing '50mm lens' aesthetic.
- + The rainfall is more clearly visible in the air compared to the other model.
- − Completely failed to include the motion blur from passing cars requested in the prompt.
- − The man's hands and face have significantly lower detail and some anatomical distortion.
- − The bicycle structure is slightly warped, particularly the handlebars and basket.
Verdict: FLUX1.1 [pro] Ultra produced a much higher quality image with impressive motion blur and technical polish, though it felt a bit too 'perfect' for a candid shot. Stable Diffusion 3.5 Medium captured the desired candid mood and imperfect framing better, but failed on the specific motion blur requirement and suffered from lower detail in the person's features. FLUX1.1 [pro] Ultra is the clear winner for its superior realism and adherence to complex prompt elements like motion blur.
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
- + Excellent adherence to the 'battle-worn' descriptor with visible sweat, grime, and authentic scarring.
- + Masterful lighting with realistic warm torchlight reflections on the metal and skin.
- + Superior rendering of the braided hair and individual beads as requested.
- − The depth of field is slightly shallower than requested, blurring some armor details.
- − The sparks in the background are somewhat muted compared to the prompt's focus on bokeh.
Stable Diffusion 3.5 Medium
- + Good interpretation of ornate engraving on the pauldrons and chestplate.
- + Effective use of bokeh sparks in the background to create atmosphere.
- + Solid facial symmetry and intense expression that fits a paladin character.
- − Failed to include the beads in the hair braids as specified in the prompt.
- − Skin texture looks a bit blotchy and digital compared to the realistic grime of Model A.
- − The lighting on the face feels a bit flat and less like a physical torch source.
Verdict: FLUX1.1 [pro] Ultra is the clear winner due to its superior realism and strict adherence to specific prompt details like the beads in the hair and the realistic 'battle-worn' texture of the skin. While Stable Diffusion 3.5 Medium produced a compelling character, it missed the bead detail and the lighting feels less integrated with the environment than FLUX.
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 clean, bolde sans-serif fonts
- + Realistic food photography that looks appetizing and professional
- + Modern, three-dimensional mockup presentation
- − Nonsensical text placeholders like 'Pizzzans' and 'Appet Love'
- − The food grid is slightly disorganized with overlapping elements
Stable Diffusion 3.5 Medium
- + Perfectly balanced grid layout following the prompt's structural request
- + Clearly defined sections for different food categories
- + Consistent flat-lay orientation for the food photography
- − Significant text artifacts and illegible font jaggedness
- − Poor resolution on the font rendering compared to the sharp layout
- − The fonts used are more decorative/rough than the 'bold sans-serif' requested
Verdict: FLUX1.1 [pro] Ultra produces a much higher quality final image with professional lighting and sharp, readable (albeit gibberish) text. Stable Diffusion 3.5 Medium followed the grid layout instructions more strictly but failed significantly on text rendering and overall image clarity.
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 typography with a glowing fiery effect and perfect spelling.
- + Highly detailed 'exploded' view that clearly separates components as requested.
- + Clean, professional composition suitable for a high-end advertisement.
- − The burger is scaled very tall, looking like multiple burgers stacked rather than one disassembled one.
- − The price is not inside a starburst as specified.
Stable Diffusion 3.5 Medium
- + Successfully included the starburst element for the price.
- + Dynamic flame background provides good contrast and warmth.
- − Failed the 'exploded' instruction; the burger is mostly assembled and floating rather than disassembled.
- − The text 'MAGIC BURGER' lacks the requested fiery, glowing effect and is too small.
- − Visible artifacts in the starburst and slightly muddy lighting on the burger patty.
Verdict: FLUX1.1 [pro] Ultra followed almost all prompt instructions with superior graphical fidelity and professional typography, though it missed the starburst requirement. Stable Diffusion 3.5 Medium included the starburst but failed significantly on the 'exploded burger' composition and the specific typographic effects. FLUX1.1 is the clear winner for its clarity, detail, and adherence to the high-energy advertisement aesthetic.
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-like texture and authentic handwriting style.
- + High level of readability for the main header and several menu items.
- + Realistic ambient lighting and chalkboard wooden frame.
- − Contains several repetition errors and gibberish lines in the mid-section.
- − Text alignment is somewhat messy and lacks the 'elegant cursive' requested for the title.
Stable Diffusion 3.5 Medium
- + Includes decorative chalk flourishes and varied sizes.
- + Better captures the 'elegant' aspect of the prompt's request for the title.
- − Extreme spelling errors and nonsensical words throughout the board.
- − Layout is cluttered and the text rendering is inconsistent.
- − Fails on the specific date and price details.
Verdict: FLUX1.1 [pro] Ultra produces a much more realistic image with convincing chalk textures and legible, if slightly repetitive, text. Stable Diffusion 3.5 Medium struggles significantly with spelling and coherence, making the menu largely unreadable despite a more decorative artistic style. FLUX1.1 is the clear winner for its superior prompt adherence and visual clarity.
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 cinematic lighting and high-resolution textures.
- + Dynamic composition with a sense of motion in the horse's mane and tail.
- + Highly detailed background featuring a curved Earth and celestial bodies.
- − Failed the specific spatial instruction; the astronaut is riding the horse.
Stable Diffusion 3.5 Medium
- + Clean, clear subjects with good contrast against the starfield.
- + Good anatomical representation of the astronaut's suit.
- − Failed the specific spatial instruction; the astronaut is riding the horse.
- − The horse's legs show anatomical artifacts and appear stiff.
- − The composition is less cinematic and looks flatter than the alternative.
Verdict: Both FLUX1.1 [pro] Ultra and Stable Diffusion 3.5 Medium failed the negative constraint to have the horse on top of the astronaut, both reverting to the standard trope of an astronaut riding a horse. FLUX1.1 [pro] Ultra is the clear winner however, as its visual quality, lighting, and cinematic scale are vastly superior to the stiff and slightly distorted output of Stable Diffusion 3.5 Medium.
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 photographic lighting and textures on both the animal and human.
- + Successful inclusion of specific details like the yellow taxi cap and dark jacket.
- + Strong bokeh effect of Manhattan streets in the background.
- − The capybara is in the passenger seat and the woman is in the driver's seat, failing the core layout requirement.
- − The capybara's paws are not on the steering wheel.
Stable Diffusion 3.5 Medium
- + Correctly places the capybara in the driver's seat and the woman in the back seat.
- + Follows the instruction to have both paws on the steering wheel.
- + Captures the professional expression and clothing requested.
- − The woman is not looking at a phone as requested.
- − The human face in the background is slightly distorted/blurry compared to the foreground.
- − The overall image clarity is lower than the competitor.
Verdict: While FLUX1.1 [pro] Ultra produces a much more realistic and high-quality image, it completely fails the prompt's spatial logic by placing the human in the driver's seat and the capybara as the passenger. Stable Diffusion 3.5 Medium, despite lower resolution and missing the 'phone' detail, accurately depicts the capybara as the driver with its paws on the wheel, making it the better choice for instruction following.
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 with nearly perfect spelling and formatting
- + Sophisticated composition with a central glowing jack-o-lantern and thorn border
- + High visual clarity and professional cinematic lighting
- − Includes a redundant, misspelled line of text below the banner
- − Omitted the word 'Party' from the main title
Stable Diffusion 3.5 Medium
- + Successfully included multiple jack-o-lanterns and prominent webs
- + Colors are vibrant and evoke a classic Halloween aesthetic
- − Significant spelling errors and gibberish text throughout
- − Layout is cluttered and lacks the 'polished' feel requested
- − Garbled dates and locations (e.g., 'The Aches' instead of 'The Arches')
Verdict: FLUX1.1 [pro] Ultra is the clear winner due to its superior text rendering and balanced composition. While it had a minor repetition error in the text, it far outperformed Stable Diffusion 3.5 Medium, which struggled with basic legibility and spelling of the required event details.
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 adherence to the isometric miniature diorama style.
- + High-quality 3D render look with clean textures and lighting.
- + Accurate text placement and includes requested flag icon.
- − Added an unnecessary tiny insect-like detail on the wooden board.
- − Salmon texture looks slightly too plastic compared to 'realistic PBR'.
Stable Diffusion 3.5 Medium
- + Bold, clean typography for the word 'SUSHI'.
- + Realistic textures on the nori and roe.
- − Failed to create an isometric miniature diorama base.
- − Missing the flag icon and the word 'JAPAN' is less prominent than requested.
- − Typography has a slight artifact/overlap on the 'S' and 'i'.
Verdict: FLUX1.1 [pro] Ultra followed the complex scene requirements much more effectively, creating a complete isometric diorama with all requested elements including the flag icon and high-clarity miniature style. Stable Diffusion 3.5 Medium produced a more basic product shot that missed the diorama base and several layout specifications.
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
- + Excellent adherence to the prompt by including all four specified animals.
- + Superior fur texture and soft lighting that matches the requested aesthetic.
- + Better composition with a clear focus on the animals interacting with butterflies.
- − The animals look a bit more like stuffed toys than 'hyper-photorealistic' real animals.
Stable Diffusion 3.5 Medium
- + Natural and vibrant color palette with high contrast.
- + Good interpretation of the golden sunrise light.
- − Failed to include the baby bunny, only showing three animals.
- − The kitten has unusual, rabbit-like ears, creating anatomical confusion.
- − The fur textures look slightly over-sharpened and digital.
Verdict: FLUX1.1 [pro] Ultra is the clear winner as it successfully included all four requested animals (puppy, kitten, bunny, and fox) whereas Stable Diffusion 3.5 Medium missed the bunny entirely. FLUX1.1 also achieved a much softer, more magical atmosphere that better suits the 'wholesome' and 'soft fur' requirements of the prompt.
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 clean lines and balanced composition.
- + Correctly followed the color palette and texture requirements.
- + Professional typography and layout that feels like a real logo.
- − Misspelled 'Florian' as 'Framlian'.
- − The steam effect is a bit singular and basic.
Stable Diffusion 3.5 Medium
- + Successfully captured the vintage hand-drawn illustration style.
- + Correctly spelled 'Caffe' and got closer to the main name 'Florrian'.
- + Included a more elaborate banner and supporting coffee cup element.
- − Misspelled 'Florian' as 'Florrian' and '1720' as '170'.
- − The cloche dome shape is distorted and looks more like a round sack.
- − The banner at the bottom contains gibberish text.
Verdict: FLUX1.1 [pro] Ultra produced a much higher quality vector logo that perfectly fits the 'minimalist restaurant logo' prompt, despite a spelling error in the primary name. Stable Diffusion 3.5 Medium struggled with the geometry of the cloche and technical details of the text, resulting in a cluttered and less professional appearance 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 vector aesthetic with clean, professional icons.
- + Adheres to the NASA color palette perfectly.
- + Includes all requested steps in a logical flow from top to bottom.
- − Text contains a significant amount of gibberish despite clear headers.
- − The numbering and labeling logic becomes confusing halfway through the graphic.
Stable Diffusion 3.5 Medium
- + Follows the NASA color scheme well.
- + Good use of space with a circular trajectory motif.
- − Icons do not match the specific prompts (e.g., Saturn V icon is missing).
- − Image quality is lower with blurry text and messy line work.
- − The steps are out of order and don't match the historical mission progression requested.
Verdict: FLUX1.1 [pro] Ultra produced a much higher quality infographic that actually looks like a professional vector poster, whereas Stable Diffusion 3.5 Medium produced a cluttered image with significant artifacts. FLUX1.1 [pro] Ultra followed the complex instructional steps much more accurately, creating distinct icons for launch and orbit, even if the fine-print text is illegible.
Explore each model
Stability AI's 2.5-billion parameter Multimodal Diffusion Transformer with improvements (MMDiT-X) text-to-image model optimized for consumer hardware, featuring improved image quality, typography, and complex prompt understanding