Stability AI

Stable Diffusion 3.5 Medium

AI Image Generation Model

Mode:

All Text to Image Image Edit

Image

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

Gallery

15 items

The Stable Diffusion 3.5 Medium gallery contains 4 curated examples demonstrating the model's text-to-image capabilities and improved typography across diverse prompts.

AI image generated by Stable Diffusion 3.5 Medium — prompt: A wide, cinematic shot of a high-end boutique storefront at dusk. The shop’s elegant glass window features the name "Stable Diffusion 3.5 Medium" in sophisticated, gold-leaf typography across the pane. Inside, warm amber lighting illuminates a minimalist interior with marble pedestals and lush indoor ferns. The street outside is wet from a recent rain, reflecting the rich, vibrant glow of the store’s interior and the deep indigo twilight sky. Professional color grading, shallow depth of field, 16:9 aspect ratio.

A wide, cinematic shot of a high-end boutique storefront at dusk. The shop’s ...

AI image generated by Stable Diffusion 3.5 Medium — prompt: A hyper-realistic close-up of an elderly artisan's weathered hands meticulously carving intricate floral patterns into a dark walnut wood panel. Soft, natural morning light spills across the workbench, illuminating floating sawdust motes and the polished steel of a small chisel. Shallow depth of field with a blurred workshop background containing vintage hand tools and wood shavings, 8k resolution, cinematic lighting, earthy tones.

A hyper-realistic close-up of an elderly artisan's weathered hands meticulous...

AI image generated by Stable Diffusion 3.5 Medium — prompt: A hyper-realistic close-up of an elderly artisan's weathered hands meticulously carving intricate floral patterns into a dark walnut wood panel. Soft, cinematic morning light streams through a dusty workshop window, illuminating fine wood shavings and the polished steel of a chisel. Deep depth of field, 8k resolution, rustic textures, warm earthy tones, professional photography.

A hyper-realistic close-up of an elderly artisan's weathered hands meticulous...

AI image generated by Stable Diffusion 3.5 Medium — prompt: A vibrant, hand-painted wooden sign hanging above a cozy bakery that says "FRESH SOURDOUGH DAILY" in elegant gold script. In the blurred background, a capybara calmly balances a small loaf of bread on its head while walking past the shop window.

A vibrant, hand-painted wooden sign hanging above a cozy bakery that says "FR...

AI image generated by Stable Diffusion 3.5 Medium, ranked #24 of 72 in the "Adorable Baby Animals in Sunny Meadow" arena challenge — prompt: 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.

Arena challenge: Adorable Baby Animals in Sunny Meadow

Hyper-photorealistic scene of fluffy baby animals—a golden retriever puppy, t...

AI image generated by Stable Diffusion 3.5 Medium, ranked #18 of 69 in the "The Capybara Taxi Driver" arena challenge — prompt: 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.

Arena challenge: The Capybara Taxi Driver

Photorealistic scene inside a yellow New York taxi at night. A capybara is dr...

AI image generated by Stable Diffusion 3.5 Medium, ranked #30 of 69 in the "Modern Clean Menu" arena challenge — prompt: 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.

Arena challenge: Modern Clean Menu

Modern minimalist restaurant menu design, white background with colorful food...

AI image generated by Stable Diffusion 3.5 Medium, ranked #39 of 70 in the "Apollo 11: Journey to Tranquility" arena challenge — prompt: 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.

Arena challenge: Apollo 11: Journey to Tranquility

Create a clean, modern vector infographic poster about the Apollo 11 mission....

AI image generated by Stable Diffusion 3.5 Medium, ranked #48 of 69 in the "Magic Burger Explosion: Fiery Photorealism Challenge" arena challenge — prompt: 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.

Arena challenge: Magic Burger Explosion: Fiery Photorealism Challenge

Ad for 'Magic Burger'. Dynamic, exploded burger with all components (bun, pat...

AI image generated by Stable Diffusion 3.5 Medium, ranked #49 of 71 in the "Fantasy Warrior" arena challenge — prompt: 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.

Arena challenge: Fantasy Warrior

Close portrait of a battle-worn paladin in ornate engraved plate armor, hair ...

AI image generated by Stable Diffusion 3.5 Medium, ranked #57 of 70 in the "Geometric Composition" arena challenge — prompt: 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.

Arena challenge: Geometric Composition

A glass cube on a wooden table. Inside the cube is a small blue sphere. On to...

Arena challenge: Vintage Cafe Logo

Vintage minimalist restaurant logo for "Caffè Florian", retro cloche dome wit...

AI image generated by Stable Diffusion 3.5 Medium, ranked #53 of 70 in the "The Halloween Invitation" arena challenge — prompt: 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.

Arena challenge: The Halloween Invitation

Vintage gothic Halloween party invitation. Dark parchment poster, spooky bord...

AI image generated by Stable Diffusion 3.5 Medium, ranked #62 of 68 in the "Candid Street Photography" arena challenge — prompt: 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.

Arena challenge: Candid Street Photography

A candid street photo of an elderly Japanese man repairing a red bicycle in l...

AI image generated by Stable Diffusion 3.5 Medium, ranked #58 of 68 in the "The Reversed Rodeo" arena challenge — prompt: Horse riding astronaut in space — horse on top, not vice versa. Surreal, highly detailed, cinematic.

Arena challenge: The Reversed Rodeo

Horse riding astronaut in space — horse on top, not vice versa. Surreal, high...