
Open-weights image model
Stable Diffusion v3.5 Large AI image generator
The Stable Diffusion that follows detailed prompts most closely, at a budget price.
No installation. No credit card. Private by default.
At a glance
Stable Diffusion v3.5 Large is an open-weights image model that Mage hosts on its own GPUs. On Mage it makes images from a prompt or one reference image. It costs from 10 Gems (about $0.01) per image and runs unlimited from the Basic plan, and new accounts get 300 free Gems to start.
- 10Gems per image, from
- $0.01About, in US dollars
- BasicUnlimited from
- 1Reference images, up to
Overview
What is Stable Diffusion v3.5 Large?
Stable Diffusion 3.5 Large is the Stable Diffusion that follows detailed prompts most closely, hosted on Mage's GPUs.
It handles colors, counts, and arrangements well for its price, with a negative prompt and one optional input image.
Samples
Made with Stable Diffusion v3.5 Large
Generated on Mage with Stable Diffusion v3.5 Large. A prompt under a sample is the exact prompt that made it.

Miniature worldPrompt: a glass terrarium on a sunny windowsill holding a tiny tropical island with one palm tree, a hammock and a miniature waterfall, tilt-shift photo

Counted, colored objectsPrompt: three hot air balloons, one red, one yellow, and one striped blue and white, floating over a misty valley of vineyards at sunrise

Watercolor storybookPrompt: a watercolor illustration of a fox reading a book under a mushroom umbrella in the rain
Strengths
What Stable Diffusion v3.5 Large does best
Best at
- Prompts with several specific objects and colors
- Tilt-shift, miniature, and playful scenes
- Watercolor and illustrated styles
- Detailed images on a budget
Trade-offs
- Less photoreal than Guava or Mango
- No Characters or references
Prompt guide
How to prompt Stable Diffusion v3.5 Large
Tips that work on this model. The prompts under the samples above are good places to start.
Tips
- List the objects with their colors ("one red, one yellow, one striped blue and white").
- Describe the arrangement plainly: in front, behind, on the left.
- Name the medium (watercolor illustration, tilt-shift photo) at the start or the end.
- Use the negative prompt for clutter you do not want.
Specs
Stable Diffusion v3.5 Large specs and inputs
| Made by | Open weights, hosted on Mage's GPUs |
|---|---|
| Output | Images |
| Aspect ratios | 21:9, 16:9, 3:2, 5:4, 1:1, 4:5, 2:3, 9:16, 9:21 |
| Image inputs | One reference image |
| Video input | No |
| Mentions by @handle | No |
| Where to use it | The Mage app, the Mage assistant, Claude and ChatGPT through the Mage MCP server, and the Mage API |
Pricing
Stable Diffusion v3.5 Large price and plans
Every price comes from the same pricing that bills your generations.
| Model | Setting | Gems | Per | USD | Basic | Pro | Pro Plus | Max |
|---|---|---|---|---|---|---|---|---|
| Stable Diffusion v3.5 Large | — | 10 | image | $0.01 | Unlimited | Unlimited | Unlimited | Unlimited |
Prices in Gems, and in US dollars at the list price of the 10,000 Gems pack ($10). Each plan column shows what that plan runs unlimited; anything else costs Gems. Other settings, such as quality levels and extra input images, can change the price.
FAQ
Stable Diffusion v3.5 Large questions
How much does Stable Diffusion v3.5 Large cost?
Can I use Stable Diffusion v3.5 Large unlimited?
Can I try Stable Diffusion v3.5 Large for free?
What can I give Stable Diffusion v3.5 Large as input?
Can I use Stable Diffusion v3.5 Large through an API, or in Claude and ChatGPT?
Is what I make with Stable Diffusion v3.5 Large private?
Compare
More AI image models on Mage
Stable Diffusion XL
Classic Stable Diffusion XL, tuned for photoreal output, at a budget price.
Z-Image
The fastest image model on Mage: photoreal drafts with solid anatomy and clean lettering.
Anima
An anime and illustration model with clean linework, flat color, and tag-based prompting.
Chroma
An open-weights, general-purpose image model built on the Flux architecture.
Flux 2
The open-weights image model for long, detailed prompts and edits from several input images.
GPT Image 2.5
OpenAI's image models: prompts followed to the letter, and text in the image that actually reads.

Make your first image with Stable Diffusion v3.5 Large
New accounts get 300 free Gems, enough to try Stable Diffusion v3.5 Large. No install, no credit card.
Start creating for free