RawFrame

Stable Diffusion 3.5 Large

Stable Diffusion 3.5 Large through the Stable Image API. Text to image at about one megapixel.

Preview

Parameters and limits may change before this model is generally available.

  • Model id: stability/sd-3.5-large
  • Type: Image, from Stability AI
  • Modes: Text to image
  • Prompt: up to 10,000 characters
  • Canceling: Only while queued. Generations finish within seconds once submitted.

Parameters

Set these in params. Anything left out takes the default, which is what the price estimate assumes.

ParameterAccepted valuesDefault
aspect_ratio1:1, 21:9, 16:9, 3:2, 5:4, 4:5, 2:3, 9:16, 9:211:1
num_outputs1 only1
seed0 to 4294967295chosen by the provider
negative_promptUp to 2,000 charactersnone
output_formatpng, jpeg, webpprovider's

References

This model takes no references.

Pricing

Billed per image delivered. The full price list for your account is on the dashboard's billing page and in pricing from GET /v1/models/stability%2Fsd-3.5-large. Each request reserves its maximum price and is charged for what was produced (Pricing and credits).

Examples

Text to image

import { RawFrame } from "@rawframe/sdk";

const rf = new RawFrame();

const generation = await rf.generations.createAndWait({
  model: "stability/sd-3.5-large",
  prompt: "A lighthouse on a basalt cliff at dusk, long exposure waves, dramatic sky",
  params: { aspect_ratio: "3:2" },
});
console.log(generation.outputs?.[0]?.url);

Tall poster

import { RawFrame } from "@rawframe/sdk";

const rf = new RawFrame();

const generation = await rf.generations.createAndWait({
  model: "stability/sd-3.5-large",
  prompt: "A retro travel poster of a desert railway station, flat colors, bold typography",
  params: { aspect_ratio: "9:16", negative_prompt: "blurry, low contrast" },
});
console.log(generation.outputs?.[0]?.url);

On this page