Skip to content

Stable Diffusion 3 Stable Diffusion 3.5 Large by Stability AI

Stability AI's open-weight image model on a fast serverless API. Stable Diffusion 3.5 Large is the newest in the Stable Diffusion 3 family, with Stable Audio 3 for music and sound.

Available Endpoints

The newest Stability AI endpoints

Stable Diffusion image models and Stable Audio, newest first. Every endpoint pay-per-use with no minimums.

Stable Diffusion 3.5 Large
fal-ai/stable-diffusion-v35-large
text-to-image

Stable Diffusion 3.5 Large is a Multimodal Diffusion Transformer (MMDiT) text-to-image model that features improved performance in image quality, typography, complex prompt understanding, and resource-efficiency.

diffusiontypographystyle
Stable Audio 3 Small SFX Base Audio Outpainting
fal-ai/stable-audio-3/small/sfx/base/audio-outpainting
audio-to-audio

Stable Audio 3 Small SFX Base audio outpainting is the foundational 459 million parameter checkpoint that extends sound-effect tracks via causal continuation guided by text prompts.

sfxextensioncontinuation
Stable Audio 3 Small SFX Audio Outpainting
fal-ai/stable-audio-3/small/sfx/audio-outpainting
audio-to-audio

Stable Audio 3 Small SFX audio outpainting is a 459 million parameter latent diffusion model that extends sound-effect tracks beyond their original endpoint via causal continuation.

sfxextensioncontinuation
Stable Audio 3 Small SFX Base Audio Inpainting
fal-ai/stable-audio-3/small/sfx/base/audio-inpainting
audio-to-audio

Stable Audio 3 Small SFX Base audio inpainting is the foundational 459 million parameter checkpoint for editing or filling selected sound-effect segments guided by text prompts.

sfxeditingrestoration
Stable Audio 3 Small SFX Audio Inpainting
fal-ai/stable-audio-3/small/sfx/audio-inpainting
audio-to-audio

Stable Audio 3 Small SFX audio inpainting is a 459 million parameter latent diffusion model that fills in or reworks selected segments of a sound-effect track guided by text prompts.

sfxeditingrestoration
Stable Audio 3 Small SFX Base Audio to Audio
fal-ai/stable-audio-3/small/sfx/base/audio-to-audio
audio-to-audio

Stable Audio 3 Small SFX Base audio-to-audio is the foundational 459 million parameter checkpoint that transforms input audio into new sound-effect variations guided by text prompts.

sfxsound-effectsstyle-transfer
Stable Audio 3
fal-ai/stable-audio-3/small/sfx/audio-to-audio
audio-to-audio

Stable Audio 3 Small SFX audio-to-audio is a 459 million parameter latent diffusion model that transforms input audio into new sound-effect variations guided by text prompts.

sfxsound-effectsstyle-transfer
Stable Audio 3 Small SFX Base Text to Audio
fal-ai/stable-audio-3/small/sfx/base/text-to-audio
text-to-audio

Stable Audio 3 Small SFX Base is the foundational 459 million parameter checkpoint generating sound effects from text prompts, intended as the unmodified base for fine-tuning.

sfxsound-effectson-device
Stable Audio 3 Small SFX Text to Audio
fal-ai/stable-audio-3/small/sfx/text-to-audio
text-to-audio

Stable Audio 3 Small SFX is a 459 million parameter latent diffusion model that generates high-quality sound effects from text prompts, designed for on-device deployment on mobile phones and consumer laptops.

sfxsound-effectson-device
Stable Audio 3 Small Music Base Audio Outpainting
fal-ai/stable-audio-3/small/music/base/audio-outpainting
audio-to-audio

Stable Audio 3 Small Music Base audio outpainting is the foundational 459 million parameter checkpoint that extends music tracks via causal continuation guided by text prompts.

musicextensioncontinuation
Stable Audio 3 Small Music Audio Outpainting
fal-ai/stable-audio-3/small/music/audio-outpainting
audio-to-audio

Stable Audio 3 Small Music audio outpainting is a 459 million parameter latent diffusion model that extends music compositions beyond their original endpoint via causal continuation.

musicextensioncontinuation
Stable Audio 3 Small Music Base Audio Inpainting
fal-ai/stable-audio-3/small/music/base/audio-inpainting
audio-to-audio

Stable Audio 3 Small Music Base audio inpainting is the foundational 459 million parameter checkpoint for editing or filling selected music segments guided by text prompts.

musiceditingrestoration

Stable Diffusion 3.5 Large and Stable Audio 3

Stable Diffusion 3.5 Large

The newest Stable Diffusion image model

Stable Diffusion 3.5 Large is the most capable model in the family, with the strongest prompt adherence and image quality in the family. It accepts LoRAs, ControlNet and IP-Adapter inputs for styled and guided generation.

Guided generation

LoRA, ControlNet and IP-Adapter in one request

Apply a trained LoRA style, guide composition with a ControlNet input, or match a reference image with IP-Adapter, all through the same Stable Diffusion 3.5 Large endpoint.

Stable Audio 3

Music and sound from the same lab

Stable Audio 3 generates music and sound effects from text, and edits, inpaints and extends existing audio. Every Stable Audio endpoint is listed below.

API Documentation

How to get access to the Stable Diffusion 3 API

The client handles the submit protocol: request status updates and the final result when generation completes.

import { fal } from "@fal-ai/client";

const result = await fal.subscribe("fal-ai/stable-diffusion-v35-large", {
  input: {
    prompt: "A lighthouse on a cliff at golden hour, oil painting, thick brush strokes",
    num_inference_steps: 28,
    guidance_scale: 3.5,
    output_format: "png",
  },
  logs: true,
  onQueueUpdate: (update) => {
    if (update.status === "IN_PROGRESS") {
      update.logs.map((log) => log.message).forEach(console.log);
    }
  },
});

console.log(result.data);
console.log(result.requestId);
FAQ

Common questions about Stable Diffusion

Which Stable Diffusion models are available on fal?

fal serves Stable Diffusion 3.5 Large for images and Stable Audio 3 for music and sound. The endpoint list on this page shows the newest Stability AI endpoints on fal.

Should I use Stable Diffusion 3 or 3.5?

Use Stable Diffusion 3.5 Large. It is the newest model in the Stable Diffusion 3 family, with the best quality and prompt adherence, and it is the Stable Diffusion image endpoint on fal today.

Can I use LoRAs and ControlNet?

Yes. Stable Diffusion 3.5 Large accepts LoRA weights, a ControlNet input and an IP-Adapter input in the same request, so you can apply a trained style or guide composition from a reference image.

How do I get started with the API?

Install the fal SDK (Python or JavaScript), grab an API key from your dashboard, and make your first request in a few lines of code. Check the API documentation for every parameter.

Can I use Stable Diffusion images for commercial projects?

Content generated through the fal API can be used in commercial projects, subject to the model's license. Check fal's terms of service and each model's page for licensing details.

Get in touch about Stable Diffusion

Want to learn more about integrating Stable Diffusion into your workflow? Leave your details and our team will reach out.

Contact Sales