Stable Diffusion 3.5 Large Text to Image

fal-ai/stable-diffusion-v35-large
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.
Inference
Commercial use

About

Generate

1. Calling the API#

Install the client#

The client provides a convenient way to interact with the model API.

npm install --save @fal-ai/client

Setup your API Key#

Set FAL_KEY as an environment variable in your runtime.

export FAL_KEY="YOUR_API_KEY"

Submit a request#

The client API handles the API submit protocol. It will handle the request status updates and return the result when the request is completed.

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

const result = await fal.subscribe("fal-ai/stable-diffusion-v35-large", {
  input: {
    prompt: "A dreamlike Japanese garden in perpetual twilight, bathed in bioluminescent cherry blossoms that emit a soft pink-purple glow. Floating paper lanterns drift lazily through the scene, their warm light creating dancing reflections in a mirror-like koi pond. Ethereal mist weaves between ancient stone pathways lined with glowing mushrooms in pastel blues and purples. A traditional wooden bridge arches gracefully over the water, dusted with fallen petals that sparkle like stardust. The scene is captured through a cinematic lens with perfect bokeh, creating an otherworldly atmosphere. In the background, a crescent moon hangs impossibly large in the sky, surrounded by a sea of stars and auroral wisps in teal and violet. Crystal formations emerge from the ground, refracting the ambient light into rainbow prisms. The entire composition follows the golden ratio, with moody film-like color grading reminiscent of Studio Ghibli, enhanced by volumetric god rays filtering through the luminous foliage. 8K resolution, masterful photography, hyperdetailed, magical realism."
  },
  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);

2. Authentication#

The API uses an API Key for authentication. It is recommended you set the FAL_KEY environment variable in your runtime when possible.

API Key#

In case your app is running in an environment where you cannot set environment variables, you can set the API Key manually as a client configuration.
import { fal } from "@fal-ai/client";

fal.config({
  credentials: "YOUR_FAL_KEY"
});

3. Queue#

Submit a request#

The client API provides a convenient way to submit requests to the model.

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

const { request_id } = await fal.queue.submit("fal-ai/stable-diffusion-v35-large", {
  input: {
    prompt: "A dreamlike Japanese garden in perpetual twilight, bathed in bioluminescent cherry blossoms that emit a soft pink-purple glow. Floating paper lanterns drift lazily through the scene, their warm light creating dancing reflections in a mirror-like koi pond. Ethereal mist weaves between ancient stone pathways lined with glowing mushrooms in pastel blues and purples. A traditional wooden bridge arches gracefully over the water, dusted with fallen petals that sparkle like stardust. The scene is captured through a cinematic lens with perfect bokeh, creating an otherworldly atmosphere. In the background, a crescent moon hangs impossibly large in the sky, surrounded by a sea of stars and auroral wisps in teal and violet. Crystal formations emerge from the ground, refracting the ambient light into rainbow prisms. The entire composition follows the golden ratio, with moody film-like color grading reminiscent of Studio Ghibli, enhanced by volumetric god rays filtering through the luminous foliage. 8K resolution, masterful photography, hyperdetailed, magical realism."
  },
  webhookUrl: "https://optional.webhook.url/for/results",
});

Fetch request status#

You can fetch the status of a request to check if it is completed or still in progress.

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

const status = await fal.queue.status("fal-ai/stable-diffusion-v35-large", {
  requestId: "764cabcf-b745-4b3e-ae38-1200304cf45b",
  logs: true,
});

Get the result#

Once the request is completed, you can fetch the result. See the Output Schema for the expected result format.

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

const result = await fal.queue.result("fal-ai/stable-diffusion-v35-large", {
  requestId: "764cabcf-b745-4b3e-ae38-1200304cf45b"
});
console.log(result.data);
console.log(result.requestId);

4. Files#

Some attributes in the API accept file URLs as input. Whenever that's the case you can pass your own URL or a Base64 data URI.

Data URI (base64)#

You can pass a Base64 data URI as a file input. The API will handle the file decoding for you. Keep in mind that for large files, this alternative although convenient can impact the request performance.

Hosted files (URL)#

You can also pass your own URLs as long as they are publicly accessible. Be aware that some hosts might block cross-site requests, rate-limit, or consider the request as a bot.

Uploading files#

We provide a convenient file storage that allows you to upload files and use them in your requests. You can upload files using the client API and use the returned URL in your requests.

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

const file = new File(["Hello, World!"], "hello.txt", { type: "text/plain" });
const url = await fal.storage.upload(file);

Read more about file handling in our file upload guide.

5. Schema#

Input#

prompt string* required

The prompt to generate an image from.

negative_prompt string

The negative prompt to use. Use it to address details that you don't want in the image. This could be colors, objects, scenery and even the small details (e.g. moustache, blurry, low resolution). Default value: ""

num_inference_steps integer

The number of inference steps to perform. Default value: 28

seed integer

The same seed and the same prompt given to the same version of the model will output the same image every time.

guidance_scale float

The CFG (Classifier Free Guidance) scale is a measure of how close you want the model to stick to your prompt when looking for a related image to show you. Default value: 3.5

sync_mode boolean

If set to true, the function will wait for the image to be generated and uploaded before returning the response. This will increase the latency of the function but it allows you to get the image directly in the response without going through the CDN.

num_images integer

The number of images to generate. Default value: 1

enable_safety_checker boolean

If set to true, the safety checker will be enabled. Default value: true

output_format OutputFormatEnum

The format of the generated image. Default value: "jpeg"

Possible enum values: jpeg, png

controlnet ControlNet

ControlNet for inference.

image_size ImageSize | Enum

The size of the generated image. Defaults to landscape_4_3 if no controlnet has been passed, otherwise defaults to the size of the controlnet conditioning image.

Possible enum values: square_hd, square, portrait_4_3, portrait_16_9, landscape_4_3, landscape_16_9

Note: For custom image sizes, you can pass the width and height as an object:

"image_size": {
  "width": 1280,
  "height": 720
}
loras list<LoraWeight>

The LoRAs to use for the image generation. You can use any number of LoRAs and they will be merged together to generate the final image. Default value: ``

ip_adapter IPAdapter

IP-Adapter to use during inference.

{
  "prompt": "A dreamlike Japanese garden in perpetual twilight, bathed in bioluminescent cherry blossoms that emit a soft pink-purple glow. Floating paper lanterns drift lazily through the scene, their warm light creating dancing reflections in a mirror-like koi pond. Ethereal mist weaves between ancient stone pathways lined with glowing mushrooms in pastel blues and purples. A traditional wooden bridge arches gracefully over the water, dusted with fallen petals that sparkle like stardust. The scene is captured through a cinematic lens with perfect bokeh, creating an otherworldly atmosphere. In the background, a crescent moon hangs impossibly large in the sky, surrounded by a sea of stars and auroral wisps in teal and violet. Crystal formations emerge from the ground, refracting the ambient light into rainbow prisms. The entire composition follows the golden ratio, with moody film-like color grading reminiscent of Studio Ghibli, enhanced by volumetric god rays filtering through the luminous foliage. 8K resolution, masterful photography, hyperdetailed, magical realism.",
  "negative_prompt": "",
  "num_inference_steps": 28,
  "guidance_scale": 3.5,
  "num_images": 1,
  "enable_safety_checker": true,
  "output_format": "jpeg"
}

Output#

images list<Image>* required

The generated image files info.

timings Timings* required
seed integer* required

Seed of the generated Image. It will be the same value of the one passed in the input or the randomly generated that was used in case none was passed.

has_nsfw_concepts list<boolean>* required

Whether the generated images contain NSFW concepts.

prompt string* required

The prompt used for generating the image.

{
  "images": [
    {
      "url": "",
      "content_type": "image/jpeg"
    }
  ],
  "prompt": ""
}

Other types#

LoraWeight#

path string* required

URL or the path to the LoRA weights.

scale float

The scale of the LoRA weight. This is used to scale the LoRA weight before merging it with the base model. Default value: 1

Image#

url string* required
width integer* required
height integer* required
content_type string

Default value: "image/jpeg"

IPAdapter#

path string* required

Hugging Face path to the IP-Adapter

subfolder string

Subfolder in which the ip_adapter weights exist

weight_name string

Name of the safetensors file containing the ip-adapter weights

image_encoder_path string* required

Path to the Image Encoder for the IP-Adapter, for example 'openai/clip-vit-large-patch14'

image_encoder_subfolder string

Subfolder in which the image encoder weights exist.

image_encoder_weight_name string

Name of the image encoder.

image_url string* required

URL of Image for IP-Adapter conditioning.

mask_image_url string

URL of the mask for the control image.

mask_threshold float

Threshold for mask. Default value: 0.5

scale float* required

Scale for ip adapter.

ImageSize#

width integer

The width of the generated image. Default value: 512

height integer

The height of the generated image. Default value: 512

ControlNet#

path string* required

URL or the path to the control net weights.

control_image_url string* required

URL of the image to be used as the control image.

conditioning_scale float

The scale of the control net weight. This is used to scale the control net weight before merging it with the base model. Default value: 1

start_percentage float

The percentage of the image to start applying the controlnet in terms of the total timesteps.

end_percentage float

The percentage of the image to end applying the controlnet in terms of the total timesteps. Default value: 1