Edit or compose from reference images with the step-distilled model and LoRAs.
The client provides a convenient way to interact with the model API.
npm install --save @fal-ai/clientThe @fal-ai/serverless-client package has been deprecated in favor of @fal-ai/client. Install the new package and update your imports — see client setup.
Set FAL_KEY as an environment variable in your runtime.
export FAL_KEY="YOUR_API_KEY"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("blackforestlabs/flux-3/klein/edit-image/lora", {
input: {
prompt: "A miniature grey amigurumi knight figure crocheted from thick woolen yarn stands on a cliff of stacked yarn skeins at night, lit by a full moon, next to a large fluffy knitted dragon in terracotta and mustard yarn, with a soft out-of-focus backdrop of indigo knitted yarn.",
image_urls: ["https://storage.googleapis.com/falserverless/example_inputs/z-image-turbo-i2i-input.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);The API uses an API Key for authentication. It is recommended you set the FAL_KEY environment variable in your runtime when possible.
import { fal } from "@fal-ai/client";
fal.config({
credentials: "YOUR_FAL_KEY"
});When running code on the client-side (e.g. in a browser, mobile app or GUI applications), make sure to not expose your FAL_KEY. Instead, use a server-side proxy to make requests to the API. For more information, check out our server-side integration guide.
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("blackforestlabs/flux-3/klein/edit-image/lora", {
input: {
prompt: "A miniature grey amigurumi knight figure crocheted from thick woolen yarn stands on a cliff of stacked yarn skeins at night, lit by a full moon, next to a large fluffy knitted dragon in terracotta and mustard yarn, with a soft out-of-focus backdrop of indigo knitted yarn.",
image_urls: ["https://storage.googleapis.com/falserverless/example_inputs/z-image-turbo-i2i-input.png"]
},
webhookUrl: "https://optional.webhook.url/for/results",
});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("blackforestlabs/flux-3/klein/edit-image/lora", {
requestId: "764cabcf-b745-4b3e-ae38-1200304cf45b",
logs: true,
});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("blackforestlabs/flux-3/klein/edit-image/lora", {
requestId: "764cabcf-b745-4b3e-ae38-1200304cf45b"
});
console.log(result.data);
console.log(result.requestId);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.
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.
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.
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);The client will auto-upload the file for you if you pass a binary object (e.g. File, Data).
Read more about file handling in our file upload guide.
LoRA weights to apply (maximum 3).
prompt string* requiredA complete caption of the target image with the edit folded in. Refer to the references by their order: the first image, the second image.
enable_prompt_expansion booleanIf set to true, the prompt is expanded into a detailed caption (grounded in the reference images when editing) before generation. Default value: true
seed integerThe same seed and the same prompt given to the same version of the model will output the same image every time.
num_images integerThe number of images to generate. Default value: 1
enable_safety_checker booleanIf set to true, the safety checker will be enabled. Default value: true
output_format OutputFormatEnumThe format of the generated image. Default value: "png"
Possible enum values: jpeg, png, webp
sync_mode booleanIf True, the media will be returned as a data URI and the output data won't be available in the request history.
The reference images to edit or compose from (up to 10).
The size of the generated image, 256 to 4096 pixels per side. If not set, a single reference image's own size (scaled to at most 4 megapixels) is used, or the first reference image's size (at most 1 megapixel) when several are given.
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
}Optional layout, with (0, 0) at the top-left of each image: keep, move, resize or remove objects from the references, or place new ones. Name boxes in the prompt by label, e.g. <dragon>.
{
"loras": [],
"prompt": "A miniature grey amigurumi knight figure crocheted from thick woolen yarn stands on a cliff of stacked yarn skeins at night, lit by a full moon, next to a large fluffy knitted dragon in terracotta and mustard yarn, with a soft out-of-focus backdrop of indigo knitted yarn.",
"enable_prompt_expansion": true,
"num_images": 1,
"enable_safety_checker": true,
"output_format": "png",
"image_urls": [
"https://storage.googleapis.com/falserverless/example_inputs/z-image-turbo-i2i-input.png"
],
"bounding_boxes": [
{
"label": "dragon",
"description": "a large fluffy knitted dragon in terracotta and mustard yarn"
}
]
}The generated images.
The timings of the generation process.
seed integer* requiredSeed used to generate the first image.
Whether the generated images contain NSFW concepts.
prompt string* requiredThe prompt used for generating the image.
{
"images": [
{
"url": "",
"content_type": "image/png",
"file_name": "z9RV14K95DvU.png",
"file_size": 4404019
}
],
"prompt": ""
}url string* requiredThe URL where the file can be downloaded from.
content_type stringThe mime type of the file.
file_name stringThe name of the file. It will be auto-generated if not provided.
file_size integerThe size of the file in bytes.
width integerThe width of the image
height integerThe height of the image
path string* requiredURL to a FLUX 3 Klein LoRA (.safetensors), e.g. from flux-3-image-klein-trainer.
scale floatScale factor for LoRA application (0.0 to 4.0). Default value: 1
width integerThe width of the generated image. Default value: 512
height integerThe height of the generated image. Default value: 512
label stringShort name for the object in this box, e.g. dragon. Write <dragon> in the prompt to tie the box to those words; a box the prompt doesn't name is added to the scene. Defaults to obj_<n>.
description string* requiredWhat to draw in this box: the object and its look.
Where the object goes in the output image, as on text-to-image. Use instead of source_box/target_box.
source_image_index integer0-based index into image_urls of the reference the object comes from. Leave unset for a new object.
Where the object is in the reference image. Requires source_image_index.
Where the object goes in the output image. Leave unset to remove a referenced object; set both boxes to move or resize it.
x_min float* requiredLeft edge as a fraction of the image width (0-1).
y_min float* requiredTop edge as a fraction of the image height (0-1).
x_max float* requiredRight edge as a fraction of the image width (0-1).
y_max float* requiredBottom edge as a fraction of the image height (0-1).