Generate
The client provides a convenient way to interact with the model API.
npm install --save @fal-ai/clientSet 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("krea/v3/edit", {
input: {
image_urls: ["https://v3b.fal.media/files/b/0a90b2a1/i89tMXz0SmiwL0ZvbnUvS_image_00240.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"
});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("krea/v3/edit", {
input: {
image_urls: ["https://v3b.fal.media/files/b/0a90b2a1/i89tMXz0SmiwL0ZvbnUvS_image_00240.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("krea/v3/edit", {
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("krea/v3/edit", {
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);Read more about file handling in our file upload guide.
prompt stringEdit instruction. Refer to images as <image-1>, <image-2>, ... and regions as @label. May be omitted when a region has a note. Default value: ""
Reference images to edit or combine (1-8). Order sets the <image-N> tags.
Bounding boxes on reference images, with optional labels and editing notes. Requires high or ultra reasoning.
regional_edit booleanWith high or ultra reasoning, true preserves pixels outside the edit regions on the chosen canvas; false disables automatic region cropping and preservation. Omit to retain automatic preservation. With image_size=auto, keeps the canvas dimensions; an explicit image_size preserves the resized input. Billing uses the generated render dimensions. Use PNG for lossless output.
model ModelEnumModel variant: berry favors quality, jam favors speed. Default value: "berry"
Possible enum values: berry, jam
Output size, rounded up to multiples of 16, at most 4,220,160 total pixels (1680×2512). auto lets the prompt expander pick the aspect ratio at about 2048×2048. Default value: auto
Possible enum values: square_hd, square, portrait_4_3, portrait_16_9, landscape_4_3, landscape_16_9, auto
Note: For custom image sizes, you can pass the width and height as an object:
"image_size": {
"width": 1280,
"height": 720
}reasoning_level ReasoningLevelEnumHow much effort the harness spends reasoning about the given editing task. Higher reasoning effort means slower generation time. high plans the edit with segmentation, web search and reference photos, keeps unedited areas of a single input image, corrects required text, and bills a flat $0.125 (5 megapixels) more per request. low and medium bill $0.025 per megapixel of the output plus each reference (references larger than the output count as the output size). ultra generates at 2K with Krea's ultra thinking mode, ignores image_size and negative_prompt, and bills a flat price by reference count: $0.27 for 1, $0.30 for 2, $0.32 for 3, $0.35 for 4, plus $0.0275 per reference past 4. Default value: "medium"
Possible enum values: low, medium, high, ultra
negative_prompt stringWhat to keep out of the image. Used by berry only. Default value: ""
seed integerLatent noise seed. Use a new seed when editing a previous output again.
output_format OutputFormatEnumOutput image format. Default value: "png"
Possible enum values: png, jpeg
sync_mode booleanReturn images as data URIs instead of saving them in request history.
enable_safety_checker booleanCheck output images for unsafe content. Disabling requires account authorization. Default value: true
{
"image_urls": [
"https://v3b.fal.media/files/b/0a90b2a1/i89tMXz0SmiwL0ZvbnUvS_image_00240.png"
],
"regions": [
{}
],
"model": "berry",
"image_size": "auto",
"reasoning_level": "medium",
"output_format": "png",
"enable_safety_checker": true
}Generated images.
seed integer* requiredLatent noise seed used for generation.
prompt string* requiredPrompt used for generation, after expansion.
Seconds spent in each generation stage; inference is the total GPU sampling time.
Safety result for each image.
{
"images": [
{
"url": "",
"content_type": "image/png",
"file_name": "z9RV14K95DvU.png",
"file_size": 4404019
}
],
"prompt": ""
}width integerThe width of the generated image. Default value: 512
height integerThe height of the generated image. Default value: 512
image_idx integer* requiredZero-based index into image_urls.
x float* requiredLeft edge as a fraction of image width.
y float* requiredTop edge as a fraction of image height.
width float* requiredWidth as a fraction of image width.
height float* requiredHeight as a fraction of image height.
label stringRefer to this region as @label. Defaults to its one-based position.
note stringEdit instruction for this region; may reference other @labels. Default value: ""
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