FLUX LoRA fine-tuning endpoint.
This endpoint fine-tunes a LoRA model on a dataset of images. By default the fine-tuning process is configured for preprocessing a subject. The training will generate both segmentation masks and caption for training.
If the is_style flag is set to True,
the training a style LoRA, which disables auto-captioning and sengmentation.
To provide your own captions, you can include a text file with the same name as
the image file. For example, if you have an image photo.jpg, you can include a
text file photo.txt with the caption.
Additionally you can include your own masks for the images. If you have a image
photo.jpg, you can include a mask file photo_mask.jpg.
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("fal-ai/flux-lora-fast-training", {
input: {
images_data_url: ""
},
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("fal-ai/flux-lora-fast-training", {
input: {
images_data_url: ""
},
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("fal-ai/flux-lora-fast-training", {
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("fal-ai/flux-lora-fast-training", {
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.
images_data_url string* requiredURL to zip archive with images. Try to use at least 4 images in general the more the better.
In addition to images the archive can contain text files with captions. Each text file should have the same name as the image file it corresponds to.
trigger_word stringTrigger word to be used in the captions. If None, a trigger word will not be used. If no captions are provide the trigger_word will be used instead of captions. If captions are the trigger word will not be used.
create_masks booleanIf True segmentation masks will be used in the weight the training loss. For people a face mask is used if possible. Default value: true
steps integerNumber of steps to train the LoRA on.
is_style booleanIf True, the training will be for a style. This will deactivate segmentation, captioning and will use trigger word instead. Use the trigger word to specify the style.
is_input_format_already_preprocessed booleanSpecifies whether the input data is already in a processed format. When set to False (default), the system expects raw input where image files and their corresponding caption files share the same name (e.g., 'photo.jpg' and 'photo.txt'). Set to True if your data is already in a preprocessed format.
data_archive_format stringThe format of the archive. If not specified, the format will be inferred from the URL.
{
"images_data_url": "",
"create_masks": true,
"steps": 1000
}URL to the trained diffusers lora weights.
URL to the training configuration file.
URL to the preprocessed images.
{
"diffusers_lora_file": {
"url": "",
"content_type": "image/png",
"file_name": "z9RV14K95DvU.png",
"file_size": 4404019
},
"config_file": {
"url": "",
"content_type": "image/png",
"file_name": "z9RV14K95DvU.png",
"file_size": 4404019
}
}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.