Train Flux LoRA (legacy) Training
About
Fine Tune
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
Migrate to @fal-ai/client
The @fal-ai/serverless-client
package has been deprecated in favor of @fal-ai/client
. Please check the migration guide for more information.
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/flux-lora-general-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);
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#
import { fal } from "@fal-ai/client";
fal.config({
credentials: "YOUR_FAL_KEY"
});
Protect your API 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.
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/flux-lora-general-training", {
input: {
images_data_url: ""
},
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/flux-lora-general-training", {
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/flux-lora-general-training", {
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);
Auto uploads
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.
5. Schema#
Input#
images_data_url
string
* requiredURL to zip archive with images of a consistent style. Try to use at least 10 images, although more is 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.
The captions can include a special string [trigger]
. If a trigger_word is specified, it will replace [trigger]
in the captions.
data_archive_format
string
File format to archive training artifacts
captions_file_url
string
URL to a jsonl file with captions. Each line should contain a json object with a 'file_name' field that matches a file name in the images_data_url archive. It should also have a 'text' field with the caption.
{"file_name": "image1.jpg", "text": "In the style of TRIGGER_WORDS A picture of a cat."} {"file_name": "image2.jpg", "text": "In the style of TRIGGER_WORDS A picture of a dog."}
The captions can include a special string [trigger]
. If a trigger_word is specified, it will replace [trigger]
in the captions.
When captioning, in general, caption the elements you do NOT want to always associated with the trigger words. Every you do NOT caption should be unconditionally associated with the trigger words.
steps
integer
Total number of training steps to perform. Default is 1000. Default value: 1000
trigger_word
string
Trigger word to be used in the captions. If None, a trigger word will not be used.
If no captions are provide the trigger_work will be used instead of captions. If captions are provided, the trigger word will replace the [trigger]
string in the captions.
rank
integer
Rank of the model. Default is 16. Default value: 16
learning_rate
float
Initial learning rate for the unet. Default is 4e-4 Default value: 0.0004
caption_dropout_rate
float
Dropout rate for captions. Default is 0.05 Default value: 0.05
high_resolution_mode
boolean
If true, will only train with the 1024 resolution bucket. Default is False. If True increases the price by 20% (price multiplied by 1.2).
experimental_optimizers
ExperimentalOptimizersEnum
Experimental. Could change in the future. Default is 'adamw8bit'. Default value: "adamw8bit"
Possible enum values: adamw8bit, prodigy, adafactor
experimental_multi_checkpoints_count
integer
Experimental. Could change in the future. Number of checkpoints to save. Default is 1. Checkpoints are only saved if the interval is set. Default value: 1
experimental_multi_checkpoints_interval
integer
Experimental. Could change in the future. Interval between saving checkpoints. Default is None. If not None must be greater than 250.
{
"images_data_url": "",
"steps": 1000,
"rank": 16,
"learning_rate": 0.0004,
"caption_dropout_rate": 0.05,
"experimental_optimizers": "adamw8bit",
"experimental_multi_checkpoints_count": 1
}
Output#
URL to the trained diffusers lora weights.
URL to the training configuration file.
URL to the tar.gz file containing the caption files.
URLs to the saved checkpoints.
{
"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
},
"experimental_multi_checkpoints": [
{
"url": "",
"content_type": "image/png",
"file_name": "z9RV14K95DvU.png",
"file_size": 4404019
}
]
}
Other types#
File#
url
string
* requiredThe URL where the file can be downloaded from.
content_type
string
The mime type of the file.
file_name
string
The name of the file. It will be auto-generated if not provided.
file_size
integer
The size of the file in bytes.
file_data
string
File data