edenartlab/sdxl-lora-trainer:b4a19aae – Run with an API on Replicate

Version

You're looking at a specific version of this model. Jump to the model overview.

edenartlab /sdxl-lora-trainer:b4a19aae

Playground API

Input

lora_training_urls

*string

Shift + Return to add a new line

Training images for new LORA concept (can be image urls or a .zip file of images)

concept_mode

string

Shift + Return to add a new line

'face' / 'style' / 'object' (default)

Default: "object"

sd_model_version

string

Shift + Return to add a new line

'sdxl' / 'sd15'

Default: "sdxl"

name

string

Shift + Return to add a new line

Name of new LORA concept

Default: "unnamed"

seed

integer

Random seed for reproducible training. Leave empty to use a random seed

resolution

integer

Square pixel resolution which your images will be resized to for training, recommended: 512 or 640

Default: 512

train_batch_size

integer

Batch size (per device) for training

Default: 4

max_train_steps

integer

Number of training steps.

Default: 400

token_warmup_steps

integer

Number of steps for token (textual_inversion) warmup.

Default: 50

checkpointing_steps

integer

Number of steps between saving checkpoints. Set to very very high number to disable checkpointing, because you don't need intermediate checkpoints.

Default: 10000

is_lora

boolean

Whether to use LoRA training. If set to False, will use full fine tuning

Default: true

prodigy_d_coef

number

Multiplier for internal learning rate of Prodigy optimizer

Default: 0.5

ti_lr

number

Learning rate for training textual inversion embeddings. Don't alter unless you know what you're doing.

Default: 0.001

freeze_ti_after_completion_f

number

Fraction of training steps after which to freeze textual inversion embeddings

Default: 0.5

lora_rank

integer

Rank of LoRA embeddings for the unet.

Default: 12

text_encoder_lora_optimizer

string

Shift + Return to add a new line

Which optimizer to use for the text_encoder_lora. ['adamw', None] are supported right now (None will disable txt-lora training)

Default: "adamw"

caption_model

string

Shift + Return to add a new line

Which captioning model to use. ['gpt4-v', 'blip'] are supported right now

Default: "gpt4-v"

n_tokens

integer

How many new tokens to inject per concept

Default: 2

verbose

boolean

verbose output

Default: true

debug

boolean

For debugging locally only (dont activate this on replicate)

Default: false

Run this model in Node.js with one line of code:

npx create-replicate --model=edenartlab/sdxl-lora-trainer

or set up a project from scratch

Install Replicate’s Node.js client library:

npm install replicate

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Import and set up the client:

import Replicate from "replicate";

const replicate = new Replicate({
  auth: process.env.REPLICATE_API_TOKEN,
});

Run edenartlab/sdxl-lora-trainer using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "edenartlab/sdxl-lora-trainer:b4a19aae0f9f46b5dc0d3d874f406cda6d18ebade467ddbfc0a33f9167d0e5eb",
  {
    input: {
      name: "unnamed",
      debug: false,
      ti_lr: 0.001,
      is_lora: true,
      verbose: true,
      n_tokens: 2,
      lora_rank: 12,
      resolution: 512,
      concept_mode: "object",
      caption_model: "gpt4-v",
      prodigy_d_coef: 0.5,
      max_train_steps: 400,
      sd_model_version: "sdxl",
      train_batch_size: 4,
      token_warmup_steps: 50,
      checkpointing_steps: 10000,
      text_encoder_lora_optimizer: "adamw",
      freeze_ti_after_completion_f: 0.5
    }
  }
);
console.log(output);

To learn more, take a look at the guide on getting started with Node.js.

Install Replicate’s Python client library:

pip install replicate

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Import the client:

import replicate

Run edenartlab/sdxl-lora-trainer using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "edenartlab/sdxl-lora-trainer:b4a19aae0f9f46b5dc0d3d874f406cda6d18ebade467ddbfc0a33f9167d0e5eb",
    input={
        "name": "unnamed",
        "debug": False,
        "ti_lr": 0.001,
        "is_lora": True,
        "verbose": True,
        "n_tokens": 2,
        "lora_rank": 12,
        "resolution": 512,
        "concept_mode": "object",
        "caption_model": "gpt4-v",
        "prodigy_d_coef": 0.5,
        "max_train_steps": 400,
        "sd_model_version": "sdxl",
        "train_batch_size": 4,
        "token_warmup_steps": 50,
        "checkpointing_steps": 10000,
        "text_encoder_lora_optimizer": "adamw",
        "freeze_ti_after_completion_f": 0.5
    }
)

# The edenartlab/sdxl-lora-trainer model can stream output as it's running.
# The predict method returns an iterator, and you can iterate over that output.
for item in output:
    # https://replicate.com/edenartlab/sdxl-lora-trainer/api#output-schema
    print(item)

To learn more, take a look at the guide on getting started with Python.

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Run edenartlab/sdxl-lora-trainer using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

curl -s -X POST \
  -H "Authorization: Bearer $REPLICATE_API_TOKEN" \
  -H "Content-Type: application/json" \
  -H "Prefer: wait" \
  -d $'{
    "version": "b4a19aae0f9f46b5dc0d3d874f406cda6d18ebade467ddbfc0a33f9167d0e5eb",
    "input": {
      "name": "unnamed",
      "debug": false,
      "ti_lr": 0.001,
      "is_lora": true,
      "verbose": true,
      "n_tokens": 2,
      "lora_rank": 12,
      "resolution": 512,
      "concept_mode": "object",
      "caption_model": "gpt4-v",
      "prodigy_d_coef": 0.5,
      "max_train_steps": 400,
      "sd_model_version": "sdxl",
      "train_batch_size": 4,
      "token_warmup_steps": 50,
      "checkpointing_steps": 10000,
      "text_encoder_lora_optimizer": "adamw",
      "freeze_ti_after_completion_f": 0.5
    }
  }' \
  https://api.replicate.com/v1/predictions

To learn more, take a look at Replicate’s HTTP API reference docs.

Output

No output yet! Press "Submit" to start a prediction.