Launch SDXL Finetuning Job



Before proceeding further, please ensure that the following conditions are met:

  • Have a valid MonsterAPI account - Don't have an account? Sign up.
  • Minimum 1,000 API credits required - Haven't purchased yet? Explore our plans.

  • After logging into your account, open the "Fine-Tuning" Portal from left side menu.
  • Then click on the "Create New Finetuning Job" button and select “Finetune SDXL Model”.

Now you are all set to follow the steps for crafting and launching an SDXL finetuning job.

Step by step guide:

  1. Select a Stable Diffusion Model and define the Prompt

Select a Stable Diffusion Model from the dropdown menu that best fits your requirements. Options include the latest models like SDXL Base 1.0, Stable Diffusion 2, and Stable Diffusion 2-1.

  1. Select a Dataset

Option 1 - S3 Presigned Link:
Please provide the S3 presigned URL to access the dataset.

Option 2 - Upload a Custom Dataset:
You can upload a custom dataset of your choice as a zip file.

Option 3 - Manual Bucket Access:
Provide the AWS Access and Secret Key along with the S3 Bucket Name and Object Key to access the dataset manually.

  1. Specify Hyperparameter Configuration

In this step, set your hyper-parameters such as learning rate, steps, resolution and so on. These parameters are automatically filled based on your chosen model, but you can modify them according to your needs.

HuggingFace credentials can be provided to upload the model into HuggingFace.

Please note: These parameters affect the fine-tuning process and can also lead to failure if not set correctly.

  1. Finally, Review and Submit Job

Click on Next to proceed to the summary page.

Review the final job summary to ensure all the settings are correct, then submit your request.

That's it! Your finetuning job starts in a couple of minutes and when it switches to IN PROGRESS state, you will be able to view the job logs.

⚙️ Optional Settings

  1. Upload model outputs to Huggingface Repo:

    If you want to store the final fine-tuned model weights in a HuggingFace repository, add your HuggingFace credentials on Third step:
    • Your Huggingface API Key (Must have write access)
    • Your Huggingface Repo Path
      If you add these credentials, the job will automatically publish the fine-tuned weights to your huggingface repo upon completion.

That's it! Finished!