In-Depth Tutorial with Ostris AI-Toolkit on RunPod

Getting Started with Ostris AI-Toolkit using RunPod

I guarantee that you will be up and running with Ostris AI-toolkit in less than 30 minutes using my in-depth tutorial published on YouTube.

Step by Step

Signing into Runpod

1. Sign into Runpod with your account. Assumption you have signed up and added some credits (We giveaway some credits from time to time on X – follow the blog so you can win).

Deploying Runpod

1. Deploy standard Runpod Pytorch 2.2.0 with a 24GB GPU. You can use newer versions also than 2.2.0

Installing Ostris AI-Toolkit

1. Once the Runpod is up and running – connect to Jupyter Notebook and open a Terminal
2. Run these commands to install the necessary components:
   • git clone https://github.com/ostris/ai-toolkit.git
   • cd ai-toolkit
   • git submodule update --init --recursive
   • python3 -m venv venv
   • source venv/bin/activate
   • pip3 install torch
   • pip3 install -r requirements.txt

Huggingface Steps

1. Sign into HF and accept the model access here black-forest-labs/FLUX.1-dev
2. Create a new file named env.txt in the root (ai-toolkit) folder using the File Explorer
3. Get a READ key from huggingface and add it to the env.txt file like so HF_TOKEN=insert_your_key_here
4. Once you have saved the file, right click it in order to rename it to.env
5. As soon as you rename the file it will no longer appear in the File Explorer

Configuring YAML File

1. Download the config YAML file (you can switch and choose others based on your need) and edit it to specify your preferences. Jump to this section in the video to follow along.
2. Once you are ready to run your training, run this command python run.py config/whatever_you_want.yaml where you need to specify the YAML file you created. You can see my newspaper-collage lora sample.yaml file below

Running Training

1. Once you have completed the above steps, you can start the training process by running the command python run.py config/whatever_you_want.yaml
2. You will see the training take place and your LoRA files will be produced in the output folder with the names specified in the YAML file. You will also see the images generated that will give you a feel for how the training is going.

Testing LoRA

1. Once the LoRA training is finished, you should download all the.safetensors files from the RunPod server. They would be lost when you delete the RunPod instance.
2. To Test the LoRA, you can use my LoRA tester workflow in ComfyUI or create your own following the preview below.

Conclusion

I hope you found my in-depth tutorial on running Ostris AI-toolkit using RunPod useful. I know many of you have commented and supported the video tutorial and also you can support the blog by using this referrer link to RunPod which doesn’t cost you any more but supports this blog and our channel.

FAQs

Q: What is RunPod?
A: RunPod is a cloud-based platform that provides access to high-end GPUs for machine learning and AI-related tasks.

Q: How do I get started with Ostris AI-toolkit using RunPod?
A: Follow the step-by-step guide provided in this article to get started with Ostris AI-toolkit using RunPod.

Q: What is the purpose of the YAML file in Ostris AI-toolkit?
A: The YAML file is used to specify the configuration for the LoRA training process, including the model, dataset, and training parameters.

Q: How do I test the LoRA model after training?
A: You can use my LoRA tester workflow in ComfyUI or create your own following the preview below.