Flux Fine-tune action

This is an example repo for fine-tuning and publishing your own custom Flux model using Replicate and GitHub Actions.

Preqrequisites

• A Replicate account
• A handful of training images

Training the model

1. Fork this repository.
2. Remove the images in the data directory and replace them with your own images.
3. Commit your changes to Git and push to your main branch on GitHub.
4. Create a Replicate API token and add it as a repository secret named REPLICATE_API_TOKEN.
5. Trigger the workflow from your GitHub repo page: "Actions" > "Train a model" > "Run workflow".
6. Go to the replicate.com/trainings to see your training in progress.

Running the model

Check out these guides for tips on training and running Flux models:

• https://replicate.com/blog/fine-tune-flux-with-faces
• https://replicate.com/blog/fine-tune-flux-with-an-api
• https://replicate.com/blog/using-synthetic-data-to-improve-flux-finetunes