Skip to content

Training tutorial #2473

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 5 commits into from
Mar 3, 2023
Merged

Training tutorial #2473

merged 5 commits into from
Mar 3, 2023

Conversation

stevhliu
Copy link
Member

This PR migrates the relevant content from the Training with Diffusers notebook into a new Tutorial section in the docs. It edits out some of the more background information so we don't bog the user down with these details, and focuses on just showing them the steps to train their own model!

@HuggingFaceDocBuilderDev
Copy link

HuggingFaceDocBuilderDev commented Feb 23, 2023

The documentation is not available anymore as the PR was closed or merged.

Copy link
Collaborator

@yiyixuxu yiyixuxu left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

love this tutorial! Thanks you!

I saw you created a new section created "tutorial"? what is this section intended for?

I would have thought this would belong to the "training" section

Comment on lines +11 to +14
- sections:
- local: tutorials/basic_training
title: Train a diffusion model
title: Tutorials
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I think it can go under the training section we already have.

Copy link
Member

@sayakpaul sayakpaul left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Wow!

@stevhliu
Copy link
Member Author

The tutorial section is intended to introduce newcomers to the library and help them learn and get started/oriented to be able to use the rest of the library. You can think of this section as the gateway docs to the rest of the library or like a mini crash course on 🧨 Diffusers. It gives users, especially newcomers, a safe/welcoming space to get comfortable before digging deeper into the rest of the docs on how they can start solving tasks specific to them.

In this case, after reading how to train for unconditional image generation, it sets the user up to better understand some of the more complicated training examples like Textual Inversion and DreamBooth (at least it helped me to see some familiar things in the notebook that I had previously seen before).

Happy to hear what you think! 🤗

Copy link
Member

@pcuenca pcuenca left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Very cool, I love the idea of tutorials!

Copy link
Contributor

@patrickvonplaten patrickvonplaten left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Great very clean! Also nice that we log images during training

@stevhliu stevhliu merged commit fa6d52d into huggingface:main Mar 3, 2023
@stevhliu stevhliu deleted the training-tutorial branch March 3, 2023 23:41
mengfei25 pushed a commit to mengfei25/diffusers that referenced this pull request Mar 27, 2023
* first draft

* ✨ minor edits

* ✨ minor fixes

* 🖍 apply feedbacks

* 🖍 apply feedback and minor edits
w4ffl35 pushed a commit to w4ffl35/diffusers that referenced this pull request Apr 14, 2023
* first draft

* ✨ minor edits

* ✨ minor fixes

* 🖍 apply feedbacks

* 🖍 apply feedback and minor edits
AmericanPresidentJimmyCarter pushed a commit to AmericanPresidentJimmyCarter/diffusers that referenced this pull request Apr 26, 2024
* first draft

* ✨ minor edits

* ✨ minor fixes

* 🖍 apply feedbacks

* 🖍 apply feedback and minor edits
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

6 participants