[docs] Task guide with Dreambooth LoRA example #330
Conversation
|
The documentation is not available anymore as the PR was closed or merged. |
| --output_dir=$OUTPUT_DIR \ | ||
| --train_text_encoder \ | ||
| --with_prior_preservation --prior_loss_weight=1.0 \ | ||
| --instance_prompt="a photo of sks dog" \ |
There was a problem hiding this comment.
Maybe briefly explain what sks is and what it does. I'd also mention that we're training on a dataset of dog images (or link to it) so users have a better idea of the initial images and where this prompt comes from.
There was a problem hiding this comment.
Thank you @MKhalusova for adding the task guide with the lora dreambooth example 🤗! This is a really cool usecase.
Left a comment
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com> Co-authored-by: Sourab Mangrulkar <13534540+pacman100@users.noreply.github.com>
…booth # Conflicts: # docs/source/task_guides/dreambooth_lora.mdx
There was a problem hiding this comment.
The multi inference adapter example is really cool! Super cool prompt of dog in supermarket isle 😁. Thank you @MKhalusova for adding the details on the helper functions leveraging PEFT multi adapter features. LGTM! 🤗
This PR adds a task guide based on this example