Update training and fine-tuning docs #1020
Merged
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
|
The documentation is not available anymore as the PR was closed or merged. |
patil-suraj
approved these changes
Oct 27, 2022
Comment on lines
+13
to
+47
| # DreamBooth fine-tuning example | ||
|
|
||
| [DreamBooth](https://arxiv.org/abs/2208.12242) is a method to personalize text-to-image models like stable diffusion given just a few (3~5) images of a subject. | ||
|
|
||
|  | ||
| _Dreambooth examples from the [project's blog](https://dreambooth.github.io)._ | ||
|
|
||
| The [Dreambooth training script](https://github.com/huggingface/diffusers/tree/main/examples/dreambooth) shows how to implement this training procedure on a pre-trained Stable Diffusion model. | ||
|
|
||
| <Tip warning={true}> | ||
|
|
||
| <!-- TODO: replace with our blog when it's done --> | ||
|
|
||
| Dreambooth fine-tuning is very sensitive to hyperparameters and easy to overfit. We recommend you take a look at our [in-depth analysis](https://wandb.ai/psuraj/dreambooth/reports/Dreambooth-Training-Analysis--VmlldzoyNzk0NDc3) with recommended settings for different subjects, and go from there. | ||
|
|
||
| </Tip> | ||
|
|
||
| ## Training locally | ||
|
|
||
| ### Installing the dependencies | ||
|
|
||
| Before running the scripts, make sure to install the library's training dependencies. We also recommend to install `diffusers` from the `main` github branch. | ||
|
|
||
| ```bash | ||
| pip install git+https://github.com/huggingface/diffusers | ||
| pip install -U -r diffusers/examples/dreambooth/requirements.txt | ||
| ``` | ||
|
|
||
| Then initialize and configure a [🤗 Accelerate](https://github.com/huggingface/accelerate/) environment with: | ||
|
|
||
| ```bash | ||
| accelerate config | ||
| ``` | ||
|
|
||
| You need to accept the model license before downloading or using the weights. In this example we'll use model version `v1-4`, so you'll need to visit [its card](https://huggingface.co/CompVis/stable-diffusion-v1-4), read the license and tick the checkbox if you agree. |
| | [**Text-to-Image**](./text2image) | - | - | | ||
| | [**Text-Inversion**](./text_inversion) | ✅ | ✅ | [](https://colab.research.google.com/github/huggingface/notebooks/blob/main/diffusers/sd_textual_inversion_training.ipynb) | ||
| | [**Text-to-Image fine-tuning**](./text2image) | ✅ | ✅ | | ||
| | [**Textual Inversion**](./text_inversion) | ✅ | - | [](https://colab.research.google.com/github/huggingface/notebooks/blob/main/diffusers/sd_textual_inversion_training.ipynb) |
There was a problem hiding this comment.
We are not using datasets for textual inversion training.
There was a problem hiding this comment.
Yes, I noticed and removed the green tick. The remaining one is for Accelerate.
Comment on lines
+88
to
+106
| export MODEL_NAME="CompVis/stable-diffusion-v1-4" | ||
| export TRAIN_DIR="path_to_your_dataset" | ||
| export OUTPUT_DIR="path_to_save_model" | ||
|
|
||
| accelerate launch train_text_to_image.py \ | ||
| --pretrained_model_name_or_path=$MODEL_NAME \ | ||
| --train_data_dir=$TRAIN_DIR \ | ||
| --use_ema \ | ||
| --resolution=512 --center_crop --random_flip \ | ||
| --train_batch_size=1 \ | ||
| --gradient_accumulation_steps=4 \ | ||
| --gradient_checkpointing \ | ||
| --mixed_precision="fp16" \ | ||
| --max_train_steps=15000 \ | ||
| --learning_rate=1e-05 \ | ||
| --max_grad_norm=1 \ | ||
| --lr_scheduler="constant" --lr_warmup_steps=0 \ | ||
| --output_dir=${OUTPUT_DIR} | ||
| ``` |
There was a problem hiding this comment.
Let's also add a section for flax example that is just merged #999
anton-l
approved these changes
Oct 27, 2022
Co-authored-by: Anton Lozhkov <anton@huggingface.co>
Co-authored-by: Anton Lozhkov <anton@huggingface.co>
PhaneeshB
pushed a commit
to nod-ai/diffusers
that referenced
this pull request
Mar 1, 2023
-- This commit adds support for standalone Vae checkpoints. Signed-off-by: Abhishek Varma <abhishek@nod-labs.com> Co-authored-by: Abhishek Varma <abhishek@nod-labs.com>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
No description provided.