Skip to content

Commit

Permalink
[dreambooth] dont use safety check when generating prior images (hugg…
Browse files Browse the repository at this point in the history
…ingface#922)

dont' use safety check when generating prior images
  • Loading branch information
patil-suraj authored Oct 20, 2022
1 parent a5eb7f4 commit 7674a36
Show file tree
Hide file tree
Showing 3 changed files with 2 additions and 2 deletions.
1 change: 0 additions & 1 deletion examples/dreambooth/README.md
Original file line number Diff line number Diff line change
Expand Up @@ -10,7 +10,6 @@ The `train_dreambooth.py` script shows how to implement the training procedure a
Before running the scripts, make sure to install the library's training dependencies:

```bash
pip install git+https://github.com/huggingface/diffusers.git
pip install -U -r requirements.txt
```

Expand Down
1 change: 1 addition & 0 deletions examples/dreambooth/requirements.txt
Original file line number Diff line number Diff line change
@@ -1,3 +1,4 @@
diffusers>==0.5.0
accelerate
torchvision
transformers>=4.21.0
Expand Down
2 changes: 1 addition & 1 deletion examples/dreambooth/train_dreambooth.py
Original file line number Diff line number Diff line change
Expand Up @@ -343,7 +343,7 @@ def main():
if cur_class_images < args.num_class_images:
torch_dtype = torch.float16 if accelerator.device.type == "cuda" else torch.float32
pipeline = StableDiffusionPipeline.from_pretrained(
args.pretrained_model_name_or_path, torch_dtype=torch_dtype
args.pretrained_model_name_or_path, torch_dtype=torch_dtype, safety_checker=None
)
pipeline.set_progress_bar_config(disable=True)

Expand Down

0 comments on commit 7674a36

Please sign in to comment.