Skip to content
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.

Sign up for GitHub

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

sdxl-trainig: fixed ci, changed gated dataset, fixes for non-square datasets #1038

Merged
merged 7 commits into from
Jun 14, 2024
Merged

sdxl-trainig: fixed ci, changed gated dataset, fixes for non-square datasets #1038

Changes from 1 commit
Commits
Show all changes
7 commits
Select commit Hold shift + click to select a range
e2e6570
sdxl-trainig: fixed ci and changed gated dataset
imangohari1 Jun 4, 2024
36ecac0
minor fixes
imangohari1 Jun 4, 2024
b7aff90
sdxl prepross fix for no-square datasets
imangohari1 Jun 5, 2024
c6b0ee3
fea(sdxl-training): fixed g1 instructions
imangohari1 Jun 12, 2024
f56a431
fea(): undo rebase. minor
imangohari1 Jun 13, 2024
7aea351
Merge branch 'huggingface:main' into sdxl-update
imangohari1 Jun 13, 2024
9e45dd4
fea(): applied make style
imangohari1 Jun 13, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Prev Previous commit
Next Next commit
fea(sdxl-training): fixed g1 instructions
  • Loading branch information
@imangohari1
imangohari1 committed Jun 12, 2024
commit c6b0ee317db447d48665ee8da56500e436690f57
4 changes: 2 additions & 2 deletions examples/stable-diffusion/training/README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -230,11 +230,11 @@ python ../../gaudi_spawn.py --world_size 8 --use_mpi train_text_to_image_sdxl.py

### Single-card Training on Gaudi1
```bash
PT_HPU_MAX_COMPOUND_OP_SIZE=5 python train_text_to_image_sdxl.py \
python train_text_to_image_sdxl.py \
--pretrained_model_name_or_path stabilityai/stable-diffusion-xl-base-1.0 \
--pretrained_vae_model_name_or_path madebyollin/sdxl-vae-fp16-fix \
--dataset_name lambdalabs/naruto-blip-captions \
--resolution 512 \
--resolution 256 \
--center_crop \
--random_flip \
--proportion_empty_prompts=0.2 \
Expand Down