What does this PR do?

Part of #8384

Test script

export MODEL_NAME="stabilityai/stable-diffusion-xl-base-1.0"
export OUTPUT_DIR="sdxl_lcm"

accelerate launch train_lcm_distill_lora_sdxl.py \
    --pretrained_teacher_model=$MODEL_NAME \
    --output_dir=$OUTPUT_DIR \
    --mixed_precision=fp16 \
    --resolution=512 \
    --lora_rank=64 \
    --learning_rate=1e-4 --loss_type="huber" --adam_weight_decay=0.0 \
    --num_train_epochs=100 \
    --dataloader_num_workers=8 \
    --dataset_name="lambdalabs/naruto-blip-captions" \
    --validation_steps=200 \
    --checkpointing_steps=200 --checkpoints_total_limit=10 \
    --train_batch_size=2 \
    --gradient_checkpointing --enable_xformers_memory_efficient_attention \
    --gradient_accumulation_steps=1 \
    --use_8bit_adam \
    --resume_from_checkpoint=latest \
    --report_to=tensorboard \
    --seed=453645634

Before submitting

• This PR fixes a typo or improves the docs (you can dismiss the other checks if that's the case).
• Did you read the contributor guideline?
• Did you read our philosophy doc (important for complex PRs)?
• Was this discussed/approved via a GitHub issue or the forum? Please add a link to it if that's the case.
• Did you make sure to update the documentation with your changes? Here are the
  documentation guidelines, and
  here are tips on formatting docstrings.
• Did you write any new necessary tests?

Who can review?

Anyone in the community is free to review the PR once the tests have passed. Feel free to tag
members/contributors who may be interested in your PR.

Thank you!

The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. The docs are available until 30 days after the last update.

Hi @rootonchair, did you try to run this test script on google colab first?

Hi @Bhavay-2001 , I haven't ran with Cobal yet but I did run on my machine's GPU