Modularize train_text_to_image_lora SD inferencing during and after training in example

[satani99]

What does this PR do?

Part of #6545

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?

@sayakpaul

[satani99]

@sayakpaul

[sayakpaul]

Thanks! Could you also provide a run command with which I could test it?

[HuggingFaceDocBuilderDev]

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.

[satani99]

export MODEL_NAME="CompVis/stable-diffusion-v1-4"
export DATASET_NAME="lambdalabs/naruto-blip-captions"

accelerate launch train_text_to_image_lora.py \
  --pretrained_model_name_or_path=$MODEL_NAME \
  --dataset_name=$DATASET_NAME --caption_column="text" \
  --resolution=512 --random_flip \
  --train_batch_size=1 \
  --num_train_epochs=100 --checkpointing_steps=5000 \
  --learning_rate=1e-04 --lr_scheduler="constant" --lr_warmup_steps=0 \
  --seed=42 \
  --output_dir="sd-pokemon-model-lora" \
  --validation_prompt="cute dragon creature" --report_to="wandb"

[sayakpaul]

Thanks a lot!

Just tested with the following and it is working pretty nicely:

export MODEL_NAME="CompVis/stable-diffusion-v1-4"
export DATASET_NAME="lambdalabs/naruto-blip-captions"

accelerate launch train_text_to_image_lora.py \
  --pretrained_model_name_or_path=$MODEL_NAME \
  --dataset_name=$DATASET_NAME --caption_column="text" \
  --resolution=512 --random_flip \
  --train_batch_size=4 \
  --num_train_epochs=4 --checkpointing_steps=20 \
  --learning_rate=1e-04 --lr_scheduler="constant" --lr_warmup_steps=0 \
  --seed=42 \
  --output_dir="/raid/.cache/huggingface/sd-pokemon-model-lora" \
  --validation_prompt="cute dragon creature" --report_to="wandb"