LoRA text2image fine-tuning - ButterChicken98/plantVillage-stableDiffusion-2-iter1

These are LoRA adaption weights for stabilityai/stable-diffusion-2. The weights were fine-tuned on the ButterChicken98/plantvillage-image-text-pairs dataset. You can find some example images in the following.

Intended uses & limitations

How to use

# TODO: add an example code snippet for running this diffusion pipeline

Limitations and bias

[TODO: provide examples of latent issues and potential remediations]

Training details

! accelerate launch /kaggle/working/diffusers/examples/text_to_image/train_text_to_image_lora.py
--pretrained_model_name_or_path="stabilityai/stable-diffusion-2"
--dataset_name="ButterChicken98/plantvillage-image-text-pairs"
--dataloader_num_workers=8
--resolution=256 --random_flip
--train_batch_size=16
--gradient_accumulation_steps=4
--max_train_steps=3000
--learning_rate=1e-04
--max_grad_norm=1
--lr_scheduler="cosine" --lr_warmup_steps=0
--output_dir="/kaggle/working"
--push_to_hub
--caption_column="captions"
--image_column="image"
--hub_model_id="plantVillage-stableDiffusion-2-iter1"
--checkpointing_steps=1000
--validation_prompt="An image of a tomato plant leaf with symptoms of Tomato Yellow Leaf Curl Virus for agricultural datasets"
--seed=1337