Upload . with huggingface_hub

README.md

@@ -0,0 +1,17 @@
+---
+license: creativeml-openrail-m
+base_model: stabilityai/stable-diffusion-xl-base-1.0
+instance_prompt: TOK
+tags:
+- stable-diffusion
+- stable-diffusion-diffusers
+- text-to-image
+- diffusers
+- lora
+inference: true
+---
+# LoRA DreamBooth - barbie2
+
+These are LoRA adaption weights for [stabilityai/stable-diffusion-xl-base-1.0](https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0). The weights were trained on the instance prompt "TOK" using [DreamBooth](https://dreambooth.github.io/). You can find some example images in the following.
+
+

train.sh

@@ -0,0 +1 @@
+accelerate launch train_dreambooth_lora.py --pretrained_model_name_or_path=stabilityai/stable-diffusion-xl-base-1.0 --instance_data_dir=/home/user/app/training_data/barbie2 --output_dir=/home/user/app/experiments/barbie2 --instance_prompt="TOK" --resolution=512 --train_batch_size=1 --gradient_accumulation_steps=1 --learning_rate=0.0001 --lr_scheduler=constant --lr_warmup_steps=0 --max_train_steps=1000 --checkpointing_steps=100 --validation_prompt="A photo in the style of TOK" --validation_epochs=100 --seed=0 --mixed_precision fp16