Upload . with huggingface_hub
Browse files
README.md
ADDED
|
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: creativeml-openrail-m
|
| 3 |
+
base_model: stabilityai/stable-diffusion-2-1-base
|
| 4 |
+
instance_prompt: wufan
|
| 5 |
+
tags:
|
| 6 |
+
- stable-diffusion
|
| 7 |
+
- stable-diffusion-diffusers
|
| 8 |
+
- text-to-image
|
| 9 |
+
- diffusers
|
| 10 |
+
- lora
|
| 11 |
+
inference: true
|
| 12 |
+
---
|
| 13 |
+
# LoRA DreamBooth - lora-dragon-ball-wufan
|
| 14 |
+
|
| 15 |
+
These are LoRA adaption weights for [stabilityai/stable-diffusion-2-1-base](https://huggingface.co/stabilityai/stable-diffusion-2-1-base). The weights were trained on the instance prompt "wufan" using [DreamBooth](https://dreambooth.github.io/). You can find some example images in the following.
|
| 16 |
+
|
| 17 |
+
|
train.sh
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
accelerate launch train_dreambooth_lora.py --pretrained_model_name_or_path=stabilityai/stable-diffusion-2-1-base --instance_data_dir=/home/user/app/training_data/lora-dragon-ball-wufan --output_dir=/home/user/app/experiments/lora-dragon-ball-wufan --instance_prompt="wufan" --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="wufan" --validation_epochs=100 --seed=0 --mixed_precision fp16 --use_8bit_adam --save_model_as="safetensors"
|