Skip to content

GitLab

Unverified Commit 7d96b38b authored by Sayak Paul's avatar Sayak Paul Committed by GitHub
Browse files

[examples] Fix CLI argument in the launch script command for text2image with LoRA (#2171) 

* Update README.md

* Update README.md
parent cedafb86
Show whitespace changes
Inline Side-by-side
Showing with 2 additions and 2 deletions
examples/text_to_image/README.md
View file @ 7d96b38b
...@@ -148,7 +148,7 @@ huggingface-cli login ...@@ -148,7 +148,7 @@ huggingface-cli login
Now we can start training! Now we can start training!
```bash ```bash
accelerate --mixed_precision="fp16" launch train_text_to_image_lora.py \ accelerate launch --mixed_precision="fp16" train_text_to_image_lora.py \
--pretrained_model_name_or_path=$MODEL_NAME \ --pretrained_model_name_or_path=$MODEL_NAME \
--dataset_name=$DATASET_NAME --caption_column="text" \ --dataset_name=$DATASET_NAME --caption_column="text" \
--resolution=512 --random_flip \ --resolution=512 --random_flip \
...@@ -157,7 +157,7 @@ accelerate --mixed_precision="fp16" launch train_text_to_image_lora.py \ ...@@ -157,7 +157,7 @@ accelerate --mixed_precision="fp16" launch train_text_to_image_lora.py \
--learning_rate=1e-04 --lr_scheduler="constant" --lr_warmup_steps=0 \ --learning_rate=1e-04 --lr_scheduler="constant" --lr_warmup_steps=0 \
--seed=42 \ --seed=42 \
--output_dir="sd-pokemon-model-lora" \ --output_dir="sd-pokemon-model-lora" \
--save_sample_prompt="cute dragon creature" --report_to="wandb" --validation_prompt="cute dragon creature" --report_to="wandb"
``` ```
The above command will also run inference as fine-tuning progresses and log the results to Weights and Biases. The above command will also run inference as fine-tuning progresses and log the results to Weights and Biases.
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment