Add note on how to use
Browse files- app_training.py +2 -0
app_training.py
CHANGED
|
@@ -83,6 +83,8 @@ def create_training_demo(trainer: Trainer,
|
|
| 83 |
value=100,
|
| 84 |
precision=0)
|
| 85 |
gr.Markdown('''
|
|
|
|
|
|
|
| 86 |
- It will take about 8 minutes to train for 1000 steps with a T4 GPU.
|
| 87 |
- You may want to try a small number of steps first, like 1, to see if everything works fine in your environment.
|
| 88 |
- You need to set the environment variable `WANDB_API_KEY` if you'd like to use W&B. See [W&B documentation](https://docs.wandb.ai/guides/track/advanced/environment-variables).
|
|
|
|
| 83 |
value=100,
|
| 84 |
precision=0)
|
| 85 |
gr.Markdown('''
|
| 86 |
+
- The base model must be a model that is compatible with [diffusers](https://github.com/huggingface/diffusers) library.
|
| 87 |
+
- It takes a few minutes to download the base model first.
|
| 88 |
- It will take about 8 minutes to train for 1000 steps with a T4 GPU.
|
| 89 |
- You may want to try a small number of steps first, like 1, to see if everything works fine in your environment.
|
| 90 |
- You need to set the environment variable `WANDB_API_KEY` if you'd like to use W&B. See [W&B documentation](https://docs.wandb.ai/guides/track/advanced/environment-variables).
|