Update app_training.py

app_training.py

@@ -37,65 +37,66 @@ def create_training_demo(trainer: Trainer,
                         visible=False)
                     validation_prompt = gr.Text(label='Validation Prompt')
 
-            with gr.Box():
-                gr.Markdown('Training Parameters')
-                with gr.Row():
-                    base_model = gr.Text(label='Base Model',
-                                         value='CompVis/stable-diffusion-v1-4',
-                                         max_lines=1)
-                    resolution = gr.Dropdown(choices=['512', '768'],
-                                             value='512',
-                                             label='Resolution',
-                                             visible=False)
-                
-                token = gr.Text(label="Hugging Face Write Token", placeholder="", visible=False if hf_token else True)
-                with gr.Accordion("Advanced settings", open=False):
-                    num_training_steps = gr.Number(
-                        label='Number of Training Steps', value=300, precision=0)
-                    learning_rate = gr.Number(label='Learning Rate',
-                                              value=0.000035)
-                    gradient_accumulation = gr.Number(
-                        label='Number of Gradient Accumulation',
-                        value=1,
-                        precision=0)
-                    seed = gr.Slider(label='Seed',
-                                     minimum=0,
-                                     maximum=100000,
-                                     step=1,
-                                     randomize=True,
-                                     value=0)
-                    fp16 = gr.Checkbox(label='FP16', value=True)
-                    use_8bit_adam = gr.Checkbox(label='Use 8bit Adam', value=False)
-                    checkpointing_steps = gr.Number(label='Checkpointing Steps',
-                                                    value=1000,
-                                                    precision=0)
-                    validation_epochs = gr.Number(label='Validation Epochs',
-                                                  value=100,
-                                                  precision=0)
-                gr.Markdown('''
-                    - The base model must be a model that is compatible with [diffusers](https://github.com/huggingface/diffusers) library.
-                    - Expected time to train a model for 300 steps: ~20 minutes with T4
-                    - You can check the training status by pressing the "Open logs" button if you are running this on your Space.
-                    ''')
-            
-            with gr.Box():
-                    gr.Markdown('Upload Settings')
+            with gr.Column():
+                with gr.Box():
+                    gr.Markdown('Training Parameters')
                     with gr.Row():
-                        upload_to_hub = gr.Checkbox(
-                            label='Upload model to Hub', value=True)
-                        use_private_repo = gr.Checkbox(label='Private',
-                                                       value=True)
-                        delete_existing_repo = gr.Checkbox(
-                            label='Delete existing repo of the same name',
-                            value=False)
-                    upload_to = gr.Radio(
-                        label='Upload to',
-                        choices=[_.value for _ in UploadTarget],
-                        value=UploadTarget.MODEL_LIBRARY.value)
-                    gr.Markdown(f'''
-                    - By default, trained models will be uploaded to [Tune-A-Video Library](https://huggingface.co/{MODEL_LIBRARY_ORG_NAME}) (see [this example model](https://huggingface.co/{SAMPLE_MODEL_REPO})).
-                    - You can also choose "Personal Profile", in which case, the model will be uploaded to https://huggingface.co/{{your_username}}/{{model_name}}.
-                    ''')
+                        base_model = gr.Text(label='Base Model',
+                                             value='CompVis/stable-diffusion-v1-4',
+                                             max_lines=1)
+                        resolution = gr.Dropdown(choices=['512', '768'],
+                                                 value='512',
+                                                 label='Resolution',
+                                                 visible=False)
+                    
+                    token = gr.Text(label="Hugging Face Write Token", placeholder="", visible=False if hf_token else True)
+                    with gr.Accordion("Advanced settings", open=False):
+                        num_training_steps = gr.Number(
+                            label='Number of Training Steps', value=300, precision=0)
+                        learning_rate = gr.Number(label='Learning Rate',
+                                                  value=0.000035)
+                        gradient_accumulation = gr.Number(
+                            label='Number of Gradient Accumulation',
+                            value=1,
+                            precision=0)
+                        seed = gr.Slider(label='Seed',
+                                         minimum=0,
+                                         maximum=100000,
+                                         step=1,
+                                         randomize=True,
+                                         value=0)
+                        fp16 = gr.Checkbox(label='FP16', value=True)
+                        use_8bit_adam = gr.Checkbox(label='Use 8bit Adam', value=False)
+                        checkpointing_steps = gr.Number(label='Checkpointing Steps',
+                                                        value=1000,
+                                                        precision=0)
+                        validation_epochs = gr.Number(label='Validation Epochs',
+                                                      value=100,
+                                                      precision=0)
+                    gr.Markdown('''
+                        - The base model must be a model that is compatible with [diffusers](https://github.com/huggingface/diffusers) library.
+                        - Expected time to train a model for 300 steps: ~20 minutes with T4
+                        - You can check the training status by pressing the "Open logs" button if you are running this on your Space.
+                        ''')
+                
+                with gr.Box():
+                        gr.Markdown('Upload Settings')
+                        with gr.Row():
+                            upload_to_hub = gr.Checkbox(
+                                label='Upload model to Hub', value=True)
+                            use_private_repo = gr.Checkbox(label='Private',
+                                                           value=True)
+                            delete_existing_repo = gr.Checkbox(
+                                label='Delete existing repo of the same name',
+                                value=False)
+                        upload_to = gr.Radio(
+                            label='Upload to',
+                            choices=[_.value for _ in UploadTarget],
+                            value=UploadTarget.MODEL_LIBRARY.value)
+                        gr.Markdown(f'''
+                        - By default, trained models will be uploaded to [Tune-A-Video Library](https://huggingface.co/{MODEL_LIBRARY_ORG_NAME}) (see [this example model](https://huggingface.co/{SAMPLE_MODEL_REPO})).
+                        - You can also choose "Personal Profile", in which case, the model will be uploaded to https://huggingface.co/{{your_username}}/{{model_name}}.
+                        ''')
         remove_gpu_after_training = gr.Checkbox(
             label='Remove GPU after training',
             value=False,