modify the interface design.

app.py

@@ -113,7 +113,9 @@ with block:
     with gr.Row():  
         gr.Markdown(description)  
         only_show_rendered_image = gr.Number(value=1, visible=False)
-        
+    default_width = [0.3, 0.3, 0.3, 0.3]
+    default_top_left_x = [0.35, 0.15, 0.15, 0.5]
+    default_top_left_y = [0.5, 0.25, 0.75, 0.75]
     with gr.Column():  
             
         with gr.Row(): 
@@ -122,11 +124,13 @@ with block:
                     exec(f"""rendered_txt_{i} = gr.Textbox(label=f"Render Text {i+1}")""")
                     
                     with gr.Accordion(f"Advanced options {i+1}", open=False):  
-                        exec(f"""width_{i} = gr.Slider(label="Bbox Width", minimum=0., maximum=1, value=0.3, step=0.01)  """)
+                        exec(f"""width_{i} = gr.Slider(label="Bbox Width", minimum=0., maximum=1, value={default_width[i]}, step=0.01)  """)
                         exec(f"""ratio_{i} = gr.Slider(label="Bbox_width_height_ratio", minimum=0., maximum=5, value=0., step=0.02, visible=False)  """)
-                        exec(f"""top_left_x_{i} = gr.Slider(label="Bbox Top Left x", minimum=0., maximum=1, value={0.35 - 0.25 * math.cos(math.pi * i)}, step=0.01)  """)
-                        exec(f"""top_left_y_{i} = gr.Slider(label="Bbox Top Left y", minimum=0., maximum=1, value={0.1 if i < 2 else 0.6}, step=0.01)  """)
-                        exec(f"""yaw_{i} = gr.Slider(label="Bbox Yaw", minimum=-180, maximum=180, value=0, step=5) """)
+                        # exec(f"""top_left_x_{i} = gr.Slider(label="Bbox Top Left x", minimum=0., maximum=1, value={0.35 - 0.25 * math.cos(math.pi * i)}, step=0.01)  """)
+                        # exec(f"""top_left_y_{i} = gr.Slider(label="Bbox Top Left y", minimum=0., maximum=1, value={0.1 if i < 2 else 0.6}, step=0.01)  """)
+                        exec(f"""top_left_x_{i} = gr.Slider(label="Bbox Top Left x", minimum=0., maximum=1, value={default_top_left_x[i]}, step=0.01)  """)
+                        exec(f"""top_left_y_{i} = gr.Slider(label="Bbox Top Left y", minimum=0., maximum=1, value={default_top_left_y[i]}, step=0.01)  """)
+                        exec(f"""yaw_{i} = gr.Slider(label="Bbox Yaw", minimum=-20, maximum=20, value=0, step=5) """)
                         # exec(f"""num_rows_{i} = gr.Slider(label="num_rows", minimum=1, maximum=4, value=1, step=1, visible=False)  """)
                         exec(f"""num_rows_{i} = gr.Slider(label="num_rows", minimum=1, maximum=4, value=1, step=1)  """)
         
@@ -134,8 +138,8 @@ with block:
             with gr.Column():
                 shared_prompt = gr.Textbox(label="Shared Prompt")
                 with gr.Row():
-                    run_button = gr.Button(value="Run")
                     show_render_button = gr.Button(value="Only Rendered")
+                    run_button = gr.Button(value="Run")     
                 with gr.Accordion("Model Options", open=False):
                     with gr.Row():
                         # model_ckpt = gr.inputs.Dropdown(["LAION-Glyph-10M", "Textcaps5K-10"], label="Checkpoint", default = "LAION-Glyph-10M")

config_cuda.yaml

@@ -1,88 +0,0 @@
-model:
-  base_learning_rate: 1.0e-6 #1.0e-5 #1.0e-4
-  target: cldm.cldm.ControlLDM
-  params:
-    linear_start: 0.00085
-    linear_end: 0.0120
-    num_timesteps_cond: 1
-    log_every_t: 200
-    timesteps: 1000
-    first_stage_key: "jpg"
-    cond_stage_key: "txt"
-    control_key: "hint"
-    image_size: 64
-    channels: 4
-    cond_stage_trainable: false
-    conditioning_key: crossattn
-    monitor: #val/loss_simple_ema
-    scale_factor: 0.18215
-    only_mid_control: False
-    sd_locked: True
-    use_ema: False #TODO: specify
-
-    control_stage_config:
-      target: cldm.cldm.ControlNet
-      params:
-        use_checkpoint: True
-        image_size: 32 # unused
-        in_channels: 4
-        hint_channels: 3
-        model_channels: 320
-        attention_resolutions: [ 4, 2, 1 ]
-        num_res_blocks: 2
-        channel_mult: [ 1, 2, 4, 4 ]
-        num_head_channels: 64 # need to fix for flash-attn
-        use_spatial_transformer: True
-        use_linear_in_transformer: True
-        transformer_depth: 1
-        context_dim: 1024
-        legacy: False
-
-    unet_config:
-      target: cldm.cldm.ControlledUnetModel
-      params:
-        use_checkpoint: True
-        image_size: 32 # unused
-        in_channels: 4
-        out_channels: 4
-        model_channels: 320
-        attention_resolutions: [ 4, 2, 1 ]
-        num_res_blocks: 2
-        channel_mult: [ 1, 2, 4, 4 ]
-        num_head_channels: 64 # need to fix for flash-attn
-        use_spatial_transformer: True
-        use_linear_in_transformer: True
-        transformer_depth: 1
-        context_dim: 1024
-        legacy: False
-
-    first_stage_config:
-      target: ldm.models.autoencoder.AutoencoderKL
-      params:
-        embed_dim: 4
-        monitor: val/rec_loss
-        ddconfig:
-          #attn_type: "vanilla-xformers"
-          double_z: true
-          z_channels: 4
-          resolution: 256
-          in_channels: 3
-          out_ch: 3
-          ch: 128
-          ch_mult:
-          - 1
-          - 2
-          - 4
-          - 4
-          num_res_blocks: 2
-          attn_resolutions: []
-          dropout: 0.0
-        lossconfig:
-          target: torch.nn.Identity
-
-    cond_stage_config:
-      target: ldm.modules.encoders.modules.FrozenOpenCLIPEmbedder
-      params:
-        freeze: True
-        layer: "penultimate"
-        # device: "cpu" #TODO: specify