Update app.py

app.py

@@ -1,5 +1,3 @@
-import numpy
-import gradio as gr
 import plotly.graph_objects as go
 
 import torch
@@ -11,25 +9,32 @@ from point_e.models.download import load_checkpoint
 from point_e.models.configs import MODEL_CONFIGS, model_from_config
 from point_e.util.plotting import plot_point_cloud
 
+import gradio as gr
+
+# Select device (CUDA if available, otherwise CPU)
 device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
 
-print('creating base model...')
+# Initialize base model
+print('Creating base model...')
 base_name = 'base40M-textvec'
 base_model = model_from_config(MODEL_CONFIGS[base_name], device)
 base_model.eval()
 base_diffusion = diffusion_from_config(DIFFUSION_CONFIGS[base_name])
 
-print('creating upsample model...')
+# Initialize upsample model
+print('Creating upsample model...')
 upsampler_model = model_from_config(MODEL_CONFIGS['upsample'], device)
 upsampler_model.eval()
 upsampler_diffusion = diffusion_from_config(DIFFUSION_CONFIGS['upsample'])
 
-print('downloading base checkpoint...')
+# Load checkpoints
+print('Downloading base checkpoint...')
 base_model.load_state_dict(load_checkpoint(base_name, device))
 
-print('downloading upsampler checkpoint...')
+print('Downloading upsampler checkpoint...')
 upsampler_model.load_state_dict(load_checkpoint('upsample', device))
 
+# Initialize sampler
 sampler = PointCloudSampler(
     device=device,
     models=[base_model, upsampler_model],
@@ -37,50 +42,34 @@ sampler = PointCloudSampler(
     num_points=[1024, 4096 - 1024],
     aux_channels=['R', 'G', 'B'],
     guidance_scale=[3.0, 0.0],
-    model_kwargs_key_filter=('texts', ''), # Do not condition the upsampler at all
+    model_kwargs_key_filter=('texts', ''),  # Do not condition the upsampler at all
 )
 
-def inference(prompt):
+# Function to create point clouds
+def create_point_cloud(inp):
+    # Generate progressive samples
     samples = None
-    for x in sampler.sample_batch_progressive(batch_size=1, model_kwargs=dict(texts=[prompt])):
+    for x in tqdm(sampler.sample_batch_progressive(batch_size=1, model_kwargs=dict(texts=[inp]))):
         samples = x
+
+    # Extract the point cloud
     pc = sampler.output_to_point_clouds(samples)[0]
-    pc = sampler.output_to_point_clouds(samples)[0]
-    colors=(238, 75, 43)
-    fig = go.Figure(
-        data=[
-            go.Scatter3d(
-                x=pc.coords[:,0], y=pc.coords[:,1], z=pc.coords[:,2], 
-                mode='markers',
-                marker=dict(
-                  size=2,
-                  color=['rgb({},{},{})'.format(r,g,b) for r,g,b in zip(pc.channels["R"], pc.channels["G"], pc.channels["B"])],
-              )
-            )
-        ],
-        layout=dict(
-            scene=dict(
-                xaxis=dict(visible=False),
-                yaxis=dict(visible=False),
-                zaxis=dict(visible=False)
-            )
-        ),
-    )
-    return fig
 
+    # Generate a Plotly figure for visualization
+    fig = plot_point_cloud(pc, grid_size=3, fixed_bounds=((-0.75, -0.75, -0.75), (0.75, 0.75, 0.75)))
+
+    # Convert Plotly figure to HTML for Gradio compatibility
+    return fig.to_html(full_html=False)
+
+# Create Gradio interface
 demo = gr.Interface(
-    fn=inference,
+    fn=create_point_cloud,
     inputs="text",
-    outputs=gr.Plot(),
-    examples=[
-        ["a red motorcycle"],
-        ["a RED pumpkin"],
-        ["a yellow rubber duck"]
-    ],
-    title="Point-E demo: text to 3D",
-    description="""Generated 3D Point Clouds with [Point-E](https://github.com/openai/point-e/tree/main). This demo uses a small, worse quality text-to-3D model to produce 3D point clouds directly from text descriptions.
-    Check out the [notebook](https://github.com/openai/point-e/blob/main/point_e/examples/text2pointcloud.ipynb).
-"""
+    outputs=gr.HTML(),  # Gradio expects HTML for Plotly visualizations
+    title="Point-E Demo - Convert Text to 3D Point Clouds",
+    description="Generate and visualize 3D point clouds from textual descriptions using OpenAI's Point-E framework."
 )
+
+# Enable queuing and launch Gradio app
 demo.queue(max_size=30)
-demo.launch(debug=True)
+demo.launch(debug=True)