Update app.py

app.py

@@ -1,146 +1,61 @@
 import gradio as gr
-import numpy as np
-import random
-from diffusers import DiffusionPipeline
 import torch
+import numpy as np
+import matplotlib.pyplot as plt
+from matplotlib.animation import FuncAnimation
+from mpl_toolkits.mplot3d import Axes3D
+from mpl_toolkits.mplot3d.art3d import Poly3DCollection
 
 device = "cuda" if torch.cuda.is_available() else "cpu"
 
-if torch.cuda.is_available():
-    torch.cuda.max_memory_allocated(device=device)
-    pipe = DiffusionPipeline.from_pretrained("stabilityai/sdxl-turbo", torch_dtype=torch.float16, variant="fp16", use_safetensors=True)
-    pipe.enable_xformers_memory_efficient_attention()
-    pipe = pipe.to(device)
-else: 
-    pipe = DiffusionPipeline.from_pretrained("stabilityai/sdxl-turbo", use_safetensors=True)
-    pipe = pipe.to(device)
-
-MAX_SEED = np.iinfo(np.int32).max
-MAX_IMAGE_SIZE = 1024
-
-def infer(prompt, negative_prompt, seed, randomize_seed, width, height, guidance_scale, num_inference_steps):
-
-    if randomize_seed:
-        seed = random.randint(0, MAX_SEED)
-        
-    generator = torch.Generator().manual_seed(seed)
-    
-    image = pipe(
-        prompt = prompt, 
-        negative_prompt = negative_prompt,
-        guidance_scale = guidance_scale, 
-        num_inference_steps = num_inference_steps, 
-        width = width, 
-        height = height,
-        generator = generator
-    ).images[0] 
-    
-    return image
+# Load the models
+vqvae_model = VQVAE().to(device)
+transformer_model = Transformer().to(device)
+vqvae_model.load_state_dict(torch.load("output/VQVAE_imp_resnet_100k_hml3d/net_last.pth", map_location=device))
+transformer_model.load_state_dict(torch.load("output/net_best_fid.pth", map_location=device))
+vqvae_model.eval()
+transformer_model.eval()
+
+
+def create_animation(joints, title="3D Motion", save_path="animation.gif"):
+    fig = plt.figure(figsize=(10, 10))
+    ax = fig.add_subplot(111, projection='3d')
+    data = np.array(joints).T
+    line, = ax.plot(data[0, 0:1], data[1, 0:1], data[2, 0:1])
+
+    def update(num, data, line):
+        line.set_data(data[:2, :num])
+        line.set_3d_properties(data[2, :num])
+        return line,
+
+    ani = FuncAnimation(fig, update, frames=len(joints), fargs=(data, line), interval=50, blit=True)
+    ani.save(save_path, writer='pillow')
+    plt.close(fig)
+    return save_path
+
+def infer(text):
+    # Process text input using the loaded models
+    motion_data = generate_motion(text, vqvae_model, transformer_model)  # Define this function as needed
+    gif_path = create_animation(motion_data, kinematic_tree)
+    return gif_path
 
 examples = [
-    "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k",
-    "An astronaut riding a green horse",
-    "A delicious ceviche cheesecake slice",
+    "Person doing yoga",
+    "A person is dancing ballet",
 ]
 
-css="""
-#col-container {
-    margin: 0 auto;
-    max-width: 520px;
-}
-"""
-
-if torch.cuda.is_available():
-    power_device = "GPU"
-else:
-    power_device = "CPU"
-
-with gr.Blocks(css=css) as demo:
-    
-    with gr.Column(elem_id="col-container"):
-        gr.Markdown(f"""
-        # Text-to-Image Gradio Template
-        Currently running on {power_device}.
-        """)
-        
-        with gr.Row():
-            
-            prompt = gr.Text(
-                label="Prompt",
-                show_label=False,
-                max_lines=1,
-                placeholder="Enter your prompt",
-                container=False,
-            )
-            
-            run_button = gr.Button("Run", scale=0)
+with gr.Blocks(css=".container { max-width: 800px; margin: auto; }") as demo:
+    with gr.Column():
+        gr.Markdown("## 3D Motion Generation")
+        text_input = gr.Textbox(label="Describe the action", placeholder="Enter text description of the action here...")
+        output_image = gr.Image(label="Generated Motion Animation")
+        submit_button = gr.Button("Generate Motion")
         
-        result = gr.Image(label="Result", show_label=False)
-
-        with gr.Accordion("Advanced Settings", open=False):
-            
-            negative_prompt = gr.Text(
-                label="Negative prompt",
-                max_lines=1,
-                placeholder="Enter a negative prompt",
-                visible=False,
-            )
-            
-            seed = gr.Slider(
-                label="Seed",
-                minimum=0,
-                maximum=MAX_SEED,
-                step=1,
-                value=0,
-            )
-            
-            randomize_seed = gr.Checkbox(label="Randomize seed", value=True)
-            
-            with gr.Row():
-                
-                width = gr.Slider(
-                    label="Width",
-                    minimum=256,
-                    maximum=MAX_IMAGE_SIZE,
-                    step=32,
-                    value=512,
-                )
-                
-                height = gr.Slider(
-                    label="Height",
-                    minimum=256,
-                    maximum=MAX_IMAGE_SIZE,
-                    step=32,
-                    value=512,
-                )
-            
-            with gr.Row():
-                
-                guidance_scale = gr.Slider(
-                    label="Guidance scale",
-                    minimum=0.0,
-                    maximum=10.0,
-                    step=0.1,
-                    value=0.0,
-                )
-                
-                num_inference_steps = gr.Slider(
-                    label="Number of inference steps",
-                    minimum=1,
-                    maximum=12,
-                    step=1,
-                    value=2,
-                )
-        
-        gr.Examples(
-            examples = examples,
-            inputs = [prompt]
+        submit_button.click(
+            fn=infer,
+            inputs=text_input,
+            outputs=output_image
         )
 
-    run_button.click(
-        fn = infer,
-        inputs = [prompt, negative_prompt, seed, randomize_seed, width, height, guidance_scale, num_inference_steps],
-        outputs = [result]
-    )
-
-demo.queue().launch()
+if __name__ == "__main__":
+    demo.launch()