Update app.py

app.py

@@ -1,146 +1,116 @@
 import gradio as gr
-import numpy as np
-import random
-from diffusers import DiffusionPipeline
 import torch
+from PIL import Image
+import numpy as np
+import cv2
+from diffusers import StableDiffusionPipeline
 
+# Setup the model
 device = "cuda" if torch.cuda.is_available() else "cpu"
+model_id = "stabilityai/sdxl-turbo"
+pipe = StableDiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.float16 if device == "cuda" else torch.float32)
+pipe = pipe.to(device)
 
-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] 
-    
+# Generate T-shirt design function
+def generate_tshirt_design(style, color, graphics, text=None):
+    prompt = f"T-shirt design, style: {style}, color: {color}, graphics: {graphics}"
+    if text:
+        prompt += f", text: {text}"
+    image = pipe(prompt).images[0]
     return image
 
+# T-shirt mockup generator with Gradio interface
 examples = [
-    "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k",
-    "An astronaut riding a green horse",
-    "A delicious ceviche cheesecake slice",
+    ["Casual", "White", "Logo: MyBrand", None],
+    ["Formal", "Black", "Text: Hello World", "Custom text"],
+    ["Sports", "Red", "Graphic: Team logo", None],
 ]
 
-css="""
+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}.
+        gr.Markdown("""
+        # T-shirt Mockup Generator with Rookus AI
         """)
-        
+
         with gr.Row():
-            
-            prompt = gr.Text(
-                label="Prompt",
-                show_label=False,
-                max_lines=1,
-                placeholder="Enter your prompt",
+            style = gr.Dropdown(
+                label="T-shirt Style",
+                choices=["Casual", "Formal", "Sports"],
+                value="Casual",
                 container=False,
             )
-            
-            run_button = gr.Button("Run", scale=0)
-        
-        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,
+
+            run_button = gr.Button("Generate Mockup", scale=0)
+
+        result = gr.Image(label="Mockup", show_label=False)
+
+        with gr.Accordion("Design Options", open=False):
+            color = gr.Radio(
+                label="T-shirt Color",
+                choices=["White", "Black", "Blue", "Red", "Green"],
+                value="White",
+            )
+
+            graphics = gr.Textbox(
+                label="Graphics/Logo",
+                placeholder="Enter graphics or logo details",
+                visible=True,
             )
-            
-            seed = gr.Slider(
-                label="Seed",
-                minimum=0,
-                maximum=MAX_SEED,
-                step=1,
-                value=0,
+
+            text = gr.Textbox(
+                label="Text (optional)",
+                placeholder="Enter optional text",
+                visible=True,
             )
-            
-            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]
+            examples=examples,
+            inputs=[style, color, graphics, text]
         )
 
+    def generate_tshirt_mockup(style, color, graphics, text=None):
+        # Generate T-shirt design
+        design_image = generate_tshirt_design(style, color, graphics, text)
+
+        # Load blank T-shirt mockup template image
+        mockup_template = Image.open("path/to/your/mockup/template.jpg")  # Update the path to your mockup template
+
+        # Convert design image and mockup template to numpy arrays
+        design_np = np.array(design_image)
+        mockup_np = np.array(mockup_template)
+
+        # Resize design image to fit mockup (example resizing)
+        design_resized = cv2.resize(design_np, (mockup_np.shape[1] // 2, mockup_np.shape[0] // 2))
+
+        # Example: Overlay design onto mockup using OpenCV
+        y_offset = mockup_np.shape[0] // 4
+        x_offset = mockup_np.shape[1] // 4
+        y1, y2 = y_offset, y_offset + design_resized.shape[0]
+        x1, x2 = x_offset, x_offset + design_resized.shape[1]
+
+        alpha_s = design_resized[:, :, 3] / 255.0 if design_resized.shape[2] == 4 else np.ones(design_resized.shape[:2])
+        alpha_l = 1.0 - alpha_s
+
+        for c in range(0, 3):
+            mockup_np[y1:y2, x1:x2, c] = (alpha_s * design_resized[:, :, c] +
+                                          alpha_l * mockup_np[y1:y2, x1:x2, c])
+
+        # Convert back to PIL image for Gradio output
+        result_image = Image.fromarray(mockup_np)
+
+        return result_image
+
     run_button.click(
-        fn = infer,
-        inputs = [prompt, negative_prompt, seed, randomize_seed, width, height, guidance_scale, num_inference_steps],
-        outputs = [result]
+        fn=generate_tshirt_mockup,
+        inputs=[style, color, graphics, text],
+        outputs=[result]
     )
 
-demo.queue().launch()
+demo.queue().launch()