Update app.py

app.py

@@ -19,23 +19,30 @@ pipe.scheduler = UniPCMultistepScheduler.from_config(pipe.scheduler.config)
 
 MAX_SEED = np.iinfo(np.int32).max
 
-# Function to generate images based on user input
-def generate_user_data(object_classes, object_bboxes):
+# Store objects
+object_classes_list = []
+object_bboxes_list = []
+
+# Function to add a new object
+def add_object(object_class, bbox):
+    object_classes_list.append(object_class)
+    object_bboxes_list.append(bbox)
+    # Return updated list of objects
+    return object_classes_list, object_bboxes_list
+
+# Function to generate images based on added objects
+def generate_image(prompt, guidance_scale, num_inference_steps, randomize_seed, seed):
     img_width, img_height = 512, 512
     r_image = np.zeros((img_height, img_width, 3), dtype=np.uint8)
     list_cond_image = []
 
-    for bbox in object_bboxes:
+    # Process bounding boxes and create conditional images
+    for bbox in object_bboxes_list:
         x1, y1, x2, y2 = map(int, bbox.split(","))
         cond_image = np.zeros_like(r_image, dtype=np.uint8)
         cond_image[y1:y2, x1:x2] = 255
         list_cond_image.append(Image.fromarray(cond_image).convert('RGB'))
 
-    return object_classes.split(","), list_cond_image
-
-# Inference function
-def infer(prompt, guidance_scale, num_inference_steps, randomize_seed, seed, object_classes, object_bboxes):
-    obj_classes, list_cond_image_pil = generate_user_data(object_classes, object_bboxes)
     if randomize_seed or seed is None:
         seed = np.random.randint(0, MAX_SEED)
 
@@ -43,11 +50,11 @@ def infer(prompt, guidance_scale, num_inference_steps, randomize_seed, seed, obj
 
     image = pipe(
         prompt=prompt,
-        layo_prompt=obj_classes,
+        layo_prompt=object_classes_list,
         guess_mode=False,
         guidance_scale=guidance_scale,
         num_inference_steps=num_inference_steps,
-        image=list_cond_image_pil,
+        image=list_cond_image,
         fuse_type="avg",
         width=512,
         height=512
@@ -57,12 +64,17 @@ def infer(prompt, guidance_scale, num_inference_steps, randomize_seed, seed, obj
 
 # Gradio UI
 with gr.Blocks() as demo:
-    gr.Markdown("# Text-to-Image Generator with Manual Input")
+    gr.Markdown("# Text-to-Image Generator with Object Addition")
 
     with gr.Row():
         prompt = gr.Textbox(label="Prompt", placeholder="Enter your prompt here")
-        object_classes = gr.Textbox(label="Object Classes (comma-separated)", placeholder="e.g., Object_1,Object_2")
-        object_bboxes = gr.Textbox(label="Bounding Boxes (format: x1,y1,x2,y2; separated by commas)", placeholder="e.g., 50,50,150,150")
+    
+    object_class_input = gr.Textbox(label="Object Class", placeholder="Enter object class (e.g., Object_1)")
+    bbox_input = gr.Textbox(label="Bounding Box (x1,y1,x2,y2)", placeholder="Enter bounding box coordinates")
+    add_button = gr.Button("Add Object")
+
+    # Display list of added objects
+    objects_display = gr.Dataframe(headers=["Object Class", "Bounding Box"], datatype=["str", "str"], value=[])
 
     with gr.Row():
         guidance_scale = gr.Slider(label="Guidance Scale", minimum=0.0, maximum=10.0, step=0.1, value=7.5)
@@ -71,12 +83,20 @@ with gr.Blocks() as demo:
     randomize_seed = gr.Checkbox(label="Randomize Seed", value=True)
     seed = gr.Slider(label="Seed", minimum=0, maximum=MAX_SEED, step=1, value=0)
 
-    run_button = gr.Button("Generate")
+    generate_button = gr.Button("Generate Image")
     result = gr.Image(label="Generated Image")
 
-    run_button.click(
-        infer,
-        inputs=[prompt, guidance_scale, num_inference_steps, randomize_seed, seed, object_classes, object_bboxes],
+    # Add object and update display
+    add_button.click(
+        fn=add_object,
+        inputs=[object_class_input, bbox_input],
+        outputs=[objects_display]
+    )
+
+    # Generate image based on added objects
+    generate_button.click(
+        fn=generate_image,
+        inputs=[prompt, guidance_scale, num_inference_steps, randomize_seed, seed],
         outputs=[result, seed]
     )