Update app.py

app.py

@@ -1,56 +1,78 @@
 import gradio as gr
 import numpy as np
 import random
-
-# import spaces #[uncomment to use ZeroGPU]
-from diffusers import DiffusionPipeline
+from PIL import Image
 import torch
+from diffusers import ControlNetModel, UniPCMultistepScheduler
+from hico_pipeline import StableDiffusionControlNetMultiLayoutPipeline
 
 device = "cuda" if torch.cuda.is_available() else "cpu"
-model_repo_id = "stabilityai/sdxl-turbo"  # Replace to the model you would like to use
-
-if torch.cuda.is_available():
-    torch_dtype = torch.float16
-else:
-    torch_dtype = torch.float32
 
-pipe = DiffusionPipeline.from_pretrained(model_repo_id, torch_dtype=torch_dtype)
+# Initialize model
+controlnet = ControlNetModel.from_pretrained("qihoo360/HiCo_T2I", torch_dtype=torch.float16)
+pipe = StableDiffusionControlNetMultiLayoutPipeline.from_pretrained(
+    "krnl/realisticVisionV51_v51VAE", controlnet=[controlnet], torch_dtype=torch.float16
+)
 pipe = pipe.to(device)
+pipe.scheduler = UniPCMultistepScheduler.from_config(pipe.scheduler.config)
 
 MAX_SEED = np.iinfo(np.int32).max
-MAX_IMAGE_SIZE = 1024
 
+# Function for generating dummy bounding box and label data
+def generate_dummy_data():
+    # Generate random image size
+    img_width, img_height = 512, 512
+    r_image = np.zeros((img_height, img_width, 3), dtype=np.uint8)
+
+    # Generate random bounding boxes and labels
+    num_objects = random.randint(1, 5)
+    r_obj_bbox = []
+    r_obj_class = ["Object"]
+    list_cond_image = []
+
+    for _ in range(num_objects):
+        x1, y1 = random.randint(0, img_width // 2), random.randint(0, img_height // 2)
+        x2, y2 = random.randint(x1, img_width), random.randint(y1, img_height)
+        r_obj_bbox.append([x1, y1, x2, y2])
+        cond_image = np.zeros_like(r_image, dtype=np.uint8)
+        cond_image[y1:y2, x1:x2] = 255
+        list_cond_image.append(cond_image)
+
+    r_obj_bbox.insert(0, [0, 0, img_width, img_height])  # Add background
+    r_obj_class.insert(0, "Background")
+    list_cond_image.insert(0, np.zeros_like(r_image, dtype=np.uint8))  # Add full background
+
+    obj_cond_image = np.stack(list_cond_image, axis=0)
+    list_cond_image_pil = [Image.fromarray(img).convert('RGB') for img in list_cond_image]
 
-# @spaces.GPU #[uncomment to use ZeroGPU]
+    return r_obj_class, r_obj_bbox, list_cond_image_pil, obj_cond_image
+
+# Inference function
 def infer(
-    prompt,
-    negative_prompt,
-    seed,
-    randomize_seed,
-    width,
-    height,
-    guidance_scale,
-    num_inference_steps,
-    progress=gr.Progress(track_tqdm=True),
+    prompt, guidance_scale, num_inference_steps, randomize_seed, seed=None
 ):
-    if randomize_seed:
+    # Generate dummy data for demonstration
+    r_obj_class, r_obj_bbox, list_cond_image_pil, _ = generate_dummy_data()
+    if randomize_seed or seed is None:
         seed = random.randint(0, MAX_SEED)
 
-    generator = torch.Generator().manual_seed(seed)
+    generator = torch.manual_seed(seed)
 
+    # Run inference
     image = pipe(
         prompt=prompt,
-        negative_prompt=negative_prompt,
+        layo_prompt=r_obj_class,
+        guess_mode=False,
         guidance_scale=guidance_scale,
         num_inference_steps=num_inference_steps,
-        width=width,
-        height=height,
-        generator=generator,
+        image=list_cond_image_pil,
+        fuse_type="avg",
+        width=512,
+        height=512
     ).images[0]
 
     return image, seed
 
-
 examples = [
     "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k",
     "An astronaut riding a green horse",
@@ -64,6 +86,7 @@ css = """
 }
 """
 
+# Gradio UI
 with gr.Blocks(css=css) as demo:
     with gr.Column(elem_id="col-container"):
         gr.Markdown(" # Text-to-Image Gradio Template")
@@ -76,19 +99,11 @@ with gr.Blocks(css=css) as demo:
                 placeholder="Enter your prompt",
                 container=False,
             )
-
             run_button = gr.Button("Run", scale=0, variant="primary")
 
         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,
@@ -99,30 +114,13 @@ with gr.Blocks(css=css) as demo:
 
             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=1024,  # Replace with defaults that work for your model
-                )
-
-                height = gr.Slider(
-                    label="Height",
-                    minimum=256,
-                    maximum=MAX_IMAGE_SIZE,
-                    step=32,
-                    value=1024,  # Replace with defaults that work for your model
-                )
-
             with gr.Row():
                 guidance_scale = gr.Slider(
                     label="Guidance scale",
                     minimum=0.0,
                     maximum=10.0,
                     step=0.1,
-                    value=0.0,  # Replace with defaults that work for your model
+                    value=7.5,
                 )
 
                 num_inference_steps = gr.Slider(
@@ -130,22 +128,19 @@ with gr.Blocks(css=css) as demo:
                     minimum=1,
                     maximum=50,
                     step=1,
-                    value=2,  # Replace with defaults that work for your model
+                    value=50,
                 )
 
         gr.Examples(examples=examples, inputs=[prompt])
-    gr.on(
-        triggers=[run_button.click, prompt.submit],
+
+    run_button.click(
         fn=infer,
         inputs=[
             prompt,
-            negative_prompt,
-            seed,
-            randomize_seed,
-            width,
-            height,
             guidance_scale,
             num_inference_steps,
+            randomize_seed,
+            seed,
         ],
         outputs=[result, seed],
     )