File size: 4,531 Bytes
3f6feda
 
 
722243d
3f6feda
722243d
 
3f6feda
 
 
722243d
 
 
 
 
3f6feda
722243d
3f6feda
 
 
722243d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3f6feda
722243d
 
 
3f6feda
722243d
3f6feda
722243d
 
 
3f6feda
 
722243d
3f6feda
722243d
3f6feda
 
722243d
 
3f6feda
 
722243d
 
 
 
3f6feda
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
722243d
3f6feda
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
722243d
3f6feda
 
 
 
 
 
 
722243d
3f6feda
 
 
722243d
 
3f6feda
 
 
 
 
722243d
 
3f6feda
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
import gradio as gr
import numpy as np
import random
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"

# 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

# 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]

    return r_obj_class, r_obj_bbox, list_cond_image_pil, obj_cond_image

# Inference function
def infer(
    prompt, guidance_scale, num_inference_steps, randomize_seed, seed=None
):
    # 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.manual_seed(seed)

    # Run inference
    image = pipe(
        prompt=prompt,
        layo_prompt=r_obj_class,
        guess_mode=False,
        guidance_scale=guidance_scale,
        num_inference_steps=num_inference_steps,
        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",
    "A delicious ceviche cheesecake slice",
]

css = """
#col-container {
    margin: 0 auto;
    max-width: 640px;
}
"""

# Gradio UI
with gr.Blocks(css=css) as demo:
    with gr.Column(elem_id="col-container"):
        gr.Markdown(" # Text-to-Image Gradio Template")

        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, variant="primary")

        result = gr.Image(label="Result", show_label=False)

        with gr.Accordion("Advanced Settings", open=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():
                guidance_scale = gr.Slider(
                    label="Guidance scale",
                    minimum=0.0,
                    maximum=10.0,
                    step=0.1,
                    value=7.5,
                )

                num_inference_steps = gr.Slider(
                    label="Number of inference steps",
                    minimum=1,
                    maximum=50,
                    step=1,
                    value=50,
                )

        gr.Examples(examples=examples, inputs=[prompt])

    run_button.click(
        fn=infer,
        inputs=[
            prompt,
            guidance_scale,
            num_inference_steps,
            randomize_seed,
            seed,
        ],
        outputs=[result, seed],
    )

if __name__ == "__main__":
    demo.launch()