File size: 5,142 Bytes
ef6c3c2
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
import gradio as gr
import numpy as np
import random
import torch
from PIL import Image
import os
from huggingface_hub import hf_hub_download
from pathlib import Path
import sys

# Add src directory to Python path
sys.path.append(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))

from src import model_loader
from src import pipeline
from src.config import Config, DeviceConfig
from transformers import CLIPTokenizer

# Create data directory if it doesn't exist
data_dir = Path("data")
data_dir.mkdir(exist_ok=True)

# Model configuration
MODEL_REPO = "stable-diffusion-v1-5/stable-diffusion-v1-5"
MODEL_FILENAME = "v1-5-pruned-emaonly.ckpt"
model_file = data_dir / MODEL_FILENAME

# Download model if it doesn't exist
if not model_file.exists():
    print(f"Downloading model from {MODEL_REPO}...")
    model_file = hf_hub_download(
        repo_id=MODEL_REPO,
        filename=MODEL_FILENAME,
        local_dir=data_dir,
        local_dir_use_symlinks=False
    )
    print("Model downloaded successfully!")

# Device configuration
device = "cuda" if torch.cuda.is_available() else "cpu"
print(f"Using device: {device}")

# Initialize configuration
config = Config(
    device=DeviceConfig(device=device),
    tokenizer=CLIPTokenizer.from_pretrained("openai/clip-vit-base-patch32")
)

# Load models with SE blocks enabled
config.models = model_loader.load_models(str(model_file), device, use_se=True)

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,
    progress=gr.Progress(track_tqdm=True),
):
    if randomize_seed:
        seed = random.randint(0, MAX_SEED)
    
    # Update config with user settings
    config.seed = seed
    config.diffusion.cfg_scale = guidance_scale
    config.diffusion.n_inference_steps = num_inference_steps
    config.model.width = width
    config.model.height = height
    
    # Generate image
    output_image = pipeline.generate(
        prompt=prompt,
        uncond_prompt=negative_prompt,
        config=config
    )
    
    # Convert numpy array to PIL Image
    image = Image.fromarray(output_image)
    
    return image, seed

examples = [
    "A ultra sharp photorealtici painting of a futuristic cityscape at night with neon lights and flying cars",
    "A serene mountain landscape at sunset with snow-capped peaks and a clear lake reflection",
    "A detailed portrait of a cyberpunk character with glowing neon implants and holographic tattoos",
]

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

with gr.Blocks(css=css) as demo:
    with gr.Column(elem_id="col-container"):
        gr.Markdown(" # Custom Diffusion Model Text-to-Image Generator")

        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):
            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=42,
            )

            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=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])
        
    gr.on(
        triggers=[run_button.click, prompt.submit],
        fn=infer,
        inputs=[
            prompt,
            negative_prompt,
            seed,
            randomize_seed,
            width,
            height,
            guidance_scale,
            num_inference_steps,
        ],
        outputs=[result, seed],
    )

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