File size: 4,181 Bytes
7ee57a2
 
 
b313358
7ee57a2
 
 
b5597fd
7ee57a2
ab043dd
7ee57a2
ab043dd
 
c61c1dc
50a2ac1
c61c1dc
7ee57a2
 
b313358
 
 
7ee57a2
ab043dd
 
 
 
 
 
 
 
 
 
 
 
7ee57a2
 
ab043dd
b313358
ab043dd
7ee57a2
 
b313358
7ee57a2
 
 
 
ab043dd
7ee57a2
ab043dd
 
7ee57a2
 
b313358
 
7ee57a2
 
 
 
 
ab043dd
7ee57a2
 
 
ab043dd
b313358
7ee57a2
 
50a2ac1
7ee57a2
 
ab043dd
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
7ee57a2
 
ab043dd
 
 
 
 
 
 
 
 
 
 
 
 
 
 
b313358
ab043dd
 
 
 
 
 
 
 
 
 
 
 
 
 
7ee57a2
 
b313358
ab043dd
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
b313358
 
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
import gradio as gr
import numpy as np
import random
from diffusers import StableDiffusionPipeline
import torch

device = "cuda" if torch.cuda.is_available() else "cpu"
model_repo_id = "hakurei/waifu-diffusion"

torch_dtype = torch.float16 if device == "cuda" else torch.float32

pipe = StableDiffusionPipeline.from_pretrained(
    model_repo_id,
    torch_dtype=torch_dtype
)

pipe = pipe.to(device)

if device == "cuda":
    pipe.enable_xformers_memory_efficient_attention()

MAX_SEED = np.iinfo(np.int32).max
MAX_IMAGE_SIZE = 512  # stable diffusion ideal size

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(device).manual_seed(seed)

    image = pipe(
        prompt=prompt,
        negative_prompt=negative_prompt if negative_prompt else None,
        guidance_scale=guidance_scale,
        num_inference_steps=num_inference_steps,
        width=width,
        height=height,
        generator=generator,
    ).images[0]

    return image, seed

examples = [
    "A fantasy portrait of a warrior woman, detailed and dramatic lighting",
    "A cute anime character with blue hair and big eyes"
]

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

power_device = "GPU" if device == "cuda" else "CPU"

with gr.Blocks(css=css) as demo:
    with gr.Column(elem_id="col-container"):
        gr.Markdown(f"# Waifu Diffusion Text-to-Image Generator\nRunning on **{power_device}**")

        with gr.Row():
            prompt = gr.Textbox(
                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.Textbox(
                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=0,
            )
            randomize_seed = gr.Checkbox(label="Randomize seed", value=True)

            with gr.Row():
                width = gr.Slider(
                    label="Width",
                    minimum=256,
                    maximum=MAX_IMAGE_SIZE,
                    step=64,
                    value=512,
                )
                height = gr.Slider(
                    label="Height",
                    minimum=256,
                    maximum=MAX_IMAGE_SIZE,
                    step=64,
                    value=512,
                )

            with gr.Row():
                guidance_scale = gr.Slider(
                    label="Guidance scale",
                    minimum=0.0,
                    maximum=15.0,
                    step=0.1,
                    value=7.5,
                )
                num_inference_steps = gr.Slider(
                    label="Number of inference steps",
                    minimum=1,
                    maximum=50,
                    step=1,
                    value=20,
                )

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

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

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

demo.queue().launch()