File size: 4,404 Bytes
1de2e39
 
 
 
 
 
 
 
 
7bc7b2d
1de2e39
 
 
 
 
 
7bc7b2d
 
1de2e39
 
 
 
 
 
 
7bc7b2d
1de2e39
 
 
35df3e8
1de2e39
 
 
 
 
 
35df3e8
 
1de2e39
7bc7b2d
 
 
 
1de2e39
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
fc67d5b
1de2e39
35df3e8
 
 
 
 
 
 
 
7bc7b2d
 
 
 
 
 
 
35df3e8
 
fd520a1
35df3e8
 
cddf6ac
f8991bb
35df3e8
7bc7b2d
1de2e39
 
 
 
 
 
35df3e8
1de2e39
35df3e8
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1de2e39
35df3e8
 
 
1de2e39
 
 
 
 
 
 
cddf6ac
1de2e39
 
 
 
 
 
 
cddf6ac
1de2e39
 
 
 
 
 
 
 
7bc7b2d
1de2e39
 
 
 
 
 
 
 
 
 
 
 
 
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
import gradio as gr
import numpy as np
import random

# import spaces #[uncomment to use ZeroGPU]
from diffusers import DiffusionPipeline
import torch

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)
# pipe = pipe.to(device)

MAX_SEED = np.iinfo(np.int32).max
MAX_IMAGE_SIZE = 1024


# @spaces.GPU #[uncomment to use ZeroGPU]
def infer(
    model_id,
    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)

    print(f"Model id: {model_id}")
    pipe = DiffusionPipeline.from_pretrained(model_id, torch_dtype=torch_dtype)
    pipe = pipe.to(device)

    generator = torch.Generator().manual_seed(seed)

    image = pipe(
        prompt=prompt,
        negative_prompt=negative_prompt,
        guidance_scale=guidance_scale,
        num_inference_steps=num_inference_steps,
        width=width,
        height=height,
        generator=generator,
    ).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;
}
"""

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

        model_id = gr.Text(
            label="Model ID",
            show_label=False,
            max_lines=1,
            placeholder="Enter model id",
            container=False,
            value="CompVis/stable-diffusion-v1-4",
        )
        prompt = gr.Text(
            label="Prompt",
            show_label=False,
            max_lines=1,
            placeholder="Enter your prompt",
            container=False,
        )
        negative_prompt = gr.Text(
            label="Negative prompt",
            show_label=False,
            max_lines=1,
            placeholder="Enter a negative prompt",
            visible=True,
            container=False,
        )

        with gr.Row():
            seed = gr.Slider(
                label="Seed",
                minimum=0,
                maximum=MAX_SEED,
                step=1,
                value=42,
            )
            guidance_scale = gr.Slider(
                label="Guidance scale",
                minimum=0.0,
                maximum=10.0,
                step=0.1,
                value=7.0,  # Replace with defaults that work for your model
            )


        with gr.Row():
            num_inference_steps = gr.Slider(
                label="Number of inference steps",
                minimum=1,
                maximum=50,
                step=1,
                value=20,  # Replace with defaults that work for your model
            )
            run_button = gr.Button("Run", scale=0, variant="primary")

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

        with gr.Accordion("Advanced Settings", open=False):

            with gr.Row():
                width = gr.Slider(
                    label="Width",
                    minimum=256,
                    maximum=MAX_IMAGE_SIZE,
                    step=32,
                    value=512,  # Replace with defaults that work for your model
                )

                height = gr.Slider(
                    label="Height",
                    minimum=256,
                    maximum=MAX_IMAGE_SIZE,
                    step=32,
                    value=512,  # Replace with defaults that work for your model
                )


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

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