File size: 3,363 Bytes
05ca552
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
506eb50
05ca552
 
 
 
 
 
506eb50
05ca552
 
 
 
 
b297a29
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
e3e69da
50d06b5
b297a29
 
 
 
 
e3e69da
 
 
 
b297a29
05ca552
bdca464
 
 
e3e69da
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
bdca464
 
 
 
 
 
 
e3e69da
 
bdca464
 
 
e3e69da
bdca464
50d06b5
bdca464
 
 
 
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
import gradio as gr
from PIL import Image
from io import BytesIO
import torch
import os
from diffusers import DiffusionPipeline, DDIMScheduler
MY_SECRET_TOKEN=os.environ.get('HF_TOKEN_SD')
has_cuda = torch.cuda.is_available()
device = torch.device('cpu' if not has_cuda else 'cuda')

pipe = DiffusionPipeline.from_pretrained(
    "CompVis/stable-diffusion-v1-4",
        safety_checker=None,
    use_auth_token=MY_SECRET_TOKEN,
    custom_pipeline="imagic_stable_diffusion",
    scheduler = DDIMScheduler(beta_start=0.00085, beta_end=0.012, beta_schedule="scaled_linear", clip_sample=False, set_alpha_to_one=False)
).to(device)

#generator = torch.Generator("cuda").manual_seed(0)

def infer(prompt, init_image):
    res = pipe.train(
        prompt,
        init_image,
        guidance_scale=7.5,
        num_inference_steps=50)
    
    res = pipe(alpha=1)

    return res.images[0]

title = """
    <div style="text-align: center; max-width: 650px; margin: 0 auto;">
        <div
        style="
            display: inline-flex;
            align-items: center;
            gap: 0.8rem;
            font-size: 1.75rem;
        "
        >
        <h1 style="font-weight: 900; margin-bottom: 7px;">
            Imagic Stable Diffusion • Community Pipeline
        </h1>
        </div>
        <p style="margin-bottom: 10px; font-size: 94%">
        Text-Based Real Image Editing with Diffusion Models
        <br />This pipeline aims to implement <a href="" target="_blank">this paper</a> to Stable Diffusion, allowing for real-world image editing.
        <br /><img src="https://user-images.githubusercontent.com/788417/196388568-4ee45edd-e990-452c-899f-c25af32939be.png" />
        </p>
    </div>
"""

article = """
    <div class="footer">
        <p><a href="https://github.com/huggingface/diffusers/tree/main/examples/community#imagic-stable-diffusion" target="_blank">Community pipeline</a> baked by <a href="https://github.com/apolinario" style="text-decoration: underline;" target="_blank">@apolinario</a> - Gradio Demo by 🤗 Sylvain Filoni
        </p>
    </div>
"""

css = '''
    #col-container {max-width: 700px; margin-left: auto; margin-right: auto;}
    a {text-decoration-line: underline; font-weight: 600;}
    .footer {
            margin-bottom: 45px;
            margin-top: 35px;
            text-align: center;
            border-bottom: 1px solid #e5e5e5;
        }
        .footer>p {
            font-size: .8rem;
            display: inline-block;
            padding: 0 10px;
            transform: translateY(10px);
            background: white;
        }
        .dark .footer {
            border-color: #303030;
        }
        .dark .footer>p {
            background: #0b0f19;
        }
'''


with gr.Blocks(css=css) as block:
    with gr.Column(elem_id="col-container"):
        gr.HTML(title)

        prompt_input = gr.Textbox(label="Prompt", placeholder="Describe the image with what you want to change about the subject")
        image_init = gr.Image(source="upload", type="filepath", label="Input Image")
        
        submit_btn = gr.Button("Submit")
        
        image_output = gr.Image(label="Result")
        
        gr.HTML(article)

    submit_btn.click(fn=infer, inputs=[prompt_input,image_init], outputs=[image_output])
    
block.queue(max_size=32,concurrency_count=20).launch(show_api=False)