File size: 6,212 Bytes
8219169
 
 
 
 
 
 
 
 
 
 
5d1594c
8219169
 
 
 
 
 
 
 
 
 
f0a547a
 
8219169
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
5d1594c
8219169
 
 
5d1594c
 
8219169
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
5d1594c
 
 
 
8219169
5d1594c
 
8219169
 
 
 
 
 
 
 
 
 
 
 
5d1594c
 
8219169
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
a7890ea
8219169
 
 
a7890ea
8219169
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
import spaces
import gradio as gr
import time
import torch

from PIL import Image
from segment_utils import(
    segment_image_withmask,
    restore_result,
)
from diffusers import (
    StableDiffusionXLInpaintPipeline,
    DiffusionPipeline,
    T2IAdapter,
    MultiAdapter,
)

from controlnet_aux import (
    LineartDetector,
    CannyDetector,
)

BASE_MODEL = "stabilityai/sdxl-turbo"

DEVICE = "cuda" if torch.cuda.is_available() else "cpu"

DEFAULT_EDIT_PROMPT = "a woman, blue hair, high detailed"
DEFAULT_NEGATIVE_PROMPT = "worst quality, normal quality, low quality, low res, blurry, text, watermark, logo, banner, extra digits, cropped, jpeg artifacts, signature, username, error, sketch ,duplicate, ugly, monochrome, horror, geometry, mutation, disgusting, poorly drawn face, bad face, fused face, ugly face, worst face, asymmetrical, unrealistic skin texture, bad proportions, out of frame, poorly drawn hands, cloned face, double face"

DEFAULT_CATEGORY = "hair"

lineart_detector = LineartDetector.from_pretrained("lllyasviel/Annotators")
lineart_detector = lineart_detector.to(DEVICE)

canndy_detector = CannyDetector()

adapters = MultiAdapter(
    [
        T2IAdapter.from_pretrained(
            "TencentARC/t2i-adapter-lineart-sdxl-1.0",
            torch_dtype=torch.float16,
            varient="fp16",
        ),
        T2IAdapter.from_pretrained(
            "TencentARC/t2i-adapter-canny-sdxl-1.0",
            torch_dtype=torch.float16,
            varient="fp16",
        ),
    ]
)
adapters = adapters.to(torch.float16)

basepipeline = StableDiffusionXLInpaintPipeline.from_pretrained(
    BASE_MODEL,
    torch_dtype=torch.float16,
    use_safetensors=True,
    # adapter=adapters,
    # custom_pipeline="./pipelines/pipeline_sdxl_adapter_inpaint_custom.py",
)

basepipeline = basepipeline.to(DEVICE)

basepipeline.enable_model_cpu_offload()

@spaces.GPU(duration=30)
def image_to_image(
    input_image: Image,
    mask_image: Image,
    edit_prompt: str,
    seed: int,
    num_steps: int,
    guidance_scale: float,
    generate_size: int,
    lineart_scale: float = 1.0,
    canny_scale: float = 0.5,
):
    run_task_time = 0
    time_cost_str = ''
    run_task_time, time_cost_str = get_time_cost(run_task_time, time_cost_str)
    # lineart_image = lineart_detector(input_image, int(generate_size*0.375), generate_size)
    # run_task_time, time_cost_str = get_time_cost(run_task_time, time_cost_str)
    # canny_image = canndy_detector(input_image, int(generate_size*0.375), generate_size)
    # run_task_time, time_cost_str = get_time_cost(run_task_time, time_cost_str)

    # cond_image = [lineart_image, canny_image]
    # cond_scale = [lineart_scale, canny_scale]

    generator = torch.Generator(device=DEVICE).manual_seed(seed)
    generated_image = basepipeline(
        generator=generator,
        prompt=edit_prompt,
        negative_prompt=DEFAULT_NEGATIVE_PROMPT,
        image=input_image,
        mask_image=mask_image,
        height=generate_size,
        width=generate_size,
        guidance_scale=guidance_scale,
        num_inference_steps=num_steps,
        # adapter_image=cond_image,
        # adapter_conditioning_scale=cond_scale,
    ).images[0]
    
    run_task_time, time_cost_str = get_time_cost(run_task_time, time_cost_str)

    return generated_image, time_cost_str

def get_time_cost(run_task_time, time_cost_str):
    now_time = int(time.time()*1000)
    if run_task_time == 0:
        time_cost_str = 'start'
    else:
        if time_cost_str != '': 
            time_cost_str += f'-->'
        time_cost_str += f'{now_time - run_task_time}'
    run_task_time = now_time
    return run_task_time, time_cost_str

def create_demo() -> gr.Blocks:
    with gr.Blocks() as demo:
        croper = gr.State()
        with gr.Row():
            with gr.Column():
                edit_prompt = gr.Textbox(lines=1, label="Edit Prompt", value=DEFAULT_EDIT_PROMPT)
                generate_size = gr.Number(label="Generate Size", value=512)
                seed = gr.Number(label="Seed", value=8)
                category = gr.Textbox(label="Category", value=DEFAULT_CATEGORY, visible=False)
            with gr.Column():
                num_steps = gr.Slider(minimum=1, maximum=100, value=15, step=1, label="Num Steps")
                guidance_scale = gr.Slider(minimum=0, maximum=30, value=5, step=0.5, label="Guidance Scale")
                mask_expansion = gr.Number(label="Mask Expansion", value=50, visible=True)
            with gr.Column():
                mask_dilation = gr.Slider(minimum=0, maximum=10, value=2, step=1, label="Mask Dilation")
                lineart_scale = gr.Slider(minimum=0, maximum=2, value=1, step=0.1, label="Lineart Scale")
                canny_scale = gr.Slider(minimum=0, maximum=2, value=0.5, step=0.1, label="Canny Scale")
                g_btn = gr.Button("Edit Image")
                
        with gr.Row():
            with gr.Column():
                input_image = gr.Image(label="Input Image", type="pil")
            with gr.Column():
                restored_image = gr.Image(label="Restored Image", type="pil", interactive=False)
            with gr.Column():
                origin_area_image = gr.Image(label="Origin Area Image", type="pil", interactive=False)
                generated_image = gr.Image(label="Generated Image", type="pil", interactive=False)
                generated_cost = gr.Textbox(label="Time cost by step (ms):", visible=True, interactive=False)
                mask_image = gr.Image(label="Mask Image", type="pil", interactive=False)
        
        g_btn.click(
            fn=segment_image_withmask,
            inputs=[input_image, category, generate_size, mask_expansion, mask_dilation],
            outputs=[origin_area_image, mask_image, croper],
        ).success(
            fn=image_to_image,
            inputs=[origin_area_image, mask_image, edit_prompt,seed, num_steps, guidance_scale, generate_size, lineart_scale, canny_scale],
            outputs=[generated_image, generated_cost],
        ).success(
            fn=restore_result,
            inputs=[croper, category, generated_image],
            outputs=[restored_image],
        )

    return demo