File size: 9,062 Bytes
6af7294
 
 
 
 
 
 
 
 
 
92b508a
6af7294
 
 
92b508a
 
 
6af7294
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
92b508a
6af7294
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
92b508a
6af7294
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
92b508a
6af7294
 
 
 
 
 
 
92b508a
6af7294
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
92b508a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
6af7294
 
92b508a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
6af7294
 
 
 
 
9812a51
6af7294
 
 
 
 
 
 
 
 
92b508a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
6af7294
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
import gradio as gr
import torch
from diffusers import StableDiffusionImg2ImgPipeline
from .utils.schedulers import SCHEDULER_LIST, get_scheduler_list
from .utils.prompt2prompt import generate
from .utils.device import get_device
from PIL import Image
from .download import get_share_js, get_community_loading_icon, CSS

IMG2IMG_MODEL_LIST = {
    "OpenJourney v4" : "prompthero/openjourney-v4",
    "StableDiffusion 1.5" : "runwayml/stable-diffusion-v1-5",
    "StableDiffusion 2.1" : "stabilityai/stable-diffusion-2-1",
    "DreamLike 1.0" : "dreamlike-art/dreamlike-diffusion-1.0",
    "DreamLike 2.0" : "dreamlike-art/dreamlike-photoreal-2.0",
    "DreamShaper" : "Lykon/DreamShaper",
    "NeverEnding-Dream" : "Lykon/NeverEnding-Dream"
}

class StableDiffusionImage2ImageGenerator:
    def __init__(self):
        self.pipe = None

    def load_model(self, model_path, scheduler):
        model_path = IMG2IMG_MODEL_LIST[model_path]
        if self.pipe is None:
            self.pipe = StableDiffusionImg2ImgPipeline.from_pretrained(
                model_path, safety_checker=None, torch_dtype=torch.float32
            )

        device = get_device()
        self.pipe = get_scheduler_list(pipe=self.pipe, scheduler=scheduler)

        self.pipe.to(device)
        self.pipe.enable_attention_slicing()

        return self.pipe

    def generate_image(
        self,
        image_path: str,
        model_path: str,
        prompt: str,
        negative_prompt: str,
        scheduler: str,
        guidance_scale: int,
        num_inference_step: int,
        seed_generator=0,
    ):
        pipe = self.load_model(
            model_path=model_path,
            scheduler=scheduler,
        )

        if seed_generator == 0:
            random_seed = torch.randint(0, 1000000, (1,))
            generator = torch.manual_seed(random_seed)
        else:
            generator = torch.manual_seed(seed_generator)

        image = Image.open(image_path)
        images = pipe(
            prompt,
            image=image,
            negative_prompt=negative_prompt,
            num_images_per_prompt=1,
            num_inference_steps=num_inference_step,
            guidance_scale=guidance_scale,
            generator=generator,
        ).images

        return images

    def app():
        demo = gr.Blocks(css=CSS)
        with demo:
            with gr.Row():
                with gr.Column():
                    image2image_image_file = gr.Image(
                        type="filepath", label="Upload",elem_id="image-upload-img2img"
                    ).style(height=260)

                    image2image_prompt = gr.Textbox(
                        lines=1,
                        placeholder="Prompt, keywords that describe the changes you want to apply to your image",
                        show_label=False,
                        elem_id="prompt-text-input-img2img",
                        value=''
                    )

                    image2image_negative_prompt = gr.Textbox(
                        lines=1,
                        placeholder="Negative Prompt, keywords that describe what you don't want in your image",
                        show_label=False,
                        elem_id = "negative-prompt-text-input-img2img",
                        value=''
                    )

                    # add button for generating a prompt from the prompt
                    image2image_generate_prompt_button = gr.Button(
                        label="Generate Prompt",
                        type="primary",
                        align="center",
                        value = "Generate Prompt"
                    )

                    # show a text box with the generated prompt
                    image2image_generated_prompt = gr.Textbox(
                        lines=1,
                        placeholder="Generated Prompt",
                        label = "Generated Prompt",
                        show_label=True,
                        info="Auto generated prompts for inspiration.",
                    )
                    image2image_model_path = gr.Dropdown(
                        choices=list(IMG2IMG_MODEL_LIST.keys()),
                        value=list(IMG2IMG_MODEL_LIST.keys())[0],
                        label="Imaget2Image Model Selection",
                        elem_id="model-dropdown-img2img",
                        info="Select the model you want to use for image2image generation."
                    )
                    image2image_scheduler = gr.Dropdown(
                        choices=SCHEDULER_LIST,
                        value=SCHEDULER_LIST[0],
                        label="Scheduler",
                        elem_id="scheduler-dropdown-img2img",
                        info="Scheduler list for models. Different schdulers result in different outputs."
                    )

                    image2image_seed_generator = gr.Slider(
                        label="Seed(0 for random)",
                        minimum=0,
                        maximum=1000000,
                        value=0,
                        elem_id="seed-slider-img2img",
                        info="Set the seed to a specific value to reproduce the results."
                    )


                    image2image_guidance_scale = gr.Slider(
                        minimum=0.1,
                        maximum=15,
                        step=0.1,
                        value=7.5,
                        label="Guidance Scale",
                        elem_id = "guidance-scale-slider-img2img",
                        info = "Guidance scale determines how much the prompt will affect the image. Higher the value, more the effect."
                        )

                    image2image_num_inference_step = gr.Slider(
                        minimum=1,
                        maximum=100,
                        step=1,
                        value=50,
                        label="Num Inference Step",
                        elem_id = "num-inference-step-slider-img2img",
                        info = "Number of inference step determines the quality of the image. Higher the number, better the quality."
                    )

                    image2image_predict_button = gr.Button(value="Generate image")

                with gr.Column():
                    output_image = gr.Gallery(
                        label="Generated images",
                        show_label=False,
                        elem_id="gallery-img2img",
                    ).style(grid=(1, 2))

                    with gr.Group(elem_id="container-advanced-btns"):
                        with gr.Group(elem_id="share-btn-container"):
                            community_icon_html, loading_icon_html = get_community_loading_icon("img2img")
                            community_icon = gr.HTML(community_icon_html)
                            loading_icon = gr.HTML(loading_icon_html)
                            share_button = gr.Button("Save artwork", elem_id="share-btn-img2img")

                    # Create an html for describing the models
                    gr.HTML(
                        """
                        <div id="model-description-img2img">
                            <h3>Image2Image Models</h3>
                            <p>Image2Image models are trained to generate images from a given prompt. The prompt should specify what to change in general for the provided image.</p>
                            <p>For example with a butterfly image, the prompt can be "blue butterfly".</p>
                            <p>Negative prompt can be used to specify what not to change in the image. For example, with the butterfly image, the negative prompt can be "dark blue, blurry image".</p>
                            <hr>
                            <p>Stable Diffusion 1.5 & 2.1: Default model for many tasks. </p>
                            <p>OpenJourney v4: Generates fantasy themed images similar to the Midjourney model. </p>
                            <p>Dreamlike Photoreal 1.0 & 2.0 is SD 1.5 that generates realistic images. </p>
                            </div>
                        """
                    )
            image2image_predict_button.click(
                fn=StableDiffusionImage2ImageGenerator().generate_image,
                inputs=[
                    image2image_image_file,
                    image2image_model_path,
                    image2image_prompt,
                    image2image_negative_prompt,
                    image2image_scheduler,
                    image2image_guidance_scale,
                    image2image_num_inference_step,
                    image2image_seed_generator,
                ],
                outputs=[output_image],
            )

            image2image_generate_prompt_button.click(
                fn=generate,
                inputs=[image2image_prompt],
                outputs=[image2image_generated_prompt],
            )


        return demo