File size: 7,645 Bytes
4eab2b0
 
 
 
 
5b88ede
4eab2b0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
985620f
4eab2b0
 
e2b10be
4eab2b0
 
 
 
 
 
 
 
d62180d
4eab2b0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
985620f
4eab2b0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
985620f
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
from diffusers import StableDiffusionPipeline, StableDiffusionImg2ImgPipeline, DPMSolverMultistepScheduler
import gradio as gr
import torch
from PIL import Image

model_id = 'SG161222/Realistic_Vision_V6.0_B1_noVAE'
prefix = 'RAW photo,'
     
scheduler = DPMSolverMultistepScheduler.from_pretrained(model_id, subfolder="scheduler")

pipe = StableDiffusionPipeline.from_pretrained(
  model_id,
  torch_dtype=torch.float16 if torch.cuda.is_available() else torch.float32,
  scheduler=scheduler)

pipe_i2i = StableDiffusionImg2ImgPipeline.from_pretrained(
  model_id,
  torch_dtype=torch.float16 if torch.cuda.is_available() else torch.float32,
  scheduler=scheduler)

if torch.cuda.is_available():
  pipe = pipe.to("cuda")
  pipe_i2i = pipe_i2i.to("cuda")

def error_str(error, title="Error"):
    return f"""#### {title}
            {error}"""  if error else ""


def _parse_args(prompt, generator):
        parser = argparse.ArgumentParser(
            description="making it work."
        )
        parser.add_argument(
            "--no-half-vae", help="no half vae"
        )

        cmdline_args = parser.parse_args()
        command = cmdline_args.command
        conf_file = cmdline_args.conf_file
        conf_args = Arguments(conf_file)
        opt = conf_args.readArguments()

        if cmdline_args.config_overrides:
            for config_override in cmdline_args.config_overrides.split(";"):
                config_override = config_override.strip()
                if config_override:
                    var_val = config_override.split("=")
                    assert (
                        len(var_val) == 2
                    ), f"Config override '{var_val}' does not have the form 'VAR=val'"
                    conf_args.add_opt(opt, var_val[0], var_val[1], force_override=True)

def inference(prompt, guidance, steps, width=512, height=512, seed=0, img=None, strength=0.5, neg_prompt="", auto_prefix=False):
  generator = torch.Generator('cuda').manual_seed(seed) if seed != 0 else None
  prompt = f"{prefix} {prompt}" if auto_prefix else prompt

  try:
    if img is not None:
      return img_to_img(prompt, neg_prompt, img, strength, guidance, steps, width, height, generator), None
    else:
      return txt_to_img(prompt, neg_prompt, guidance, steps, width, height, generator), None
  except Exception as e:
    return None, error_str(e)
      
      

def txt_to_img(prompt, neg_prompt, guidance, steps, width, height, generator):

    result = pipe(
      prompt,
      negative_prompt = neg_prompt,
      num_inference_steps = int(steps),
      guidance_scale = guidance,
      width = width,
      height = height,
      generator = generator)
    
    return result.images[0]

def img_to_img(prompt, neg_prompt, img, strength, guidance, steps, width, height, generator):

    ratio = min(height / img.height, width / img.width)
    img = img.resize((int(img.width * ratio), int(img.height * ratio)), Image.LANCZOS)
    result = pipe_i2i(
        prompt,
        negative_prompt = neg_prompt,
        init_image = img,
        num_inference_steps = int(steps),
        strength = strength,
        guidance_scale = guidance,
        width = width,
        height = height,
        generator = generator)
        
    return result.images[0]

    def fake_safety_checker(images, **kwargs):
      return result.images[0], [False] * len(images)
    
    pipe.safety_checker = fake_safety_checker

css = """.main-div div{display:inline-flex;align-items:center;gap:.8rem;font-size:1.75rem}.main-div div h1{font-weight:900;margin-bottom:7px}.main-div p{margin-bottom:10px;font-size:94%}a{text-decoration:underline}.tabs{margin-top:0;margin-bottom:0}#gallery{min-height:20rem}
"""
with gr.Blocks(css=css) as demo:
    gr.HTML(
        f"""
            <div class="main-div">
              <div>
                <h1 style="color:orange;">📷 Realistic Vision V6.0_B1 📸</h1>
              </div>
              <p>
               Demo for <a href="https://huggingface.co/SG161222/Realistic_Vision_V6.0_B1_noVAE">Realistic Vision V6.0_B1</a>
               Stable Diffusion model by <a href="https://huggingface.co/SG161222/"><abbr title="SG1611222">Eugene</abbr></a>.  {"" if prefix else ""}  
              Running on {"<b>GPU 🔥</b>" if torch.cuda.is_available() else f"<b>CPU ⚡</b>"}. 
              </p>
           <p>Please use the prompt template below to get an example of the desired generation results:
           </p>

<b>Prompt</b>:
<details><code>
RAW photo, * subject *, (high detailed skin:1.2), 8k uhd, dslr, soft lighting, high quality, film grain, Fujifilm XT3
<br>
<br>
<q><i>
Example: RAW photo, a close up portrait photo of 26 y.o woman in wastelander clothes, long haircut, pale skin, slim body, background is city ruins, <br>
(high detailed skin:1.2), 8k uhd, dslr, soft lighting, high quality, film grain, Fujifilm XT3 
</i></q>
</code></details>

<br>
<b>Negative Prompt</b>:
<details><code>
(deformed iris, deformed pupils, semi-realistic, cgi, 3d, render, sketch, cartoon, drawing, anime:1.4), text, close up, cropped, out of frame, worst quality, <br>
low quality, jpeg artifacts, ugly, duplicate, morbid, mutilated, extra fingers, mutated hands, poorly drawn hands, poorly drawn face, mutation, deformed, blurry, <br>
dehydrated, bad anatomy, bad proportions, extra limbs, cloned face, disfigured, gross proportions, malformed limbs, missing arms, missing legs, extra arms, <br>
extra legs, fused fingers, too many fingers, long neck
</code></details>

<br>
Have Fun & Enjoy ⚡ 
<br>
             
            </div>
        """
    )
    with gr.Row():
        
        with gr.Column(scale=55):
          with gr.Group():
              with gr.Row():
                prompt = gr.Textbox(label="Prompt", show_label=False,max_lines=2,placeholder=f"{prefix} [your prompt]").style(container=False)
                generate = gr.Button(value="Generate").style(rounded=(False, True, True, False))

              image_out = gr.Image(height=512)
          error_output = gr.Markdown()

        with gr.Column(scale=45):
          with gr.Tab("Options"):
            with gr.Group():
              neg_prompt = gr.Textbox(label="Negative prompt", placeholder="What to exclude from the image")
              auto_prefix = gr.Checkbox(label="Prefix styling tokens automatically (RAW photo,)", value=prefix, visible=prefix)

              with gr.Row():
                guidance = gr.Slider(label="Guidance scale", value=7.5, maximum=15)
                steps = gr.Slider(label="Steps", value=25, minimum=2, maximum=75, step=1)

              with gr.Row():
                width = gr.Slider(label="Width", value=512, minimum=64, maximum=1024, step=8)
                height = gr.Slider(label="Height", value=512, minimum=64, maximum=1024, step=8)

              seed = gr.Slider(0, 2147483647, label='Seed (0 = random)', value=0, step=1)

          with gr.Tab("Image to image"):
              with gr.Group():
                image = gr.Image(label="Image", height=256, tool="editor", type="pil")
                strength = gr.Slider(label="Transformation strength", minimum=0, maximum=1, step=0.01, value=0.5)

    auto_prefix.change(lambda x: gr.update(placeholder=f"{prefix} [your prompt]" if x else "[Your prompt]"), inputs=auto_prefix, outputs=prompt, queue=False)

    inputs = [prompt, guidance, steps, width, height, seed, image, strength, neg_prompt, auto_prefix]
    outputs = [image_out, error_output]
    prompt.submit(inference, inputs=inputs, outputs=outputs)
    generate.click(inference, inputs=inputs, outputs=outputs)

    

demo.queue(concurrency_count=1)
demo.launch()