File size: 8,835 Bytes
be9cf62
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
190548d
 
 
2a8a3fd
d234e1e
 
 
 
2a8a3fd
d234e1e
 
2a8a3fd
be9cf62
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
898989f
 
be9cf62
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
from diffusers import AutoencoderKL, UNet2DConditionModel, StableDiffusionPipeline, StableDiffusionImg2ImgPipeline, DPMSolverMultistepScheduler
import gradio as gr
import torch
from PIL import Image
import datetime
import time
import psutil

start_time = time.time()

class Model:
    def __init__(self, name, path="", prefix=""):
        self.name = name
        self.path = path
        self.prefix = prefix
        self.pipe_t2i = None
        self.pipe_i2i = None

models = [
   Model("Cool Japanese Diffusion", "alfredplpl/cool-japan-diffusion-for-learning-2-0", "Cool Japanese Diffusion"),
]

     
scheduler = DPMSolverMultistepScheduler(
    beta_start=0.00085,
    beta_end=0.012,
    beta_schedule="scaled_linear",
    num_train_timesteps=1000,
    trained_betas=None,
    predict_epsilon=True,
    thresholding=False,
    algorithm_type="dpmsolver++",
    solver_type="midpoint",
    lower_order_final=True,
)

custom_model = None

last_mode = "txt2img"
current_model = models[0]
current_model_path = current_model.path

print(f"{datetime.datetime.now()} Downloading vae...")
vae = AutoencoderKL.from_pretrained(current_model.path, subfolder="vae")
for model in models:
    try:
        print(f"{datetime.datetime.now()} Downloading {model.name} model...")
        unet = UNet2DConditionModel.from_pretrained(model.path, subfolder="unet")
        model.pipe_t2i = StableDiffusionPipeline.from_pretrained(model.path, unet=unet, vae=vae, scheduler=scheduler)
        model.pipe_i2i = StableDiffusionImg2ImgPipeline.from_pretrained(model.path, unet=unet, vae=vae, scheduler=scheduler)
    except Exception as e:
        print(f"{datetime.datetime.now()} Failed to load model " + model.name + ": " + str(e))
        models.remove(model)
    pipe = models[0].pipe_t2i
  
if torch.cuda.is_available():
  pipe = pipe.to("cuda")

device = "Running on GPU πŸ”₯" if torch.cuda.is_available() else "Running on CPU πŸ₯Ά"

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

def custom_model_changed(path):
  models[0].path = path
  global current_model
  current_model = models[0]

def on_model_change(model_name):
  
  prefix = "γƒ—γƒ­γƒ³γƒ—γƒˆγ‚’ε…₯εŠ›" + next((m.prefix for m in models if m.name == model_name), None) + "\" is prefixed automatically" if model_name != models[0].name else "Don't forget to use the custom model prefix in the prompt!"

  return gr.update(visible = model_name == models[0].name), gr.update(placeholder=prefix)

def inference(model_name, prompt, guidance, steps, width=512, height=512, seed=0, img=None, strength=0.5, neg_prompt=""):

  print(psutil.virtual_memory()) 
  global current_model
  for model in models:
    if model.name == model_name:
      current_model = model
      model_path = current_model.path

  generator = torch.Generator('cuda').manual_seed(seed) if seed != 0 else None

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

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

    print(f"{datetime.datetime.now()} txt_to_img, model: {current_model.name}")

    global last_mode
    global pipe
    global current_model_path
    if model_path != current_model_path or last_mode != "txt2img":
        current_model_path = model_path
        pipe = pipe.to("cpu")
        pipe = current_model.pipe_t2i

        if torch.cuda.is_available():
          pipe = pipe.to("cuda")
        last_mode = "txt2img"

    prompt = current_model.prefix + prompt  
    result = pipe(
      prompt,
      negative_prompt = neg_prompt,
      # num_images_per_prompt=n_images,
      num_inference_steps = int(steps),
      guidance_scale = guidance,
      width = width,
      height = height,
      generator = generator)
    
    return replace_nsfw_images(result)

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

    print(f"{datetime.datetime.now()} img_to_img, model: {model_path}")

    global last_mode
    global pipe
    global current_model_path
    if model_path != current_model_path or last_mode != "img2img":
        current_model_path = model_path

        if current_model == custom_model:
          pipe = StableDiffusionImg2ImgPipeline.from_pretrained(current_model_path, scheduler=scheduler, safety_checker=lambda images, clip_input: (images, False))
        else:
          pipe = pipe.to("cpu")
          pipe = current_model.pipe_i2i
        
        if torch.cuda.is_available():
          pipe = pipe.to("cuda")
        last_mode = "img2img"

    prompt = current_model.prefix + prompt
    ratio = min(height / img.height, width / img.width)
    img = img.resize((int(img.width * ratio), int(img.height * ratio)), Image.LANCZOS)
    result = pipe(
        prompt,
        negative_prompt = neg_prompt,
        # num_images_per_prompt=n_images,
        init_image = img,
        num_inference_steps = int(steps),
        strength = strength,
        guidance_scale = guidance,
        width = width,
        height = height,
        generator = generator)
        
    return replace_nsfw_images(result)

def replace_nsfw_images(results):
      
    for i in range(len(results.images)):
      if results.nsfw_content_detected[i]:
        results.images[i] = Image.open("nsfw.png")
    return results.images[0]

css = """.finetuned-diffusion-div div{display:inline-flex;align-items:center;gap:.8rem;font-size:1.75rem}.finetuned-diffusion-div div h1{font-weight:900;margin-bottom:7px}.finetuned-diffusion-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:
    with gr.Row():
        
        with gr.Column(scale=55):
          with gr.Group():
              model_name = gr.Dropdown(label="Model", choices=[m.name for m in models], value=current_model.name)
              with gr.Box(visible=False) as custom_model_group:
                custom_model_path = gr.Textbox(label="Custom model path", placeholder="Path to model, e.g. nitrosocke/Arcane-Diffusion", interactive=True)
                gr.HTML("<div><font size='2'>Custom models have to be downloaded first, so give it some time.</font></div>")
              
              with gr.Row():
                prompt = gr.Textbox(label="Prompt", show_label=False, max_lines=2,placeholder="Enter prompt. Style applied automatically").style(container=False)
                generate = gr.Button(value="Generate").style(rounded=(False, True, True, False))


              image_out = gr.Image(height=512)
              # gallery = gr.Gallery(
              #     label="Generated images", show_label=False, elem_id="gallery"
              # ).style(grid=[1], height="auto")
          error_output = gr.Markdown()

        with gr.Column(scale=45):
          with gr.Tab("Options"):
            with gr.Group():
              neg_prompt = gr.Textbox(label="Negative prompt", placeholder="γƒγ‚¬γƒ†γ‚£γƒ–γƒ—γƒ­γƒ³γƒ—γƒˆγ‚’ε…₯εŠ›")

              # n_images = gr.Slider(label="Images", value=1, minimum=1, maximum=4, step=1)

              with gr.Row():
                guidance = gr.Slider(label="CFG 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="strength", minimum=0, maximum=1, step=0.01, value=0.5)

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

    ex = gr.Examples([
       [models[0].name, "iron man", 7.5, 50],
      
    ], inputs=[model_name, prompt, guidance, steps, seed], outputs=outputs, fn=inference, cache_examples=False)

    gr.HTML("""
    <div style="border-top: 1px solid #303030;">
      <br>
      <p>Model by TopdeckingLands.</p>
    </div>
    """)

print(f"Space built in {time.time() - start_time:.2f} seconds")

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