File size: 5,681 Bytes
c1b02ca db8b7ba c1b02ca d1d5355 c1b02ca d1d5355 c1b02ca |
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 |
from contextlib import nullcontext
import gradio as gr
from torch import autocast
from removebg import RemoveBg
import os
import torch
import PIL
from PIL import Image
from diffusers import StableDiffusionPipeline
from transformers import CLIPFeatureExtractor, CLIPTextModel, CLIPTokenizer
def image_grid(imgs, rows, cols):
assert len(imgs) == rows*cols
w, h = imgs[0].size
grid = Image.new('RGB', size=(cols*w, rows*h))
grid_w, grid_h = grid.size
for i, img in enumerate(imgs):
grid.paste(img, box=(i%cols*w, i//cols*h))
return grid
pretrained_model_name_or_path = "vmanot/valiant-effort-one" #@param {type:"string"}
tokenizer = CLIPTokenizer.from_pretrained(
pretrained_model_name_or_path,
subfolder="tokenizer",
)
text_encoder = CLIPTextModel.from_pretrained(
pretrained_model_name_or_path, subfolder="text_encoder", torch_dtype=torch.float16
)
device = "cuda" if torch.cuda.is_available() else "cpu"
context = autocast if device == "cuda" else nullcontext
dtype = torch.float16 if device == "cuda" else torch.float32
pipe = StableDiffusionPipeline.from_pretrained(
pretrained_model_name_or_path,
revision="main",
torch_dtype=torch.float16,
text_encoder=text_encoder,
tokenizer=tokenizer,
).to("cuda")
disable_safety = True
if disable_safety:
def null_safety(images, **kwargs):
return images, False
pipe.safety_checker = null_safety
num_samples = 2 #@param {type:"number"}
num_rows = 2 #@param {type:"number"}
def infer(prompt, n_samples, steps, scale):
i = 0
with context("cuda"):
images = pipe(n_samples*[prompt], guidance_scale=scale, num_inference_steps=steps).images
return images
css = """
a {
color: inherit;
text-decoration: underline;
}
.gradio-container {
font-family: 'IBM Plex Sans', sans-serif;
}
.gr-button {
color: white;
border-color: #9d66e5;
background: #9d66e5;
}
input[type='range'] {
accent-color: green;
}
.dark input[type='range'] {
accent-color: green;
}
.container {
max-width: 500px;
margin-left: 200px;
padding-top: 1.5rem;
}
#gallery {
min-height: 22rem;
margin-bottom: 15px;
margin-left: auto;
margin-right: auto;
border-bottom-right-radius: .5rem !important;
border-bottom-left-radius: .5rem !important;
}
#gallery>div>.h-full {
min-height: 20rem;
}
.details:hover {
text-decoration: underline;
}
.gr-button {
white-space: nowrap;
}
.gr-button:focus {
border-color: rgb(147 197 253 / var(--tw-border-opacity));
outline: none;
box-shadow: var(--tw-ring-offset-shadow), var(--tw-ring-shadow), var(--tw-shadow, 0 0 #0000);
--tw-border-opacity: 1;
--tw-ring-offset-shadow: var(--tw-ring-inset) 0 0 0 var(--tw-ring-offset-width) var(--tw-ring-offset-color);
--tw-ring-shadow: var(--tw-ring-inset) 0 0 0 calc(3px var(--tw-ring-offset-width)) var(--tw-ring-color);
--tw-ring-color: rgb(191 219 254 / var(--tw-ring-opacity));
--tw-ring-opacity: .5;
}
#advanced-options {
margin-bottom: 20px;
}
.dark { filter: invert(1); }
.dark {
border-color: #303030;
}
.dark {
background: #0b0f19;
}
.acknowledgments h4{
margin: 1.25em 0 .25em 0;
font-weight: bold;
font-size: 115%;
}
"""
block = gr.Blocks(css=css)
examples = [
[
'Yoda',
2,
7.5,
],
[
'Abraham Lincoln',
2,
7.5,
],
[
'George Washington',
2,
7,
],
]
with block:
gr.HTML(
"""
<div style="text-align: center; max-width: 650px; margin: 0 auto;">
</div>
"""
)
with gr.Group():
with gr.Box():
with gr.Row().style(mobile_collapse=False, equal_height=True):
text = gr.Textbox(
label="Enter your prompt",
show_label=False,
max_lines=1,
placeholder="Enter your prompt",
).style(
border=(True, False, True, True),
rounded=(True, False, False, True),
container=False,
)
btn = gr.Button("Generate image").style(
margin=False,
rounded=(False, True, True, False),
)
gallery = gr.Gallery(
label="Generated images", show_label=False, elem_id="gallery"
).style(grid=[2], height="auto")
with gr.Row(elem_id="advanced-options"):
samples = gr.Slider(label="Images", minimum=1, maximum=4, value=2, step=1)
steps = gr.Slider(label="Steps", minimum=5, maximum=50, value=25, step=5)
scale = gr.Slider(
label="Guidance Scale", minimum=0, maximum=50, value=7.5, step=0.1
)
ex = gr.Examples(examples=examples, fn=infer, inputs=[text, samples, scale], outputs=gallery, cache_examples=False)
ex.dataset.headers = [""]
text.submit(infer, inputs=[text, samples, steps, scale], outputs=gallery)
btn.click(infer, inputs=[text, samples, steps, scale], outputs=gallery)
block.launch(debug=True) |