File size: 5,780 Bytes
1e78ace 5ba6fd4 1e78ace 5ba6fd4 1e78ace |
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 |
from diffusers import AutoPipelineForImage2Image, AutoPipelineForText2Image
import torch
import os
try:
import intel_extension_for_pytorch as ipex
except:
pass
from PIL import Image
import numpy as np
import gradio as gr
import psutil
import time
import math
SAFETY_CHECKER = os.environ.get("SAFETY_CHECKER", None)
# check if MPS is available OSX only M1/M2/M3 chips
mps_available = hasattr(torch.backends, "mps") and torch.backends.mps.is_available()
xpu_available = hasattr(torch, "xpu") and torch.xpu.is_available()
device = torch.device(
"cuda" if torch.cuda.is_available() else "xpu" if xpu_available else "cpu"
)
torch_device = device
torch_dtype = torch.float16
if mps_available:
device = torch.device("mps")
torch_device = "cpu"
torch_dtype = torch.float32
if SAFETY_CHECKER == "True":
i2i_pipe = AutoPipelineForImage2Image.from_pretrained(
"stabilityai/sdxl-turbo",
torch_dtype=torch_dtype,
variant="fp16" if torch_dtype == torch.float16 else "fp32",
)
t2i_pipe = AutoPipelineForText2Image.from_pretrained(
"stabilityai/sdxl-turbo",
torch_dtype=torch_dtype,
variant="fp16" if torch_dtype == torch.float16 else "fp32",
)
else:
i2i_pipe = AutoPipelineForImage2Image.from_pretrained(
"stabilityai/sdxl-turbo",
safety_checker=None,
torch_dtype=torch_dtype,
variant="fp16" if torch_dtype == torch.float16 else "fp32",
)
t2i_pipe = AutoPipelineForText2Image.from_pretrained(
"stabilityai/sdxl-turbo",
safety_checker=None,
torch_dtype=torch_dtype,
variant="fp16" if torch_dtype == torch.float16 else "fp32",
)
t2i_pipe.to(device=torch_device, dtype=torch_dtype).to(device)
t2i_pipe.set_progress_bar_config(disable=True)
i2i_pipe.to(device=torch_device, dtype=torch_dtype).to(device)
i2i_pipe.set_progress_bar_config(disable=True)
def resize_crop(image, size=512):
image = image.convert("RGB")
w, h = image.size
image = image.resize((size, int(size * (h / w))), Image.BICUBIC)
return image
async def predict(init_image, prompt, strength, steps, seed=1231231):
if init_image is not None:
init_image = resize_crop(init_image)
generator = torch.manual_seed(seed)
last_time = time.time()
if int(steps * strength) < 1:
steps = math.ceil(1 / max(0.10, strength))
results = i2i_pipe(
prompt=prompt,
image=init_image,
generator=generator,
num_inference_steps=steps,
guidance_scale=0.0,
strength=strength,
width=512,
height=512,
output_type="pil",
)
else:
generator = torch.manual_seed(seed)
last_time = time.time()
results = t2i_pipe(
prompt=prompt,
generator=generator,
num_inference_steps=steps,
guidance_scale=0.0,
width=512,
height=512,
output_type="pil",
)
print(f"Pipe took {time.time() - last_time} seconds")
nsfw_content_detected = (
results.nsfw_content_detected[0]
if "nsfw_content_detected" in results
else False
)
if nsfw_content_detected:
gr.Warning("NSFW content detected.")
return Image.new("RGB", (512, 512))
return results.images[0]
css = """
#container{
margin: 0 auto;
max-width: 80rem;
}
#intro{
max-width: 100%;
text-align: center;
margin: 0 auto;
}
"""
with gr.Blocks(css=css) as demo:
init_image_state = gr.State()
with gr.Column(elem_id="container"):
gr.Markdown(
"""# Real Time Image Generation
""",
elem_id="intro",
)
with gr.Row():
prompt = gr.Textbox(
placeholder="Insert your prompt here:",
scale=5,
container=False,
)
generate_bt = gr.Button("Generate", scale=1)
with gr.Row():
with gr.Column():
image_input = gr.Image(
sources=["upload", "webcam", "clipboard"],
label="Webcam",
type="pil",
)
with gr.Column():
image = gr.Image(type="filepath")
with gr.Accordion("Advanced options", open=False):
strength = gr.Slider(
label="Strength",
value=0.7,
minimum=0.0,
maximum=1.0,
step=0.001,
)
steps = gr.Slider(
label="Steps", value=2, minimum=1, maximum=10, step=1
)
seed = gr.Slider(
randomize=True,
minimum=0,
maximum=12013012031030,
label="Seed",
step=1,
)
inputs = [image_input, prompt, strength, steps, seed]
generate_bt.click(fn=predict, inputs=inputs, outputs=image, show_progress=False)
prompt.change(fn=predict, inputs=inputs, outputs=image, show_progress=False)
steps.change(fn=predict, inputs=inputs, outputs=image, show_progress=False)
seed.change(fn=predict, inputs=inputs, outputs=image, show_progress=False)
strength.change(fn=predict, inputs=inputs, outputs=image, show_progress=False)
image_input.change(
fn=lambda x: x,
inputs=image_input,
outputs=init_image_state,
show_progress=False,
queue=False,
)
demo.queue()
demo.launch()
|