File size: 4,832 Bytes
07bbe45 587df09 4abbbf6 73b72bb 07bbe45 73b72bb 07bbe45 4abbbf6 07bbe45 7ccb3f3 |
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 |
import gradio as gr
import numpy as np
import random
import generation_sdxl
import functools
from diffusers import DiffusionPipeline, UNet2DConditionModel
import torch
device = "cuda" if torch.cuda.is_available() else "cpu"
if torch.cuda.is_available():
torch.cuda.max_memory_allocated(device=device)
pipe = DiffusionPipeline.from_pretrained("stabilityai/sdxl-turbo", torch_dtype=torch.float16, variant="fp16", use_safetensors=True)
pipe.enable_xformers_memory_efficient_attention()
pipe = pipe.to(device)
else:
pipe = DiffusionPipeline.from_pretrained("stabilityai/sdxl-turbo", use_safetensors=True)
pipe = pipe.to(device)
unet = UNet2DConditionModel.from_pretrained("dbaranchuk/sdxl-cfg-distill-unet")
pipe.unet = unet
MAX_SEED = np.iinfo(np.int32).max
MAX_IMAGE_SIZE = 1024
def infer(prompt, negative_prompt, seed, randomize_seed, width, height, guidance_scale, num_inference_steps):
if randomize_seed:
seed = random.randint(0, MAX_SEED)
generator = torch.Generator().manual_seed(seed)
prompt = ['Long-exposure night photography of a starry sky over a mountain range, with light trails.']
text_encoders = [pipe.text_encoder, pipe.text_encoder_2]
tokenizers = [pipe.tokenizer, pipe.tokenizer_2]
compute_embeddings_fn = functools.partial(
generation_sdxl.compute_embeddings,
proportion_empty_prompts=0,
text_encoders=text_encoders,
tokenizers=tokenizers,
)
images = generation_sdxl.sample_deterministic(
pipe,
prompt,
num_inference_steps=4,
generator=generator,
guidance_scale=7.0,
is_sdxl=True,
timesteps=[249, 499, 699, 999],
use_dynamic_guidance=False,
tau1=1.0,
tau2=1.0,
compute_embeddings_fn=compute_embeddings_fn
)[0]
return images
examples = [
"Astronaut in a jungle, cold color palette, muted colors, detailed, 8k",
"An astronaut riding a green horse",
"A delicious ceviche cheesecake slice",
]
css="""
#col-container {
margin: 0 auto;
max-width: 520px;
}
"""
if torch.cuda.is_available():
power_device = "GPU"
else:
power_device = "CPU"
with gr.Blocks(css=css) as demo:
with gr.Column(elem_id="col-container"):
gr.Markdown(f"""
# Text-to-Image Gradio Template
Currently running on {power_device}.
""")
with gr.Row():
prompt = gr.Text(
label="Prompt",
show_label=False,
max_lines=1,
placeholder="Enter your prompt",
container=False,
)
run_button = gr.Button("Run", scale=0)
result = gr.Image(label="Result", show_label=False)
with gr.Accordion("Advanced Settings", open=False):
negative_prompt = gr.Text(
label="Negative prompt",
max_lines=1,
placeholder="Enter a negative prompt",
visible=False,
)
seed = gr.Slider(
label="Seed",
minimum=0,
maximum=MAX_SEED,
step=1,
value=0,
)
randomize_seed = gr.Checkbox(label="Randomize seed", value=True)
with gr.Row():
width = gr.Slider(
label="Width",
minimum=256,
maximum=MAX_IMAGE_SIZE,
step=32,
value=512,
)
height = gr.Slider(
label="Height",
minimum=256,
maximum=MAX_IMAGE_SIZE,
step=32,
value=512,
)
with gr.Row():
guidance_scale = gr.Slider(
label="Guidance scale",
minimum=0.0,
maximum=10.0,
step=0.1,
value=0.0,
)
num_inference_steps = gr.Slider(
label="Number of inference steps",
minimum=1,
maximum=12,
step=1,
value=2,
)
gr.Examples(
examples = examples,
inputs = [prompt]
)
run_button.click(
fn = infer,
inputs = [prompt, negative_prompt, seed, randomize_seed, width, height, guidance_scale, num_inference_steps],
outputs = [result]
)
demo.queue().launch(share=True)
|