Spaces:
Running
Running
File size: 4,119 Bytes
bd8a222 5408021 bd8a222 ff5b4f4 bd8a222 5408021 bd8a222 acd8555 bd8a222 5408021 bd8a222 98a5d61 b9f1f79 bd8a222 acd8555 bd8a222 5408021 ff5b4f4 5408021 bd8a222 ff5b4f4 bd8a222 ff5b4f4 bd8a222 ff5b4f4 bd8a222 ff5b4f4 98a5d61 ff5b4f4 bd8a222 ff5b4f4 98a5d61 ff5b4f4 bd8a222 ff5b4f4 bd8a222 5408021 bd8a222 5408021 bd8a222 ff5b4f4 bd8a222 acd8555 |
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 |
import gradio as gr
import numpy as np
import random
from diffusers import DiffusionPipeline
import torch
device = "cuda" if torch.cuda.is_available() else "cpu"
MAX_SEED = np.iinfo(np.int32).max
MAX_IMAGE_SIZE = 1024
def load_pipeline(model_id):
if torch.cuda.is_available():
torch_dtype = torch.float16
else:
torch_dtype = torch.float32
pipe = DiffusionPipeline.from_pretrained(model_id, torch_dtype=torch_dtype)
return pipe.to(device)
# Initialize with default model
pipe = load_pipeline("CompVis/stable-diffusion-v1-4")
available_models = [
"CompVis/stable-diffusion-v1-4",
"runwayml/stable-diffusion-v1-5",
"stabilityai/stable-diffusion-2-1",
"prompthero/openjourney",
"stabilityai/sdxl-base-0.9"
]
def infer(
model_id,
prompt,
negative_prompt,
seed,
randomize_seed,
width,
height,
guidance_scale,
num_inference_steps,
progress=None,
):
global pipe
if model_id:
pipe = load_pipeline(model_id)
if randomize_seed:
seed = random.randint(0, MAX_SEED)
# Ensure width and height are divisible by 8
width = max(256, (width // 8) * 8)
height = max(256, (height // 8) * 8)
# Set default value if num_inference_steps is None
if num_inference_steps is None:
num_inference_steps = 20
generator = torch.Generator().manual_seed(seed)
image = pipe(
prompt=prompt,
negative_prompt=negative_prompt,
guidance_scale=guidance_scale,
num_inference_steps=int(num_inference_steps), # Ensure it's an integer
width=width,
height=height,
generator=generator,
).images[0]
return image, seed
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: 640px;
}
"""
with gr.Blocks(css=css) as demo:
with gr.Column(elem_id="col-container"):
gr.Markdown(" # Text-to-Image Gradio Template with Model Selection")
model_id = gr.Dropdown(
label="Model Selection",
choices=available_models,
value="CompVis/stable-diffusion-v1-4",
)
prompt = gr.Text(
label="Prompt",
show_label=True,
max_lines=1,
placeholder="Enter your prompt",
)
negative_prompt = gr.Text(
label="Negative prompt",
max_lines=1,
placeholder="Enter a negative prompt",
)
seed = gr.Slider(
label="Seed",
minimum=0,
maximum=MAX_SEED,
step=1,
value=42,
)
guidance_scale = gr.Slider(
label="Guidance scale",
minimum=0.0,
maximum=20.0,
step=0.1,
value=7.0,
)
num_inference_steps = gr.Slider(
label="Number of inference steps",
minimum=1,
maximum=100,
step=1,
value=20,
)
with gr.Row():
width = gr.Slider(
label="Width",
minimum=256,
maximum=MAX_IMAGE_SIZE,
step=8,
value=512,
)
height = gr.Slider(
label="Height",
minimum=256,
maximum=MAX_IMAGE_SIZE,
step=8,
value=512,
)
run_button = gr.Button("Run", scale=0, variant="primary")
result = gr.Image(label="Result", show_label=False)
gr.Examples(examples=examples, inputs=[prompt])
gr.on(
triggers=[run_button.click, prompt.submit],
fn=infer,
inputs=[
model_id,
prompt,
negative_prompt,
seed,
guidance_scale,
num_inference_steps,
width,
height,
],
outputs=[result, seed],
)
if __name__ == "__main__":
demo.launch()
|