Spaces:
Runtime error
Runtime error
File size: 5,216 Bytes
2823934 d006030 c167a04 2823934 d006030 c7b9640 d006030 c2633fb a2a71ed c167a04 4ac8a6d c167a04 c2633fb 4ac8a6d c2633fb 2823934 c167a04 2823934 4ac8a6d 2823934 c2633fb 2823934 c2633fb 58a0d29 2823934 58a0d29 2823934 58a0d29 2823934 58a0d29 2823934 58a0d29 2823934 58a0d29 2823934 4ac8a6d 2823934 4ac8a6d 2823934 58a0d29 2823934 58a0d29 2823934 58a0d29 |
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 |
import gradio as gr
import numpy as np
import random
from diffusers import DiffusionPipeline
import torch
from huggingface_hub import login
import os
import bitsandbytes as bnb
import onnx
import onnxruntime as ort
from onnxruntime.quantization import quantize_dynamic, QuantType
device = "cuda" if torch.cuda.is_available() else "cpu"
# Set your Hugging Face token
HUGGINGFACE_TOKEN = os.getenv("HUGGINGFACE_TOKEN")
login(token=HUGGINGFACE_TOKEN)
# Path to your model repository and safetensors weights
base_model_repo = "stabilityai/stable-diffusion-3-medium-diffusers"
lora_weights_path = "./pytorch_lora_weights.safetensors"
# Load the base model with 8-bit precision
pipeline = DiffusionPipeline.from_pretrained(
base_model_repo,
torch_dtype=torch.float16 if torch.cuda.is_available() else torch.float32,
use_auth_token=HUGGINGFACE_TOKEN
)
bnb.optim.load_int8_model(pipeline.model, device=device)
pipeline.load_lora_weights(lora_weights_path)
pipeline.enable_sequential_cpu_offload() # Efficient memory usage
pipeline.enable_xformers_memory_efficient_attention() # Enable xformers memory efficient attention
pipeline = pipeline.to(device)
# Export to ONNX
onnx_model_path = "model.onnx"
pipeline.model.eval()
dummy_input = torch.randn(1, 3, 512, 512, device=device)
torch.onnx.export(pipeline.model, dummy_input, onnx_model_path, export_params=True, opset_version=11, do_constant_folding=True, input_names=['input'], output_names=['output'])
# Quantize ONNX model to 8-bit
quantized_model_path = "model_quantized.onnx"
quantize_dynamic(onnx_model_path, quantized_model_path, weight_type=QuantType.QUInt8)
# Load quantized ONNX model
session = ort.InferenceSession(quantized_model_path)
MAX_SEED = np.iinfo(np.int32).max
MAX_IMAGE_SIZE = 768 # Reduce max image size to fit within memory constraints
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(device=device).manual_seed(seed)
image = pipeline(
prompt=prompt,
negative_prompt=negative_prompt,
guidance_scale=guidance_scale,
num_inference_steps=num_inference_steps,
width=width,
height=height,
generator=generator
).images[0]
return image
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.Textbox(
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.Textbox(
label="Negative prompt",
max_lines=1,
placeholder="Enter a negative prompt",
visible=True,
)
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=7.5,
)
num_inference_steps = gr.Slider(
label="Number of inference steps",
minimum=1,
maximum=50,
step=1,
value=30,
)
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()
|