File size: 6,942 Bytes
0d89806 00a9186 0d89806 9582ec0 4b257ce 2670857 9582ec0 463b37d 0d89806 6524a56 0d89806 6524a56 f788b7c 6524a56 dbbe505 0d89806 825b5cb 0d89806 1adb3ff 0d89806 43247b9 0d89806 9085e1a 0d89806 9085e1a 0d89806 8693079 6524a56 0d89806 6524a56 0d89806 |
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 |
import functools
import os
import shutil
import sys
import git
import gradio as gr
import numpy as np
import torch as torch
from PIL import Image
from gradio_imageslider import ImageSlider
import spaces
import fire
import argparse
import os
import logging
import numpy as np
import torch
from PIL import Image
from tqdm.auto import tqdm
import glob
import json
import cv2
import sys
sys.path.append("../")
from models.depth_normal_pipeline_clip import DepthNormalEstimationPipeline
from utils.seed_all import seed_all
import matplotlib.pyplot as plt
from utils.de_normalized import align_scale_shift
from utils.depth2normal import *
from diffusers import DiffusionPipeline, DDIMScheduler, AutoencoderKL
from models.unet_2d_condition import UNet2DConditionModel
from transformers import CLIPTextModel, CLIPTokenizer
from transformers import CLIPImageProcessor, CLIPVisionModelWithProjection
import torchvision.transforms.functional as TF
from torchvision.transforms import InterpolationMode
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
stable_diffusion_repo_path = "stabilityai/stable-diffusion-2-1-unclip"
vae = AutoencoderKL.from_pretrained(stable_diffusion_repo_path, subfolder='vae')
scheduler = DDIMScheduler.from_pretrained(stable_diffusion_repo_path, subfolder='scheduler')
sd_image_variations_diffusers_path = 'lambdalabs/sd-image-variations-diffusers'
image_encoder = CLIPVisionModelWithProjection.from_pretrained(sd_image_variations_diffusers_path, subfolder="image_encoder")
feature_extractor = CLIPImageProcessor.from_pretrained(sd_image_variations_diffusers_path, subfolder="feature_extractor")
unet = UNet2DConditionModel.from_pretrained('.', subfolder="unet")
pipe = DepthNormalEstimationPipeline(vae=vae,
image_encoder=image_encoder,
feature_extractor=feature_extractor,
unet=unet,
scheduler=scheduler)
try:
import xformers
pipe.enable_xformers_memory_efficient_attention()
except:
pass # run without xformers
pipe = pipe.to(device)
@spaces.GPU
def depth_normal(img,
denoising_steps,
ensemble_size,
processing_res,
seed,
domain):
seed = int(seed)
if seed >= 0:
torch.manual_seed(seed)
pipe_out = pipe(
img,
denoising_steps=denoising_steps,
ensemble_size=ensemble_size,
processing_res=processing_res,
batch_size=0,
domain=domain,
show_progress_bar=True,
)
depth_colored = pipe_out.depth_colored
normal_colored = pipe_out.normal_colored
return depth_colored, normal_colored
def run_demo():
custom_theme = gr.themes.Soft(primary_hue="blue").set(
button_secondary_background_fill="*neutral_100",
button_secondary_background_fill_hover="*neutral_200")
custom_css = '''#disp_image {
text-align: center; /* Horizontally center the content */
}'''
_TITLE = '''GeoWizard: Unleashing the Diffusion Priors for 3D Geometry Estimation from a Single Image'''
_DESCRIPTION = '''
<div>
Generate consistent depth and normal from single image. High quality and rich details. (PS: We find the demo running on ZeroGPU output slightly inferior results compared to A100 or 3060 with everything exactly the same.)
<a style="display:inline-block; margin-left: .5em" href='https://github.com/fuxiao0719/GeoWizard/'><img src='https://img.shields.io/github/stars/fuxiao0719/GeoWizard?style=social' /></a>
</div>
'''
_GPU_ID = 0
with gr.Blocks(title=_TITLE, theme=custom_theme, css=custom_css) as demo:
with gr.Row():
with gr.Column(scale=1):
gr.Markdown('# ' + _TITLE)
gr.Markdown(_DESCRIPTION)
with gr.Row(variant='panel'):
with gr.Column(scale=1):
input_image = gr.Image(type='pil', image_mode='RGBA', height=320, label='Input image')
example_folder = os.path.join(os.path.dirname(__file__), "./files")
example_fns = [os.path.join(example_folder, example) for example in os.listdir(example_folder)]
gr.Examples(
examples=example_fns,
inputs=[input_image],
cache_examples=False,
label='Examples (click one of the images below to start)',
examples_per_page=30
)
with gr.Column(scale=1):
with gr.Accordion('Advanced options', open=True):
with gr.Column():
domain = gr.Radio(
[
("Outdoor", "outdoor"),
("Indoor", "indoor"),
("Object", "object"),
],
label="Data Type (Must Select One matches your image)",
value="indoor",
)
denoising_steps = gr.Slider(
label="Number of denoising steps (More steps, better quality)",
minimum=1,
maximum=50,
step=1,
value=10,
)
ensemble_size = gr.Slider(
label="Ensemble size (More steps, higher accuracy)",
minimum=1,
maximum=15,
step=1,
value=3,
)
seed = gr.Number(0, label='Random Seed. Negative values for not specifying')
processing_res = gr.Radio(
[
("Native", 0),
("Recommended", 768),
],
label="Processing resolution",
value=768,
)
run_btn = gr.Button('Generate', variant='primary', interactive=True)
with gr.Row():
with gr.Column():
depth = gr.Image(interactive=False, show_label=False)
with gr.Column():
normal = gr.Image(interactive=False, show_label=False)
run_btn.click(fn=depth_normal,
inputs=[input_image, denoising_steps,
ensemble_size,
processing_res,
seed,
domain],
outputs=[depth, normal]
)
demo.queue().launch(share=True, max_threads=80)
if __name__ == '__main__':
fire.Fire(run_demo)
|