app.py

import gradio as gr

UPSAMPLER_THEME = gr.themes.Soft(
    primary_hue=gr.themes.colors.indigo,
    secondary_hue=gr.themes.colors.purple,
    neutral_hue=gr.themes.colors.slate,
).set(
    button_primary_background_fill="linear-gradient(135deg, #6366f1, #a855f7)",
    button_primary_background_fill_hover="linear-gradient(135deg, #5457e5, #9333ea)",
    button_primary_text_color="#ffffff",
    button_primary_border_color="*primary_500",
)

UPSAMPLER_CSS = """
footer{display:none !important}
.gradio-container{max-width:1000px !important; margin:0 auto !important}
h1,h2,h3{font-family:system-ui,-apple-system,'Segoe UI',sans-serif}
"""
import cv2
import matplotlib
import numpy as np
import os
from PIL import Image
import spaces
import torch
import tempfile
from gradio_imageslider import ImageSlider
from huggingface_hub import hf_hub_download

from depth_anything_v2.dpt import DepthAnythingV2

css = """
#img-display-container {
    max-height: 100vh;
}
#img-display-input {
    max-height: 80vh;
}
#img-display-output {
    max-height: 80vh;
}
#download {
    height: 62px;
}
"""
DEVICE = 'cuda' if torch.cuda.is_available() else 'cpu'
model_configs = {
    'vits': {'encoder': 'vits', 'features': 64, 'out_channels': [48, 96, 192, 384]},
    'vitb': {'encoder': 'vitb', 'features': 128, 'out_channels': [96, 192, 384, 768]},
    'vitl': {'encoder': 'vitl', 'features': 256, 'out_channels': [256, 512, 1024, 1024]},
    'vitg': {'encoder': 'vitg', 'features': 384, 'out_channels': [1536, 1536, 1536, 1536]}
}
encoder2name = {
    'vits': 'Small',
    'vitb': 'Base',
    'vitl': 'Large',
    'vitg': 'Giant', # we are undergoing company review procedures to release our giant model checkpoint
}
encoder = 'vitl'
model_name = encoder2name[encoder]
model = DepthAnythingV2(**model_configs[encoder])
filepath = hf_hub_download(repo_id=f"depth-anything/Depth-Anything-V2-{model_name}", filename=f"depth_anything_v2_{encoder}.pth", repo_type="model")
state_dict = torch.load(filepath, map_location="cpu")
model.load_state_dict(state_dict)
model = model.to(DEVICE).eval()

header = """<div style="max-width:760px;margin:0 auto;text-align:center;padding:20px 16px 2px;font-family:system-ui,-apple-system,'Segoe UI',sans-serif">
  <h1 style="font-size:1.7rem;font-weight:700;margin:0 0 6px;letter-spacing:-.02em">Depth Anything V2</h1>
  <p style="font-size:1rem;line-height:1.5;opacity:.6;margin:0">Turn any photo into a detailed depth map with Depth Anything V2.</p>
</div>"""

footer = """<div style="max-width:640px;margin:2rem auto .4rem;text-align:center;font-family:system-ui,-apple-system,'Segoe UI',sans-serif">
  <p style="font-size:.85rem;line-height:1.6;opacity:.5;margin:0 0 10px">Depth Anything V2 is a state-of-the-art monocular depth estimation model that turns a single photo into a detailed depth map online, no stereo pair or LiDAR required. The grayscale depth maps it produces are used for 3D parallax effects, depth-of-field and bokeh simulation, relighting, ControlNet conditioning, and robotics prototyping.</p>
  <p style="font-size:.85rem;line-height:1.6;opacity:.65;margin:0">Maintained by <a href="https://upsampler.com" target="_blank" rel="noopener" style="color:#8b7cf6;font-weight:600;text-decoration:none">Upsampler</a>. Check out the <a href="https://upsampler.com/free-depth-map-generator-no-signup" target="_blank" rel="noopener" style="color:#8b7cf6;font-weight:600;text-decoration:none">free depth map generator</a>, no sign-up required.</p>
</div>"""

# Single forward pass of the depth model: ~1-3s on ZeroGPU. Request a tight
# duration so anonymous visitors with small quotas aren't rejected up front
# (ZeroGPU checks the requested duration against remaining quota) and the
# task gets higher queue priority.
@spaces.GPU(duration=12)
def predict_depth(image):
    return model.infer_image(image)

with gr.Blocks(theme=UPSAMPLER_THEME, css=UPSAMPLER_CSS + "\n" + css) as demo:
    gr.HTML(header)

    with gr.Row():
        with gr.Column():
            input_image = gr.Image(label="Input Image", type='numpy', elem_id='img-display-input')
            submit = gr.Button(value="Compute Depth", variant="primary")
        with gr.Column():
            depth_image_slider = ImageSlider(label="Depth Map with Slider View", elem_id='img-display-output', position=0.5)
            gray_depth_file = gr.File(label="Grayscale depth map", elem_id="download",)
            raw_file = gr.File(label="16-bit raw output (can be considered as disparity)", elem_id="download",)

    cmap = matplotlib.colormaps.get_cmap('Spectral_r')

    def on_submit(image):
        original_image = image.copy()

        h, w = image.shape[:2]

        depth = predict_depth(image[:, :, ::-1])

        raw_depth = Image.fromarray(depth.astype('uint16'))
        tmp_raw_depth = tempfile.NamedTemporaryFile(suffix='.png', delete=False)
        raw_depth.save(tmp_raw_depth.name)

        depth = (depth - depth.min()) / (depth.max() - depth.min()) * 255.0
        depth = depth.astype(np.uint8)
        colored_depth = (cmap(depth)[:, :, :3] * 255).astype(np.uint8)

        gray_depth = Image.fromarray(depth)
        tmp_gray_depth = tempfile.NamedTemporaryFile(suffix='.png', delete=False)
        gray_depth.save(tmp_gray_depth.name)

        return [(original_image, colored_depth), tmp_gray_depth.name, tmp_raw_depth.name]

    submit.click(on_submit, inputs=[input_image], outputs=[depth_image_slider, gray_depth_file, raw_file])

    gr.HTML(footer)


if __name__ == '__main__':
    demo.queue().launch(ssr_mode=False, show_error=True)