import os
import torch
import sys
# import spaces #fixme
import random
import gradio as gr
import random
from configs.infer_config import get_parser
from huggingface_hub import hf_hub_download
traj_examples = [
['0 40', '0 0', '0 0'],
['0 -35', '0 0', '0 -0.1'],
['0 -3 -15 -20 -17 -5 0', '0 -2 -5 -10 -8 -5 0 2 5 3 0', '0 0'],
['0 3 10 20 17 10 0', '0 -2 -8 -6 0 2 5 3 0', '0 -0.02 -0.09 -0.16 -0.09 0'],
['0 30', '0 -1 -5 -4 0 1 5 4 0', '0 -0.2'],
]
# img_examples = [
# ['test/images/boy.png'],
# ['test/images/car.jpeg'],
# ['test/images/fruit.jpg'],
# ['test/images/room.png'],
# ['test/images/castle.png'],
# ]
img_examples = [
['test/images/boy.png',0,1],
['test/images/car.jpeg',5,1],
['test/images/fruit.jpg',5,1],
['test/images/room.png',10,1],
['test/images/castle.png',-4,1],
]
max_seed = 2 ** 31
def download_model():
REPO_ID = 'Drexubery/ViewCrafter_25'
filename_list = ['model.ckpt']
for filename in filename_list:
local_file = os.path.join('./checkpoints/', filename)
if not os.path.exists(local_file):
hf_hub_download(repo_id=REPO_ID, filename=filename, local_dir='./checkpoints/', force_download=True)
# download_model() #fixme
parser = get_parser() # infer_config.py
opts = parser.parse_args() # default device: 'cuda:0'
tmp = str(random.randint(10**(5-1), 10**5 - 1))
opts.save_dir = f'./{tmp}'
os.makedirs(opts.save_dir,exist_ok=True)
test_tensor = torch.Tensor([0]).cuda()
opts.device = str(test_tensor.device)
# opts.config = './configs/inference_pvd_1024_gradio.yaml' #fixme
opts.config = './configs/inference_pvd_1024_local.yaml' #fixme
# # install pytorch3d # fixme
# pyt_version_str=torch.__version__.split("+")[0].replace(".", "")
# version_str="".join([
# f"py3{sys.version_info.minor}_cu",
# torch.version.cuda.replace(".",""),
# f"_pyt{pyt_version_str}"
# ])
# print(version_str)
# os.system(f"{sys.executable} -m pip install --no-index --no-cache-dir pytorch3d -f https://dl.fbaipublicfiles.com/pytorch3d/packaging/wheels/{version_str}/download.html")
# os.system("mkdir -p checkpoints/ && wget https://download.europe.naverlabs.com/ComputerVision/DUSt3R/DUSt3R_ViTLarge_BaseDecoder_512_dpt.pth -P checkpoints/")
# print(f'>>> System info: {version_str}')
from viewcrafter import ViewCrafter
CAMERA_MOTION_MODE = ["Basic Camera Trajectory", "Custom Camera Trajectory"]
def proceed(mode):
if mode == "Basic Camera Trajectory":
return gr.update(visible=True), gr.update(visible=False)
else:
return gr.update(visible=False), gr.update(visible=True)
def viewcrafter_demo(opts):
css = """#input_img {max-width: 1024px !important} #output_vid {max-width: 1024px; max-height:576px} #random_button {max-width: 100px !important}"""
image2video = ViewCrafter(opts, gradio = True)
# image2video.run_traj_basic = spaces.GPU(image2video.run_traj_basic, duration=50) # fixme
# image2video.run_traj = spaces.GPU(image2video.run_traj, duration=50) # fixme
# image2video.run_gen = spaces.GPU(image2video.run_gen, duration=260) # fixme
with gr.Blocks(analytics_enabled=False, css=css) as viewcrafter_iface:
gr.Markdown("")
with gr.Row():
with gr.Column():
# # step 1: input an image
# gr.Markdown("---\n## Step 1: Input an Image, selet an elevation angle and a center_scale factor", show_label=False, visible=True)
# gr.Markdown("1. Estimate an elevation angle that represents the angle at which the image was taken; a value bigger than 0 indicates a top-down view, and it doesn't need to be precise.
2. The origin of the world coordinate system is by default defined at the point cloud corresponding to the center pixel of the input image. You can adjust the position of the origin by modifying center_scale; a value smaller than 1 brings the origin closer to you.
")
with gr.Row():
with gr.Column():
with gr.Row():
i2v_input_image = gr.Image(label="Input Image",elem_id="input_img")
with gr.Row():
i2v_elevation = gr.Slider(minimum=-45, maximum=45, step=1, elem_id="elevation", label="elevation", value=5)
i2v_center_scale = gr.Slider(minimum=0.1, maximum=2, step=0.1, elem_id="i2v_center_scale", label="center_scale", value=1)
# with gr.Column():
# step 2 - camera trajectory generation
# gr.Markdown("---\n## Step 2: Input camera trajectory", show_label=False, visible=True)
# gr.Markdown(f"\n - {CAMERA_MOTION_MODE[0]}: Select from 6 basic camera trajectory \
# \n - {CAMERA_MOTION_MODE[1]}: Customize complex camera trajectory yourself \
# \n - Click `Proceed` to go into next step",
# show_label=False, visible=True)
with gr.Column():
camera_mode = gr.Radio(choices=CAMERA_MOTION_MODE, value=CAMERA_MOTION_MODE[0], label="Camera trajectory mode", interactive=True, visible=True)
pro_btn = gr.Button("1.Select camera trajectory mode")
with gr.Column(visible=False) as ouput1:
gr.Markdown(" 2.Click on one basic trajectory
")
with gr.Row():
left = gr.Button(value = "Left")
right = gr.Button(value = "Right")
with gr.Row():
up = gr.Button(value = "Up")
down = gr.Button(value = "Down")
with gr.Row():
zoomin = gr.Button(value = "Zoom in")
zoomout = gr.Button(value = "Zoom out")
with gr.Column():
i2v_traj_video1 = gr.Video(label="Camera Trajectory",elem_id="traj_vid",autoplay=True,show_share_button=True)
with gr.Column(visible=False) as ouput2:
gr.Markdown(" Input a d_phi sequence, a d_theta sequence, and a d_r sequence, then click 'Generate custom trajectory'
(Tutorial) You can reduce the sampling steps for faster inference; try different random seed if the result is not satisfying.
")
with gr.Row():
with gr.Column():
i2v_output_video = gr.Video(label="Generated Video",elem_id="output_vid",autoplay=True,show_share_button=True)
with gr.Column():
with gr.Row():
i2v_steps = gr.Slider(minimum=1, maximum=50, step=1, elem_id="i2v_steps", label="Sampling steps", value=50)
i2v_seed = gr.Slider(label='Random seed', minimum=0, maximum=max_seed, step=1, value=0)
i2v_end_btn = gr.Button("3.Generate video")
# with gr.Tab(label='Result'):
gr.Examples(examples=img_examples,
inputs=[i2v_input_image,i2v_elevation, i2v_center_scale,],
# examples_per_page=6
)
pro_btn.click(inputs=[camera_mode],
outputs=[ouput1,ouput2],
fn = proceed
)
# generate trajectory buttn
i2v_traj_btn2.click(inputs=[i2v_input_image, i2v_elevation, i2v_center_scale, i2v_d_phi2, i2v_d_theta2, i2v_d_r2],
outputs=[i2v_traj_video2],
fn = image2video.run_traj
)
left.click(inputs=[i2v_input_image, i2v_elevation, i2v_center_scale,left],
outputs=[i2v_traj_video1],
fn = image2video.run_traj_basic
)
right.click(inputs=[i2v_input_image, i2v_elevation, i2v_center_scale,right],
outputs=[i2v_traj_video1],
fn = image2video.run_traj_basic
)
up.click(inputs=[i2v_input_image, i2v_elevation, i2v_center_scale,up],
outputs=[i2v_traj_video1],
fn = image2video.run_traj_basic
)
down.click(inputs=[i2v_input_image, i2v_elevation, i2v_center_scale,down],
outputs=[i2v_traj_video1],
fn = image2video.run_traj_basic
)
zoomin.click(inputs=[i2v_input_image, i2v_elevation, i2v_center_scale,zoomin],
outputs=[i2v_traj_video1],
fn = image2video.run_traj_basic
)
zoomout.click(inputs=[i2v_input_image, i2v_elevation, i2v_center_scale,zoomout],
outputs=[i2v_traj_video1],
fn = image2video.run_traj_basic
)
i2v_end_btn.click(inputs=[i2v_steps, i2v_seed],
outputs=[i2v_output_video],
fn = image2video.run_gen
)
return viewcrafter_iface
viewcrafter_iface = viewcrafter_demo(opts)
viewcrafter_iface.queue(max_size=10)
# viewcrafter_iface.launch() #fixme
viewcrafter_iface.launch(server_name='11.220.92.96', server_port=80, max_threads=10,debug=True)