File size: 10,976 Bytes
880de81 02abdab 880de81 02abdab 880de81 02abdab 4c7362f 1167d4f 0be0bad 4a445e6 880de81 946878e 880de81 946878e 880de81 946878e 880de81 946878e 880de81 946878e 880de81 946878e e50a69b 946878e 880de81 946878e 880de81 946878e 880de81 946878e 880de81 36e4433 880de81 02abdab 6c8ddcc 880de81 6c8ddcc 880de81 84d7c6f 880de81 36e4433 880de81 6c8ddcc 880de81 6c8ddcc 880de81 84d7c6f 75813eb c43a83e 880de81 c43a83e 946878e c43a83e 946878e c43a83e 946878e c43a83e 946878e c43a83e 946878e c43a83e 946878e 880de81 946878e e50a69b 880de81 9c021ca 946878e 9c021ca 880de81 946878e 9c021ca 946878e 9c021ca 880de81 167ab4b 880de81 946878e 880de81 c43a83e 880de81 4c7362f 1167d4f 880de81 4c7362f |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 |
import os
import json
import gradio as gr
import tempfile
from PIL import Image, ImageDraw, ImageFont
import cv2
from typing import Tuple, Optional
import torch
from pathlib import Path
import time
import torch
import spaces
import os
from video_highlight_detector import (
load_model,
BatchedVideoHighlightDetector,
get_video_duration_seconds
)
def load_examples(json_path: str) -> dict:
with open(json_path, 'r') as f:
return json.load(f)
def format_duration(seconds: int) -> str:
hours = seconds // 3600
minutes = (seconds % 3600) // 60
secs = seconds % 60
if hours > 0:
return f"{hours}:{minutes:02d}:{secs:02d}"
return f"{minutes}:{secs:02d}"
# @spaces.GPU
# def process_video(
# video_path: str,
# progress = gr.Progress()
# ) -> Tuple[str, str, str, str]:
# try:
# # duration = get_video_duration_seconds(video_path)
# # if duration > 1200: # 20 minutes
# # return None, None, None, "Video must be shorter than 20 minutes"
# progress(0.1, desc="Loading model...")
# model, processor = load_model()
# detector = BatchedVideoHighlightDetector(model, processor, batch_size=8)
# progress(0.2, desc="Analyzing video content...")
# video_description = detector.analyze_video_content(video_path)
# progress(0.3, desc="Determining highlight types...")
# highlight_types = detector.determine_highlights(video_description)
# progress(0.4, desc="Detecting and extracting highlights...")
# with tempfile.NamedTemporaryFile(suffix='.mp4', delete=False) as tmp_file:
# output_path = tmp_file.name
# detector.create_highlight_video(video_path, output_path)
# # progress(0.9, desc="Adding watermark...")
# # output_path = temp_output.replace('.mp4', '_watermark.mp4')
# # add_watermark(temp_output, output_path)
# os.unlink(output_path)
# progress(1.0, desc="Complete!")
# video_description = video_description[:500] + "..." if len(video_description) > 500 else video_description
# highlight_types = highlight_types[:500] + "..." if len(highlight_types) > 500 else highlight_types
# return output_path, video_description, highlight_types, None
# except Exception as e:
# return None, None, None, f"Error processing video: {str(e)}"
def create_ui(examples_path: str):
examples_data = load_examples(examples_path)
with gr.Blocks() as app:
gr.Markdown("# Video Highlight Generator")
gr.Markdown("Upload a video and get an automated highlight reel!")
with gr.Row():
gr.Markdown("## Example Results")
with gr.Row():
for example in examples_data["examples"]:
with gr.Column():
gr.Video(
value=example["original"]["url"],
label=f"Original ({format_duration(example['original']['duration_seconds'])})",
interactive=False
)
gr.Markdown(f"### {example['title']}")
with gr.Column():
gr.Video(
value=example["highlights"]["url"],
label=f"Highlights ({format_duration(example['highlights']['duration_seconds'])})",
interactive=False
)
with gr.Accordion("Model chain of thought details", open=False):
gr.Markdown(f"#Summary: {example['analysis']['video_description']}")
gr.Markdown(f"#Highlights to search for: {example['analysis']['highlight_types']}")
# Main interface section
gr.Markdown("## Try It Yourself!")
with gr.Row():
# Left column: Upload and Process
with gr.Column(scale=1):
input_video = gr.Video(
label="Upload your video (max 20 minutes)",
interactive=True
)
process_btn = gr.Button("Process Video", variant="primary")
# Right column: Progress and Analysis
with gr.Column(scale=1):
# Output video (initially hidden)
output_video = gr.Video(
label="Highlight Video",
visible=False,
interactive=False,
downloadable=True
)
status = gr.Markdown()
with gr.Accordion("Model chain of thought details", open=True, visible=False) as analysis_accordion:
video_description = gr.Markdown("", elem_id="video_desc")
highlight_types = gr.Markdown("", elem_id="highlight_types")
@spaces.GPU
def on_process(video, progress=gr.Progress()):
if not video:
return {
status: "Please upload a video",
video_description: "",
highlight_types: "",
output_video: gr.update(visible=False)
}
try:
duration = get_video_duration_seconds(video)
if duration > 1200: # 20 minutes
return {
status: "Video must be shorter than 20 minutes",
video_description: "",
highlight_types: "",
output_video: gr.update(visible=False)
}
progress(0.1, desc="Loading model...")
status.value = "Loading model..."
model, processor = load_model()
detector = BatchedVideoHighlightDetector(model, processor, batch_size=8)
progress(0.2, desc="Analyzing video content...")
status.value = "Analyzing video content..."
video_desc = detector.analyze_video_content(video)
# Update description in real-time
video_description.value = f"#Summary: {video_desc[:500] + '...' if len(video_desc) > 500 else video_desc}"
progress(0.3, desc="Determining highlight types...")
status.value = "Determining highlight types..."
highlights = detector.determine_highlights(video_desc)
# Update highlights in real-time
highlight_types.value = f"#Highlights to search for: {highlights[:500] + '...' if len(highlights) > 500 else highlights}"
progress(0.4, desc="Detecting and extracting highlights...")
status.value = "Detecting and extracting highlights..."
with tempfile.NamedTemporaryFile(suffix='.mp4', delete=False) as tmp_file:
temp_output = tmp_file.name
detector.create_highlight_video(video, temp_output)
# progress(0.9, desc="Adding watermark...")
# status.value = "Adding watermark..."
# output_path = temp_output.replace('.mp4', '_watermark.mp4')
# add_watermark(temp_output, output_path)
# os.unlink(temp_output)
progress(1.0, desc="Complete!")
return {
status: "Processing complete!",
video_description: video_description.value,
highlight_types: highlight_types.value,
output_video: gr.update(value=temp_output, visible=True)
}
except Exception as e:
return {
status: f"Error processing video: {str(e)}",
video_description: "",
highlight_types: "",
output_video: gr.update(visible=False)
}
process_btn.click(
on_process,
inputs=[input_video],
outputs=[status, video_description, highlight_types, output_video]
)
return app
# gr.Markdown("## Try It Yourself!")
# with gr.Row():
# input_video = gr.Video(
# label="Upload your video (max 20 minutes)",
# interactive=True
# )
# gr.Progress()
# process_btn = gr.Button("Process Video", variant="primary")
# status = gr.Markdown(visible=True)
# with gr.Row() as results_row:
# with gr.Column():
# video_description = gr.Markdown(visible=False)
# with gr.Column():
# highlight_types = gr.Markdown(visible=False)
# with gr.Row() as output_row:
# output_video = gr.Video(label="Highlight Video", visible=False)
# download_btn = gr.Button("Download Highlights", visible=False)
# def on_process(video, progress=gr.Progress()):
# if not video:
# return {
# status: "Please upload a video",
# video_description: gr.update(visible=False),
# highlight_types: gr.update(visible=False),
# output_video: gr.update(visible=False),
# download_btn: gr.update(visible=False)
# }
# status.value = "Processing video..."
# output_path, desc, highlights, err = process_video(video, progress=progress)
# if err:
# return {
# status: f"Error: {err}",
# video_description: gr.update(visible=False),
# highlight_types: gr.update(visible=False),
# output_video: gr.update(visible=False),
# download_btn: gr.update(visible=False)
# }
# return {
# status: "Processing complete!",
# video_description: gr.update(value=desc, visible=True),
# highlight_types: gr.update(value=highlights, visible=True),
# output_video: gr.update(value=output_path, visible=True),
# download_btn: gr.update(visible=True)
# }
# process_btn.click(
# on_process,
# inputs=[input_video],
# outputs=[status, video_description, highlight_types, output_video, download_btn]
# )
# download_btn.click(
# lambda x: x,
# inputs=[output_video],
# outputs=[output_video]
# )
# return app
if __name__ == "__main__":
# Initialize CUDA
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
zero = torch.Tensor([0]).to(device)
app = create_ui("video_spec.json")
app.launch() |