forked from prehistoric-systems/comixify
Personal Fork
End-to-end solution that transforms input video into a comics in just a few seconds
* Add ComixGAN #1 * Add minor fixes * Reduce batch size * Fix concatenate bug * Fix GPU memory not released problem #2 * Build client * Fix style_transfer_mode bug * Improve timings * Add minor fix with GPU name * Fix tf session problem * Compile frontend * Change parameters * Fix occasional yt Error |
||
|---|---|---|
| api | ||
| CartoonGAN | ||
| comic_layout | ||
| ComixGAN | ||
| frontend | ||
| keyframes | ||
| keyframes_rl | ||
| neural_image_assessment | ||
| popularity | ||
| settings | ||
| style_transfer | ||
| tmp | ||
| .gitignore | ||
| db.env | ||
| docker-compose-prod.yml | ||
| docker-compose.yml | ||
| dockerfile | ||
| entrypoint.sh | ||
| Makefile.config | ||
| manage.py | ||
| nginx.conf | ||
| package-lock.json | ||
| package.json | ||
| prepare_setup.sh | ||
| README.md | ||
| requirements.txt | ||
| utils.py | ||
comixify
#TODO:
- Prepare readme
- Download videos directly from YouTube
- Fix model loading to memory
- Replace ffmpeg with some keyframes extractor
- Prepare own ComixGAN
- Prepare some more intelligent method for comic layout
- Prepare some method for voice extraction