audio-to-image

A Stable Diffusion based pipeline to generate an image from a 10 second audio clip

Name		Name	Last commit message	Last commit date
Latest commit History 56 Commits
data		data
.gitignore		.gitignore
Architecture.jpg		Architecture.jpg
README.md		README.md
audio_dataset.py		audio_dataset.py
cnn_embedding_processor.py		cnn_embedding_processor.py
custom_pipeline_stable_diffusion.py		custom_pipeline_stable_diffusion.py
delete_original_videos.py		delete_original_videos.py
download_videos.py		download_videos.py
embedding_processor.py		embedding_processor.py
extract_audio_clips.py		extract_audio_clips.py
extract_best_image.ipynb		extract_best_image.ipynb
extract_video_clips.py		extract_video_clips.py
main.py		main.py
train_model.py		train_model.py
vggsound.csv		vggsound.csv

Provide feedback