CogVideo Tutorial: DALL-E For Text To Video Generation
DALL-E is well known for its image generation given a sentence. Well, the next logical step is video generation given a sentence, and that is what CogVideo aims to do. This is an exciting early step in this area of research.
#ai #aiart #machinelearning #dalle2 #stablediffusion
Github: https://github.com/THUDM/CogVideo
Discord: / discord
Donations(if you want):
Ethereum:
4CE913643909Fa3168297cC2857C0aDdAB389Ad8
Monero: 45mqN96o5JZZhwVTZHHiQJeyhp3WndiPC44hdrAmWeDGeCmaC1c45gTGh5eDUtEhx3JDGbsAnsD3VBXKdiorUhusUydLG22
Timestamps
00:00 - Intro
00:58 - Web Demo
01:24 - Hardware Requirements
02:00 - Cloning Repo
03:28 - Downloading Model Weights
03:53 - Setting Up Docker
04:49 - Model Weights Setup
06:00 - Docker Setup Pt2
07:18 - Modifying Run Script
08:50 - Running Run Script
09:24 - Input To Model With Google Translate
10:15 - Generated Results
11:22 - My Thoughts And Concerns
12:57 - Outro And Colab Opportunity