Make-A-Video: Text-To-Video Generation Without Text-Video Data | Paper Explained
🚀 Find out how to get started using Weights & Biases 🚀
http://wandb.me/ai-epiphany
👨👩👧👦 Join our Discord community 👨👩👧👦
/ discord
In this video I cover the latest text-to-video paper from Meta: "Make-A-Video: Text-To-Video Generation Without Text-Video Data".
I walk you through the 3-stage approach that consists of:
Training a DALL-E 2 type of a model
Integrating temporal information and tuning on unlabeled videos
Fine-tuning the frame interpolation module.
▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬
✅ Paper: https://arxiv.org/abs/2209.14792
✅ Website: https://makeavideo.studio/
▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬
⌚️ Timetable:
00:00 Intro
00:25 (sponsored) Weights & Biases
01:37 Going through the generations
06:15 High-level paper overview
10:50 Results
15:40 Limitations
16:30 Diving deep: DALL-E 2 backbone
23:35 Expanding to 3D - temporal info integration
32:39 Frame interpolation
37:24 3-stage training
41:28 Outro
▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬
💰 BECOME A PATREON OF THE AI EPIPHANY ❤️
If these videos, GitHub projects, and blogs help you,
consider helping me out by supporting me on Patreon!
The AI Epiphany - / theaiepiphany
One-time donation - https://www.paypal.com/paypalme/theai...
Huge thank you to these AI Epiphany patreons:
Eli Mahler
Petar Veličković
▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬
💼 LinkedIn - / aleksagordic
🐦 Twitter - / gordic_aleksa
👨👩👧👦 Discord - / discord
📺 YouTube - / theaiepiphany
📚 Medium - / gordicaleksa
💻 GitHub - https://github.com/gordicaleksa
📢 AI Newsletter - https://aiepiphany.substack.com/
▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬
#makeavideo #meta #texttovideo