Emu - Enhancing Image Generation Models Using Photogenic Needles in a Haystack
Emu is the foundational model for Emu Edit and Emu Video which allow precise editing of objects in images and videos.
This video is about the Emu architecture (a modified Latent Diffusion Model) and the quality fine-tuning procedure that leads to the mind-blowing images generated by Emu. It also walks through the curation process for the quality fine-tuning dataset.
Emu paper title: Enhancing Image Generation Models Using Photogenic Needles in a Haystack
Emu paper link: scontent-lhr6-1.xx.fbcdn.net/...
Emu blog: ai.meta.com/research/publicat...
Emu Edit paper: emu-edit.metademolab.com/asse...
Emu Edit project: emu-edit.metademolab.com
Emu Video: ai.meta.com/blog/emu-text-to-...
Emu Video paper: emu-video.metademolab.com/ass...
Emu Video project: emu-video.metademolab.com
⌚️ ⌚️ ⌚️ TIMESTAMPS ⌚️ ⌚️ ⌚️
0:00 - Intro
0:53 - AI Bites Twitter ( / ai_bites )
1:06 - Approach
1:45 - Architecture
3:15 - U-Net Modifications
3:43 - Pre-Training
4:58 - Fine Tuning (Quality Tuning)
5:20 - Fine Tuning data curation (automatic)
6:20 - Fine Tuning data curation (manual)
7:15 - Evaluation
9:16 - Quality Tuning to other models
🛠 🛠 🛠 MY SOFTWARE TOOLS 🛠 🛠 🛠
✍️ Notion - affiliate.notion.so/aibites-yt
✍️ Notion AI - affiliate.notion.so/ys9rqzv2vdd8
📹 OBS Studio for video editing - obsproject.com
📼 Manim for some animations - www.manim.community
🎵 My music - www.bensound.com and
📚 📚 📚 BOOKS I HAVE READ, REFER AND RECOMMEND 📚 📚 📚
📖 Deep Learning by Ian Goodfellow - amzn.to/3Wnyixv
📙 Pattern Recognition and Machine Learning by Christopher M. Bishop - amzn.to/3ZVnQQA
📗 Machine Learning: A Probabilistic Perspective by Kevin Murphy - amzn.to/3kAqThb
📘 Multiple View Geometry in Computer Vision by R Hartley and A Zisserman - amzn.to/3XKVOWi
MY KEY LINKS
RU-vid: / @aibites
Twitter: / ai_bites
Patreon: / ai_bites
Github: github.com/ai-bites
WHO AM I?
I am a Machine Learning Researcher/practitioner who has seen the grind of academia and start-ups equally. I started my career as a software engineer 15 years ago. Because of my love for Mathematics (coupled with a glimmer of luck), I graduated with a Master's in Computer Vision and Robotics in 2016 when the now happening AI revolution just started. Life has changed for the better ever since.
#machinelearning #deeplearning #aibites
4 авг 2024
