[ML News] Text-to-Image models are taking over! (Imagen, DALL-E 2, Midjourney, CogView 2 & more)

Subscribers:
284,000
Published on ● Video Link: https://www.youtube.com/watch?v=af6WPqvzjjk



Duration: 20:49
27,879 views
1,255


#mlnews #dalle #imagen

All things text-to-image models like DALL-E and Imagen!

OUTLINE:
0:00 - Intro
0:30 - Imagen: Google's Text-to-Image Diffusion Model
7:15 - Unified I/O by AllenAI
9:40 - CogView2 is Open-Source
11:05 - Google bans DeepFakes from Colab
13:05 - DALL-E generates real Cosmopolitan cover
15:45 - DALL-E tips & tricks
17:00 - Midjourney moves to Open Beta
17:50 - DALLE-mini is not Crayon
19:00 - Deep Learning Resources

AMENDMENTS:
The Unified-IO paper is here: https://arxiv.org/abs/2206.08916

References:
Imagen: Google's Text-to-Image Diffusion Model
https://imagen.research.google/?utm_source=pocket_mylist
https://arxiv.org/pdf/2205.11487.pdf

Unified I/O by AllenAI
https://unified-io.allenai.org/
https://blog.allenai.org/introducing-ai2s-unified-io-9c0ec7fe1e43

CogView2 is Open-Source
https://github.com/THUDM/CogView2
file:///Users/yk/Downloads/big.1.pdf
https://huggingface.co/spaces/THUDM/CogView2
https://arxiv.org/pdf/2204.14217.pdf

Google bans DeepFakes from Colab
https://www-vice-com.cdn.ampproject.org/c/s/www.vice.com/amp/en/article/v7v4gx/google-bans-deepfakes-from-its-machine-learning-platform?utm_source=pocket_mylist

DALL-E generates real Cosmopolitan cover
https://www.cosmopolitan.com/lifestyle/a40314356/dall-e-2-artificial-intelligence-cover/
https://www.instagram.com/p/CfEwohiJdXW/?hl=en

DALL-E tips & tricks
https://twitter.com/GuyP/status/1544710725708513280?s=09&t=c3NpErPx80INQVeaWkIqIg&utm_source=pocket_mylist
https://twitter.com/GuyP/status/1552681939806691329?s=09&t=LV2ChcukUziXfvfNK-sY0A&utm_source=pocket_mylist
https://twitter.com/GuyP/status/1547234780001042432
https://dallery.gallery/the-dalle-2-prompt-book/

Midjourney moves to Open Beta
https://twitter.com/midjourney?lang=en
https://twitter.com/search?q=%23midjourney&f=image

DALLE-mini is not Crayon
https://www.craiyon.com/

Deep Learning Resources
https://github.com/jacobhilton/deep_learning_curriculum
https://arxiv.org/abs/2206.13446
https://arxiv.org/pdf/2206.13446.pdf

Links:
Homepage: https://ykilcher.com
Merch: https://ykilcher.com/merch
YouTube: https://www.youtube.com/c/yannickilcher
Twitter: https://twitter.com/ykilcher
Discord: https://ykilcher.com/discord
LinkedIn: https://www.linkedin.com/in/ykilcher

If you want to support me, the best thing to do is to share out the content :)

If you want to support me financially (completely optional and voluntary, but a lot of people have asked for this):
SubscribeStar: https://www.subscribestar.com/yannickilcher
Patreon: https://www.patreon.com/yannickilcher
Bitcoin (BTC): bc1q49lsw3q325tr58ygf8sudx2dqfguclvngvy2cq
Ethereum (ETH): 0x7ad3513E3B8f66799f507Aa7874b1B0eBC7F85e2
Litecoin (LTC): LQW2TRyKYetVC8WjFkhpPhtpbDM4Vw7r9m
Monero (XMR): 4ACL8AGrEo5hAir8A9CeVrW8pEauWvnp1WnSDZxW7tziCDLhZAGsgzhRQABDnFy8yuM9fWJDviJPHKRjV4FWt19CJZN9D4n




Other Videos By Yannic Kilcher


2022-10-21Neural Networks are Decision Trees (w/ Alexander Mattick)
2022-10-07This is a game changer! (AlphaTensor by DeepMind explained)
2022-10-02[ML News] OpenAI's Whisper | Meta Reads Brain Waves | AI Wins Art Fair, Annoys Humans
2022-09-18[ML News] Stable Diffusion Takes Over! (Open Source AI Art)
2022-09-17How to make your CPU as fast as a GPU - Advances in Sparsity w/ Nir Shavit
2022-09-13More Is Different for AI - Scaling Up, Emergence, and Paperclip Maximizers (w/ Jacob Steinhardt)
2022-09-02The hidden dangers of loading open-source AI models (ARBITRARY CODE EXPLOIT!)
2022-08-26The Future of AI is Self-Organizing and Self-Assembling (w/ Prof. Sebastian Risi)
2022-08-13The Man behind Stable Diffusion
2022-08-10[ML News] AI models that write code (Copilot, CodeWhisperer, Pangu-Coder, etc.)
2022-08-07[ML News] Text-to-Image models are taking over! (Imagen, DALL-E 2, Midjourney, CogView 2 & more)
2022-07-31[ML News] This AI completes Wikipedia! Meta AI Sphere | Google Minerva | GPT-3 writes a paper
2022-07-27[ML News] BLOOM: 176B Open-Source | Chinese Brain-Scale Computer | Meta AI: No Language Left Behind
2022-07-06JEPA - A Path Towards Autonomous Machine Intelligence (Paper Explained)
2022-07-02ARC Challenge Live Coding
2022-06-26Video PreTraining (VPT): Learning to Act by Watching Unlabeled Online Videos (Paper Explained)
2022-06-23Parti - Scaling Autoregressive Models for Content-Rich Text-to-Image Generation (Paper Explained)
2022-06-15Did Google's LaMDA chatbot just become sentient?
2022-06-03GPT-4chan: This is the worst AI ever
2022-06-01Did I crash the NFT market?
2022-05-13[ML News] DeepMind's Flamingo Image-Text model | Locked-Image Tuning | Jurassic X & MRKL



Tags:
deep learning
machine learning
arxiv
explained
neural networks
ai
artificial intelligence
paper
imagen
dalle
dalle 2
dall e
dall e 2
midjourney
midjourney diffusion
generative models
ai art
aiart
mlnews
ml news
kilcher news
ml news yannic
google imagen
cogview
cog view
cog view 2
dalle mini
dalle-mini
dalle mega