Parti - Scaling Autoregressive Models for Content-Rich Text-to-Image Generation (Paper Explained)

Jun 28, 2022

|

37 views

Yannic Kilcher

Details

#parti #ai #aiart Parti is a new autoregressive text-to-image model that shows just how much scale can achieve. This model's outputs are crips, accurate, realistic, and can combine arbitrary styles, concepts, and fulfil even challenging requests. OUTLINE: 0:00 - Introduction 2:40 - Example Outputs 6:00 - Model Architecture 17:15 - Datasets (incl. PartiPrompts) 21:45 - Experimental Results 27:00 - Picking a cherry tree 29:30 - Failure cases 33:20 - Final comments Website: https://parti.research.google/ Paper: https://arxiv.org/abs/2206.10789 Github: https://github.com/google-research/parti 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

0:00 - Introduction 2:40 - Example Outputs 6:00 - Model Architecture 17:15 - Datasets (incl. PartiPrompts) 21:45 - Experimental Results 27:00 - Picking a cherry tree 29:30 - Failure cases 33:20 - Final comments

Category: Misc.

Category: Research Paper

Comments

loading...

Reactions (0) | Note

📝 No reactions yet

Be the first one to share your thoughts!

Reactions(0)

Note

loading...

Recommended

The ICAPS Three

ICAPS | Jul 2, 2014

ICAPS 2014: Daniel Harabor on "Improving Jump Point Search"

ICAPS | Jul 2, 2014

ICAPS 2014 Invited Talk: Peter Wurman

ICAPS | Jul 2, 2014

ICAPS 2014: Mike Phillips on "PA*SE: Parallel A* for Slow Expansions"

ICAPS | Jul 3, 2014

ICAPS 2014: Vidal Alcázar on "Analyzing the Impact of Partial States..."

ICAPS | Jul 3, 2014