LAION-5B: 5 billion image-text-pairs dataset (with the authors)
#laion #clip #dalle
LAION-5B is an open, free dataset consisting of over 5 billion image-text-pairs. Today's video is an interview with three of its creators. We dive into the mechanics and challenges of operating at such large scale, how to keep cost low, what new possibilities are enabled with open datasets like this, and how to best handle safety and legal concerns.
OUTLINE:
0:00 - Intro
1:30 - Start of Interview
2:30 - What is LAION?
11:10 - What are the effects of CLIP filtering?
16:40 - How big is this dataset?
19:05 - Does the text always come from the alt-property?
22:45 - What does it take to work at scale?
25:50 -When will we replicate DALL-E?
31:30 - The surprisingly efficient pipeline
35:20 - How do you cover the S3 costs?
40:30 - Addressing safety & legal concerns
55:15 - Where can people get started?
References:
LAION website: https://laion.ai/
LAION Discord: https://discord.com/invite/mVcgxMPD7e
LAION-5B: https://laion.ai/laion-5b-a-new-era-o...
img2dataset tool: https://github.com/rom1504/img2dataset
LAION-400M: https://paperswithcode.com/dataset/la...
Links:
TabNine Code Completion (Referral): http://bit.ly/tabnine-yannick
YouTube: https://www.youtube.com/c/yannickilcher
Twitter: https://twitter.com/ykilcher
Discord: https://discord.gg/4H8xxDF
BitChute: https://www.bitchute.com/channel/yann...
LinkedIn: https://www.linkedin.com/in/ykilcher
BiliBili: https://space.bilibili.com/2017636191
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/yannick...
Patreon: https://www.patreon.com/yannickilcher
Bitcoin (BTC): bc1q49lsw3q325tr58ygf8sudx2dqfguclvngvy2cq
Ethereum (ETH): 0x7ad3513E3B8f66799f507Aa7874b1B0eBC7F85e2
Litecoin (LTC): LQW2TRyKYetVC8WjFkhpPhtpbDM4Vw7r9m
Monero (XMR): 4ACL8AGrEo5hAir8A9CeVrW8pEauWvnp1WnSDZxW7tziCDLhZAGsgzhRQABDnFy8yuM9fWJDviJPHKRjV4FWt19CJZN9D4n
-
The Quartering
14 hours agoLIVE JD Vance vs Tim Walz Debate! Real Time Fact Check & Coverage On WW3!
189K186 -
4:09:21
Breaking Points
12 hours agoJD Vance VS. Tim Walz Debate LIVE
77K47 -
3:35:06
Fresh and Fit
5 hours agoJD Vance VS Tim Walz! Vice President Debate 2024
120K133 -
Benny Johnson
10 hours ago🚨 DEBATE-MAGEDDON: Kamala In PANIC Ahead of Trump Debate, Dems Admit DEFEAT!? Lara Trump Joins LIVE
223K767 -
3:03:36
Laura Loomer
10 hours agoEP79: LIVE VP DEBATE COVERAGE: JD VANCE VS TIM WALZ
92.4K51 -
1:35:19
Glenn Greenwald
12 hours agoIran's Missile Retaliation Against Israel: What Does It Mean For The U.S. & The Region? Plus: VP Debate Reaction On Locals | SYSTEM UPDATE #344
211K227 -
Fresh and Fit
13 hours agoIran Launches Massive Missile Attack On Israel
230K75 -
4:27:53
WeAreChange
11 hours agoLIVE W/ Alex Jones & Roger Stone: Vance vs. Walz, HOT CONFLICT Igniting!
161K70 -
Slightly Offensive
13 hours agoTHE MOST RETARDED VP DEBATE STREAM | Guest: Breanna Morello
102K34 -
Josh Pate's College Football Show
12 hours agoChaotic Saturday Coming | Full Week 6 Predictions | New JP Poll | Added Best Bets
64.4K3