Gaurav Seth (@gseth83) header
Gaurav Seth (@gseth83) profile picture

Amateur android dev, graphic designing for Android & iOS, photography & a game enthusiast.

Planet Earth
Joined August 2010
Photo by Gaurav Seth (@gseth83)Photo by Gaurav Seth (@gseth83)Photo by Gaurav Seth (@gseth83)Photo by Gaurav Seth (@gseth83)Photo by Gaurav Seth (@gseth83)Photo by Gaurav Seth (@gseth83)Photo by Gaurav Seth (@gseth83)Photo by Gaurav Seth (@gseth83)Photo by Gaurav Seth (@gseth83)Photo by Gaurav Seth (@gseth83)
MyWallApp, Pixel 7a
13
1
90
11,528
Gaurav Seth retweeted
The next @boringcompany merch will put Uranium in Uranus
2,564
1,744
531
31,680
15,818,229
It's gonna be no for me dawg.
🇨🇳 CHINESE ROBOT DRAWS BLOOD WITH SNIPER PRECISION A hospital in Hangzhou has a blood-drawing robot now. It finds your vein, sticks the needle, and pulls the blood. No nurse. No drama. Made by Beijing Magicnurse, it hits the vein 94.3% of the time, which is probably better than your last blood test. It doesn’t ask how your day is going. It doesn’t miss. It just stabs with precision. Welcome to healthcare 3000. Source: @chengdu_china
4
1
19
5,916
Gaurav Seth retweeted
Replying to @elonmusk
Is this a @grok output @elonmusk ? Very good if so
1
1
1
3
981
Gaurav Seth retweeted
1/39 It's time to share how I create portraits for The Grand Timeline! Get ready for a ton of technical details. As usual, I couldn't explain it briefly. 🧶
16
22
10
91
30,632
Gaurav Seth retweeted
1
4
2,021
#MNML Apps used: @jorpMan ditutto kwgt @gseth83 diddly @obasu75 phony walls @Jeisonv62840567 hishoot2
7
16
1
25
2,754
Gaurav Seth retweeted
Wallpaper by @lagguydesign Icon pack by @gseth83 Widget by @Abhishek01kr
2
1
5
2,053
🍁🪻 Leaves 🪻🍁 Colorful leaves wallpaper to download 🔽 Arrow kwgt Clockwidget by @Ahmadansari2233 X Viby iconpack by @gseth83 @NovaLauncher 8.0.17 @SamsungNL Galaxy S23 Plus 512gb.
1
9
745
135 new walls, mywallapp
1
1
1
539
This is awesome....👌
🌟✨ Dive into the Future of Creativity with Picsi.Ai - Powered by InsightFace! 🎨🚀 We're ecstatic to introduce the revolutionary /Headshot Creator, to everyone including FREE members (limited trial) starting today! Come to linktr.ee/picsi.ai to get started!
1
1
351
Here is official Google's demo-video of Assistant with Bard for Pixel Tips app So maybe we will see it in the next Pixel Feature Drop ? t.me/google_nws/3887
10
43
13
343
62,981
MyWallApp, Pixel 8 Pro
2
353
Pixel 8 Pro, MyWallApp 😊
3
359
📞 Realme GT 5 Pro 📞 New Realme GT 5 Pro wallpaper to download 🔽 One You Galaxy Watch 6 clock widget.. To set in all colors by @NovaLauncher Viby iconpack by @gseth83 @SamsungNL Galaxy S23 Plus 512gb
1
2
7
1,663
Gaurav Seth retweeted
India became first country to demonstrate the capability of engagement of 04 aerial targets simultaneously at 25Km ranges by command guidance using single firing unit. The test was conducted by @IAF_MCC using Akash Weapon System @DefenceMinIndia @SpokespersonMoD
588
5,078
504
19,319
899,128
Our December software update begins rolling out today to all supported Pixel devices running #Android14. Along with the latest #FeatureDrop, you’ll see improvements to: 🔊Audio 🔋Battery & charging 📷Camera 🌐Bluetooth & Wi-Fi 🎉And more! Learn more: goo.gle/3GstKQS
88
100
9
826
79,267
We’ve rolled out a few updates to Stable Audio. With much more coming soon... stableaudio.com/ Find out what’s new 🧵
11
37
9
176
78,108
Last wall for Nov before the holiday month. Pixel 8 Pro, MyWallApp. 🤩
2
18
1,970
Gaurav Seth retweeted
Over the last few months I have spent a lot of time sampling from this model. Some tips: 1) You can generate videos even with small GPUs (just decrease number of frames you decode at a time as this eats most VRAM). 14 frames (decoding one at a time) should be less than 20GB VRAM
Stability releases Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets model: huggingface.co/stabilityai/s… present Stable Video Diffusion — a latent video diffusion model for high-resolution, state-of-the-art text-to-video and image-to-video generation. Recently, latent diffusion models trained for 2D image synthesis have been turned into generative video models by inserting temporal layers and finetuning them on small, high-quality video datasets. However, training methods in the literature vary widely, and the field has yet to agree on a unified strategy for curating video data. In this paper, we identify and evaluate three different stages for successful training of video LDMs: text-to-image pretraining, video pretraining, and high-quality video finetuning.
11
60
11
274
117,409