Barsee 🐶 Profile picture
Apr 21, 2023 11 tweets 6 min read Read on X
AI-generated 3D scene created from photos/videos are insane.

It's called #NeRfs and can be done with @LumaLabsAI or @nvidia

Here's are 10 mind blowing video generated by AI:

1. Dollyzoom Effect by @karenxcheng
2. @franclucent took over a 100+ NVIDIA's NeRFs and put it together in a video.

The video looks awesome.
3. They created NeRF from inside of a volcano while playing catch with a ball 🌋🏈

Done by @nerfstudioteam
4. This is not a drone footage.

It's Zip-NeRF: it’s a modified version of NeRF that uses multi-scale image pyramids to improve rendering quality 👇
5. Instruct-NeRF2NeRF: Editing 3D Scenes with Instructions

proj: instruct-nerf2nerf.github.io
6. He created the NeRfs with @LumaLabsAI and processed it with @runwayml
's Gen-1.

Awesome work by @JustMDMZ
7. Text to Physical Search 🔥

Super easy to search for everyday things.

It combines CLIP vectors and NeRF which allows you to quickly search from text descriptions.

lerf.io
8. Created with LumaLabsAI, processed the output via Kaiber AI.

It looks beautiful and mystical.

Another one by @tommyoshima

9. This is perfect for brands advertisement.

This looks really fresh.
If you found this helpful or interesting.

Please retweet the tweet below to share it with your friends❤️

• • •

Missing some Tweet in this thread? You can try to force a refresh
 

Keep Current with Barsee 🐶

Barsee 🐶 Profile picture

Stay in touch and get notified when new unrolls are available from this author!

Read all threads

This Thread may be Removed Anytime!

PDF

Twitter may remove this content at anytime! Save it as PDF for later use!

Try unrolling a thread yourself!

how to unroll video
  1. Follow @ThreadReaderApp to mention us!

  2. From a Twitter thread mention us with a keyword "unroll"
@threadreaderapp unroll

Practice here first or read more on our help page!

More from @heyBarsee

May 13
OpenAI wins the internet with another big breakthrough in AI.

It takes their ChatGPT capabilities to a whole new level.

Here are 7 revolutionary innovations they unveiled today:
1/ OpenAI introduces 'GPT-4 Omni', enhancing its AI model to support voice, text, and vision, available to all users including free accounts.
2/ 'GPT-4 Omni' comes with a new voice assistant.

- it can handle interruptions
- does real-time response
- even picks up on emotion

It actually sounds like "HER"

Read 9 tweets
May 6
12 AI images are almost impossible to comprehend as fake (until you look closely) - a thread🧵👇

1/12 Image
2/12 Image
3/12 Image
Read 14 tweets
May 4
AI is about to change the VFX industry 🤯

Simulon can add any 3D model to your real footage video in a matter of minutes

Here are 13 most hyper-realistic videos (you'll feel like you can touch them):

1/ a pair of Muhammed Ali’s gloves brought to life
2/ The way it is able to interact with reality will change the way we view video content forever!
3/ What are you playing first? 🎮

Read 15 tweets
May 3
Meta is spending $30 billion on NVIDIA GPUs just to train their AI that will surpass human intelligence.

This is more than the Apollo moon mission cost.

Here's everything you need to know: 🧵 Image
Since ChatGPT was unveiled, OpenAI and Microsoft have dominated the headlines in artificial intelligence.

Meta, however, has been steadily increasing its presence with frequent releases of new AI products, never content to be left behind.
Meta recently announced that they are spending billions to buy 350,000 Nvidia H100 GPUs to develop its version of artificial general intelligence (AGI)

AGI is an AI that matches or even surpasses human intelligence in nearly all areas. Image
Read 18 tweets
Apr 27
It's been an insane week for AI (part 2)

Here are 14 most impressive reveals from this week:

1/ China just released OpenAI’s Sora rival “Vidu” which can create realistic clips in seconds.
2/ Apple is in talks with OpenAI for iPhone generative AI features.

The update could include a new Apple AI chatbot like ChatGPT.

Source: @markgurman Image
@markgurman 3/ Meta finally rolls out multimodal AI capabilities for its smart glasses

The glasses can translate languages, make video calls, identify objects, capture photos, and listen to music.
Read 15 tweets
Apr 23
It's been an insane week for AI/AR.

Here are 13 most impressive reveal from this week:

1/ Simulon can add any 3D model to your real footage video in a matter of minutes.
2/ Meta is already testing a consumer neural interface that understands what you are thinking.
3/ First successful surgery done using Apple Vision Pro.

For the first time in Brazil, a surgeon successfully used an Apple Vision Pro headset to optimize a surgical procedure.

Read 14 tweets

Did Thread Reader help you today?

Support us! We are indie developers!


This site is made by just two indie developers on a laptop doing marketing, support and development! Read more about the story.

Become a Premium Member ($3/month or $30/year) and get exclusive features!

Become Premium

Don't want to be a Premium member but still want to support us?

Make a small donation by buying us coffee ($5) or help with server cost ($10)

Donate via Paypal

Or Donate anonymously using crypto!

Ethereum

0xfe58350B80634f60Fa6Dc149a72b4DFbc17D341E copy

Bitcoin

3ATGMxNzCUFzxpMCHL5sWSt4DVtS8UqXpi copy

Thank you for your support!

Follow Us!

:(