Ethan B. Holland

Over 62,700 manually organized AI links and counting

AI Video News: Week Ending 02/16/2024

Open AI Sora

“Introducing Sora, our text-to-video model. Sora can create videos of up to 60 seconds featuring highly detailed scenes, complex camera motion, and multiple characters with vibrant emotions. https://t.co/7j2JN27M3W Prompt: “Beautiful, snowy… https://t.co/ruTEWn87vf” / X – https://twitter.com/OpenAI/status/1758192957386342435

Sora – Sora is an AI model that can create realistic and imaginative scenes from text instructions.

https://openai.com/sora

(18) OpenAI Sora: All Example Videos Upscaled to 4K (no sound) – YouTube – https://www.youtube.com/watch?v=f2h9Jt2Awpc

“To me this is the most impressive part of OpenAI’s Sora demo. Being able to change the style and environment of any video with a simple text prompt – with this kind of detail and realism, is pretty surreal. As someone who creates a lot of videos… this changes things. A lot. https://t.co/B7BpO5f013” / X – https://twitter.com/rpnickson/status/1758572753802641747

“All of these UNBELIEVABLE videos were created using Sora, the new AI model from OpenAI Watch each one and see how it makes you feel… I don’t think it’s crazy for me to say this going to shift Hollywood, social apps and media forever Video #1 Prompt: The camera directly faces… https://t.co/NJfphtGbWb” / X – https://twitter.com/gregisenberg/status/1758216163014660535

“@MrBeast @_tim_brooks @billpeeb @model_mechanic https://t.co/vb9giSg9np” / X – https://twitter.com/sama/status/1758249750909096142

“https://t.co/nej4TIwgaP” / X – https://twitter.com/sama/status/1758218820542763012

“2. An insanely detailed video of a woman’s eye blinking generated with AI using Sora https://t.co/yuGNbGks4C” / X – https://twitter.com/rowancheung/status/1758538823066107945

“14. Drone video POV driving through the woods generated by Sora https://t.co/syaUyGV2lg” / X – https://twitter.com/rowancheung/status/1758539799793656193

“10. Sora’s view of puppies playing in the snow https://t.co/7S2e8k5Hvq” / X – https://twitter.com/rowancheung/status/1758539507991728448

“5. Mountain bike infinity loop generated by Sora (you can’t tell where the video ends) https://t.co/wIWbRptW0P” / X – https://twitter.com/rowancheung/status/1758539071016566934

“https://t.co/WanFKOzdIw” / X – https://twitter.com/sama/status/1758219575882301608

“🚨 BREAKING: OpenAI just launched Sora, an AI model that can create 60-second videos from just text prompts. The video below was 100% created by Sora. https://t.co/qu9KN1QUMv” / X – https://twitter.com/rowancheung/status/1758194965534978067

“Video #9 Prompt: Reflections in the window of a train traveling through the Tokyo suburbs. My take: This trips me out. I was recently in Tokyo on what feels like this exact same train, looking out this exact same view. It’s like I’m having a weird deja-vu type of experience… https://t.co/saqiCshs3z” / X – https://twitter.com/gregisenberg/status/1758219702088630675

“”a walking figure made out of water tours an art gallery with many beautiful works of art in different styles” Video generated by Sora Sora has object permanence – the paintings stay consistent before and after the water man walks in front https://t.co/lQgmlhHbir” / X – https://twitter.com/_tim_brooks/status/1758666264032280683

“Sora is incredible: “A backcountry skier in a yellow jacket with a backpack doing a first line in fresh powder in the Italian Dolomites. Make him average/ok at skiing so its relatable” https://t.co/UAtgTwvIbu” / X – https://twitter.com/sGianella/status/1758237698349801878

“I’m still gathering my thoughts after seeing the #SORA drop from @OpenAI – It handles complex scenes, multiple characters & accurate details of the subject and background Just look at what the following prompt generated: “Historical footage of California during the gold rush.” https://t.co/YGN42X1Mxb” / X – https://twitter.com/SpiderMonkeyXYZ/status/1758249644763836745

“Sora performance scales with compute https://t.co/ceuQYcSXT2” / X – https://twitter.com/tsarnick/status/1758323312483303443 

“Pretty much, just describe to edit. In the sora technical paper they note that they apply SDEdit by @chenlin_meng et al fine – you can take that further through scene decomposition, segmentation, regional prompting & more to autocorrect & balance image, video, audio, etc etc https://t.co/C2k4vf2bkm” / X – https://twitter.com/EMostaque/status/1758854642635526625 

“If you are not following the more academic debate on Sora, beyond what it does as a movie maker, you may want to read this thread The current discussion is whether Sora is secretly a simulator, not merely a maker of movies. This would have pretty big implications for AI, if true” / X – https://twitter.com/emollick/status/1758989174810546344

“If you think OpenAI Sora is a creative toy like DALLE, … think again. Sora is a data-driven physics engine. It is a simulation of many worlds, real or fantastical. The simulator learns intricate rendering, “intuitive” physics, long-horizon reasoning, and semantic grounding, all… https://t.co/pRuiXhUqYR” / X – https://twitter.com/DrJimFan/status/1758210245799920123

“People aren’t taking the “everyone will be filmmakers” seriously enough. I made this 20s trailer in 15mins with an OpenAI Sora clip, David Attenborough’s voice on Eleven Labs, and sampling some nature music from Youtube on iMovie https://t.co/pbfmle9bvb” / X – https://twitter.com/debarghya_das/status/1758338330163622203

“”a photorealistic video of a butterfly that can swim navigating underwater through a beautiful coral reef” Video generated by Sora https://t.co/nebCKLa09U” / X – https://twitter.com/_tim_brooks/status/1758959726933774489

“Sora can generate multiple videos side-by-side simultaneously. This is a single video sample from Sora. We didn’t stitch this together; Sora decided it wanted to have five different viewpoints all at once! https://t.co/hGae80tM5a” / X – https://twitter.com/billpeeb/status/1758960998315135360

“”The camera lowers and widens to a grand panoramic view overlooking the beautiful ocean and the historical buildings along the a stunning coastal picturesque town perched on the cliffs…” Video generated by Sora. https://t.co/d35Zebo4vc” / X – https://twitter.com/billpeeb/status/1758958132615619005

“Give it a year and this annotation as a form of editing will work directly. You’ll get an edited version with the improvements you ask for. You will still need the human to do the annotation.” / X – https://twitter.com/fofrAI/status/1758720040109801509

“When you pull up with an offering of oat milk, but your cat overlord only drinks whole milk 🥛 🐈 👑 Generated with OpenAI Sora by @billpeeb https://t.co/OWVXPFJLyq” / X – https://twitter.com/bilawalsidhu/status/1758654618802978986

“here is sora, our video generation model: https://t.co/CDr4DdCrh1 today we are starting red-teaming and offering access to a limited number of creators. @_tim_brooks @billpeeb @model_mechanic are really incredible; amazing work by them and the team. remarkable moment.” / X – https://twitter.com/sama/status/1758193609927721350 

“OpenAI just dropped the bomb on video generation. But how do they compare to their closest rival? OpenAI: Sora vs Runway: Gen2 https://t.co/JYbnCqm6Dd” / X – https://twitter.com/doganuraldesign/status/1758411532805779874

“Well then! OpenAI just shattered the “Visual” Turing Test 🤯 “Is it real or is it fake?” isn’t just for photos now. Videos too have fallen, and I couldn’t be more excited. With Sora you can create minute long (!) videos with complete freedom for camera motion, aesthetic style,… https://t.co/gpKKoVJU5K” / X – https://twitter.com/bilawalsidhu/status/1758236299696198122

“I think I kinda understand how Sora works now So Stable Diffusion / DALL-e for example is a 2d model so it has X/Y coords Then Stable Video Diffusion, one of the first video models, is the same but with a temporal dimension, it can predict the next frames, so it has X/Y/t… https://t.co/VUXC4M21de” / X – https://twitter.com/levelsio/status/1758496691391479929

Other Video News

“The power of Leonardo AI. The image to video feature, even without motion control, is absolutely fantastic. Incredible tool. https://t.co/jz9XejRX3o” / X – https://twitter.com/OnwardsProject/status/1758113942927441935

SEINE: Short-to-Long Vidoes Diffusion Model for Generative Transition and Prediction – https://vchitect.github.io/SEINE-project/ 

[2402.08934v1] Extreme Video Compression with Pre-trained Diffusion Models – https://arxiv.org/abs/2402.08934v1

Be Sure To Read “This Week In AI”

This week’s executive overview and top links are here:

AI News #20: Week Ending 02/16/2024 with Executive Summary and Top 39 Stories

The post you just read is an extension of my weekly newsletter, This Week In AI, an executive summary of the top things to know in AI. Each week, I create an accessible overview for laypeople to feel confident they are conversant with the week’s AI developments. I include a curated list of must-click links of the week, to offer everyone a hands-on opportunity to explore the most intriguing updates in artificial intelligence across various categories, including robotics, imagery, video, AR/VR, science, ethics, and more. Beyond the overview, I post these topic-based deeper dives (below). If you haven’t read this week’s overview, I recommend starting there.

Credits/Sources

Most of these links come from just a few incredible sources.  Please follow them:

Previous Issues

One response to “AI Video News: Week Ending 02/16/2024”

  1. AI News #20: Week Ending 02/16/2024 with Executive Summary and Top 39 Links – Ethan B. Holland

    […] AI Video News of the Week: AI video in this case refers to generative video. Much like imagery meant generative imagery. This usually text-to-video, where a user enters a prompt (“a wizard walking out of a flaming building”) and a tool like Pika or Runway generates an video in the likeness of the description. It also covers animation of still images, where an image is given motion (like a photo of a waterfall appearing to have flowing water). As with images, this is different than AI vision, where an AI “looks at” an image or video and can derive context, details, and contents. Video, in this case, is video creation and modification/editing.This weeks’s latest AI video news: https://ethanbholland.com/2024/02/26/ai-video-news-week-ending-02-16-2024/ […]

    Reply

Leave a Reply

Trending

Discover more from Ethan B. Holland

Subscribe now to keep reading and get access to the full archive.

Continue reading