Fun fact: the longest part of making this entire video was animating the pointer finger and the screen zooms.

Need more research to render Crytek Sponza though.

Generated.

The normalization of magic. The fact that you can do all of this in a few minutes inside Runway is still pretty wild to me.

Exploring Large Scale Environments in #Houdini using Solaris. Rendered with Karma XPU.

Leopard slugs by Gen-4.

'GAIA' Solarpunk 3D Environment built using houdini solaris, karma, blender, gaea and nuke #cgi #3danimation #solarpunk #houdini #blender3d

life at home a 360 gaussian splat, shot with @insta360 X5 and trained in @jawset PostShot

Real-time video generation offers up so many opportunities, even beyond the mainstream. I'm looking forward to live prompting interfaces where performances and art are generated live in front of an audience, like live coding. (pic is hydra)

The best of the best when it comes to multi-modal data.

Really a great selection of films. Still shocking that these were all made in less than 48 hours.

Voting closes today at 9am ET. Watch some great films and support your favorites!

将来のストリートビューはこんな感じになるか？ 五反田駅から弊社オフィスビルまでの道のりを 全て3D空間化＆公開してみた。 誰でもブラウザで体験できるので五反田散歩してみてくださいな。 (XGRIDSレーザースキャンから3DGS生成したものをArrivalSpaceにアップした)

Also loved the style, colors and concept from "TO THE VOID". Great work. https://t.co/F7FHO8MCBY

Another one that stood out to me was "F3-L1". Again, great narration, stunning frames and interesting story. https://t.co/Li3Leghr1b

All Gen-48 films were so good. Hard to select favorites, but one had me fully hooked from the beginning. And that was "There Is No Monster". Magnificient narration, quick buildup and beautiful shots. I just want more. https://t.co/CBEZQSTU2l

Damn. So many great ones. Love all the creative ways people used Aleph.

Runway Aleph is a new way to edit, transform and generate video. Its ability to perform a wide range of generalized tasks means it can reimagine ordinary footage in endless new ways. Allowing you to turn images and videos you already have into anything you want. See below for a

Generative models are more powerful when you don't care about documentary accuracy (advertising, VFX, games, surrealistic art, animation). These are synthetic in nature and are already simulated. Generative models, in my view, are closer to graphics algorithms but now learned.

Photography and generative art is separate in my view. To me, photography is the documentation of what is real. So I am not interested in editing my photos with generative models. I only use tools that reconstruct what I saw and felt.