RIP Rotoscoping, Midjourney update, Leonardo Joins Canva | DR.AI

Don't forget to check out the podcast:?https://bit.ly/DRAIPod

Design Industry AI News

Nvidia and WPP team upto create generative 3D worlds

You can now generate 3D worlds through text prompts.?This collaboration allows you to assemble pre-made 3D assets from WPP to create worlds. One use case example is how they helped Coca-cola create an advert and then swap out objects in the scene for more culturally relevant ones depending on the market.?

Think product shot of a Coke bottle with tacos next to it in Mexico and a Sunday roast in the UK or similar stereotype.

Link

The EU’s AI Act is now in force

The EU's risk-based AI regulation began on August 1 with staggered compliance deadlines categorizing AI applications into low/no-risk, high-risk, and limited risk tiers, imposing transparency, risk management, and penalties for violations. The EU has set a precedent and we'll all watch to see if AI companies boycott the EU or?comply to their transparency rules. This will have global implications.

Link

Segment Anything Two hopefully puts a nail in the rotoscoping coffin

Meta released an update to the Segment Anything Model that enables fast, precise selection of any object in any video or image. No one loves rotoscoping so this can turn a laborious job into just a few clicks. You can try out an impressive demo for non commercial use here:?

SAM2

I wonder how long before a similar tool is brought inside AE or more likely Premiere as the technical barriers fall. If you can't wait for Adobe, and it could be a while! Check out this alternative from DeepMake who are promising more advanced tools soon: DeepMake

Learn

Create your own Stock images in Midjourney

Gizem Akda? shared a tip on Linkedin for creating your own stock imagery in Midjourney. Here is her magical formula: [object], png --c 10 --ar 3:2 --sref 2905246511 --p --s 200

The --p parameter is your personal code and you can only use it if you've rated 200+ images. Shouldn't matter if you drop it out.

Confused about the latest AI tool to use

Nick?St Pierre made it simple for you:

A.I. Tools

GILF - Make AI apps with no code

Nothing to do with grandma's - this app allows you to use text prompts to create ComfyUI workflows or use pre-existing one to make specific kinds of images. It's in effect a?No code AI App builder.?Watch the video for a better idea of what it does but this looks very interesting.

Link

Generate 3D panoramas

360° Panorama Image Generation.

Link

Leonardo is joining forces with?Canva

"We’re thrilled to announce our plans to join forces with Canva, which will supercharge the speed & scale that we’re building Leonardo.Ai ."

Link

Midjourney update?

"Midjourney V6.1 is now live! V6.1 greatly improves image quality, coherence, text, and comes with brand-new upscaling and personalization models. It’s smarter, faster, clearer, and more beautiful. We hope you enjoy our best model yet <3"

Link

A.I. Video

Living Hybrids

Artist Phil Langer brings to life his 'Hybrid Portraits' using Runways new Image to video feature and they are stunning.

CREDITS: Phil Langer

AI exploration

This video created by Claire Xue is an exploration of what creatives with no background in video can make using the latest AI tools. I think Surrealism is going to gain a lot of traction, new tools always influence culture.?

I wouldn’t consider myself a videographer, but the technology enables creatives like me—who have a sense of art direction and a vision—to create videos despite lacking resources. Generative AI lets me bring my vision to life quickly and independently.

CREDITS: Claire Xue

Thanks for reading please share this with a friend who would appreciate it. If you'd lie to receive this email direct to your inbox sign up here: https://bit.ly/design-resources-AI