Due to extremely high demand our servers are burning! 🔥🔥🔥

wow. The new model from Luma AI extending images into videos is really something else. I understood intuitively that this would become possible very soon, but it's still something else to see it and think through future iterations of. A few more examples around, e.g. the

Coming soon to Dream Machine - powerful editability and intuitive controls! Here's a sneak-peak of something exciting we are working towards. #LumaDreamMachine Sign up for early access and to be the first to know when it is ready: forms.gle/PnfNkVPs3jYhvA…

We've also updated our prompt guide to include comprehensive suggestions, including how to do a good keyframe video! Check it out here: lumaai.notion.site/FAQ-and-Prompt…

Will be in SF this Saturday at SPC for the Luma Dream Machine hackathon! Who else is joining?

GPU might be like cellular data in the future In the short term future, we will have a ton of AI apps and agents that we use frequently, but instead of paying subscription fees, what if we can just buy GPU hours and decide which app we wish to use it to run on locally?

I finally released my new video on YouTube about Diffusion Models / Score-Based Generative Models. youtube.com/watch?v=B4oHJp… Literally planned this for a year and put so much work in. I think this approach to diffusion models is so intuitive and highly recommend giving that a

mixing real videos with AI. introducing Video Extend, a new feature in Krea that lets you extend videos with AI. tutorial below 👇

Say hello to the all-new #DreamMachine. 🚀 Your visual thought partner—where ideas become reality. Ideate, visualize, and share your ideas with the world. Available now.

Check out these amazing work from our creator community!

I do love these Hitchhiker's easter eggs in grok 2

My favorite prompt: A photo-realistic cat made out of peeled oranges Show your results!

👀

"Closeup of a brush painting on a canvas." Small details. This is Luma AI #Ray2

After 7 months, our next generation of frontier model reimagined Enjoy!

My favorite serie of generations on #Ray2: Miniature Animals! All these are generated with one shot from #LumaDreamMachine Show me more ideas!

Great opportunity to join Luma at this exciting times to work with William and me on building multi-modality!

Today, we release Inductive Moment Matching (IMM): a new pre-training paradigm breaking the algorithmic ceiling of diffusion models. Higher sample quality. 10x more efficient. Single-stage, single network, stable training. Read more: lumalabs.ai/news/imm