Post

How to get URL link on X (Twitter) App

On the Twitter thread, click on or icon on the bottom
Click again on or Share Via icon
Click on Copy Link to Tweet
Paste it above and click "Unroll Thread"!
More info at Twitter Help

Luma AI

@LumaLabsAI

Jun 12, 2024 • 9 tweets • 3 min read • Read on X

Scrolly

Introducing Dream Machine - a next generation video model for creating high quality, realistic shots from text instructions and images using AI. It’s available to everyone today! Try for free here #LumaDreamMachine lumalabs.ai/dream-machine

Next level text to video!

Powerful image to video!

Realistic camera movements that blur the boundaries of reality 🎥: @Next_On_NOw

Incredible, realistic camera work🎥: @Next_On_NOw

As well as cinematic motion!🎥: @tommyoshima

And experiment with any style imaginable 🎥: Steve Schütz - IG: radstream

Unleash your inner monster maker 🎥: Monster Camp by @monster_library

Tell incredible stories… 🎥: “Break The Tie” by @ai_mov_director

• • •

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

This Thread may be Removed Anytime!

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

More from @LumaLabsAI

Luma AI

@LumaLabsAI

Mar 31

Introducing #Ray2 Camera Motion Concepts in #DreamMachine — 20+ precision-tuned camera motions designed for smooth cinematic control and great reliability. Concepts compose with each other making hundreds of impossible new camera moves possible. Available now.

We’ve developed a new way to teach generative models ideas and controls — we call them Concepts. Releasing today: Camera Motion Concepts. Learnable from just a few examples and composable into workflows for precise control in Ray2. And it’s just the start. lumalabs.ai/news/camera-mo…

Zoom In & Out

Read 14 tweets

Luma AI

@LumaLabsAI

Mar 11

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

Behind IMM is an inference-first perspective, which we believe is key to unlocking the potential of rich multi-modal data efficiently. In particular, we find that the DDIM sampler can be made more flexible by adding an input argument to the neural network.

This allows IMM to converge to good solutions much faster than diffusion models, without relying on the mathematical foundations such as denoising score matching and flow matching.

Read 5 tweets

Luma AI

@LumaLabsAI

Jan 15

Introducing Ray2, a new frontier in video generative models. Scaled to 10x compute, #Ray2 creates realistic videos with natural and coherent motion, unlocking new freedoms of creative expression and visual storytelling. Available now. Learn more . lumalabs.ai/ray

Ray2 is available now in Dream Machine, initially to paid subscribers. We are starting with text-to-video. Image-to-video, video-to-video and editing capabilities will soon follow.

Natural Motion: "wide shot of a man in a fur coat running through the snow antarctic with many explosions around him"

Read 12 tweets

Luma AI

@LumaLabsAI

Nov 25, 2024

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.

Try Dream Machine for free on iOS & Web lumalabs.ai/dream-machine

No prompt engineering needed. Just talk to Dream Machine in your own way to generate, edit, and move through your explorations fluently.

Read 8 tweets

Luma AI

@LumaLabsAI

Feb 23, 2023

twitter.com/i/web/status/1…

✨ Today we are ready to take AI Graphics to the next level: full volumetric photorealistic NeRF rendering on the web. All in realtime!

What you see is what you get for photorealistic 3D is finally here!

Starting with the the Fields Editor soon you’ll be able to reshoot in… twitter.com/i/web/status/1…