Luma
Luma AI - Ray2 Camera Angle Concepts
updated
Step 2: Take a photo of the same painting. 📸
Step 3: Use Generative Fill in Photoshop to remove the paint and create a blank version of the painting. ✏️
Step 4: Import into Dream Machine, the first frame (empty painting) and the last frame (full painting).
Step 5: Type in prompt “ink paint strokes”. 🖋️
Step 6: Generate video to animate in Dream Machine.
Step 7: 3D camera track your video from Step 1 using tools like After Effects or SynthEyes. 🕹️
Step 8: Place your video generation over the original painting and blend using VFX compositing. 🪄
👉 @kodykurth for more magic tricks and tips!
Step 2: Import photos into First & Last Frame. 🎞️
Step 3: Type prompt “camera static, the (food 1) transforms into the (food 2)”. 🥕↔🥦
Step 4: Generate video and watch your transition!✨
Create your own in #LumaDreamMachine Keyframes
#tutorial #morphing #vfx
Learn more about the Dream Machine API at: lumalabs.ai/dream-machine/api
#LumaDreamMachine #LumaAI
#timelapse #visualstorytelling #lumaai
Blog Post: blog.lumalabs.ai/p/dream-machine
Dream Machine is an AI model that makes high quality, realistic videos fast from text and images. It is a highly scalable and efficient transformer model trained directly on videos making it capable of generating physically accurate, consistent and eventful shots. Dream Machine is our first step towards building a universal imagination engine and it is available to everyone now!
We are hiring! Join our team: lumalabs.ai/join
We believe that multimodality is critical for intelligence. To go beyond language models and build more aware, capable and useful systems, the next step function change will come from vision. So, we are working on training and scaling up multimodal foundation models for systems that can see and understand, show and explain, and eventually interact with our world to effect change. We will deploy these systems to make a new kind of intelligent creative partner that can imagine with us. Free and away from the pressure of being creative. It’s for all of us whose imaginations have been constrained, who’ve had to channel vivid dreams through broken words, hoping others will see what we see in our mind’s eye. A partner that can help us show — not just tell.
Our story started with being able to capture and share our world. We are now embarking on the second chapter of this journey — one where we can imagine new ones.
As a first step, today we are thrilled to release Genie, a generative 3d model capable of creating any 3d object you can dream of in under 10 seconds. Genie can generate quad meshes and materials at any polygon count in standard formats making it suitable for wide ranging use cases. It is available today on web, in Luma’s iOS app, as well as to our Discord community.
We are also incredibly excited to announce Luma’s Series B and to bring onboard Anjney Midha and Andreessen Horowitz. We are grateful for the continued support of our partners at Amplify, Matrix, NVIDIA, South Park Commons, and Angels who have helped us get to this milestone. This round brings us to $70 million raised so far and will accelerate our investments in foundation model compute, data, and growing the team.
We are also honored to announce some phenomenal new additions to Luma! Jiaming Song is joining us from NVIDIA’s generative AI group as our Chief Scientist and will lead the foundation models research team. Matthew Tancik is joining us from Berkeley to lead the applied research team that will elevate our models into capable and delightful products. To lead Luma’s design discipline Tuhin Kumar is joining us from Apple Design Studio and will help us reimagine how interfaces, interactions, and products should feel and function in the generative world.
If our mission speaks to you, and you’d like to work with some of the best people in generative AI, join our small and nimble team. You’ll have radical ownership and grow immensely.
Alex and I couldn’t be more excited to build the future with this exceptional team.
Everything we can imagine should be real!
To hear from us on all things generative AI, follow @LumaLabsAI on X, @luma_ai on Insta and join our Discord community for early access to new models and features.
Media Kit - lumalabs.ai/media-kit
#LumaAI #3D #AI #GaussianSplat #ThreeJS #R3F #reactdeveloper #WebDevelopment #WebDeveloper
💬 Create 3D things in seconds on Discord
⚡️ Prototype in various styles
🎨 Customize materials
🆓 Free during research preview
🔥 Browser & Phone-Friendly: Hyperefficient and fast rendering everywhere
👌 Embed Anywhere: 8-20MB streaming files (even smaller soon!)
✨ Ultra High Quality offline NeRF renders & mesh exports
🍕 Creating is as easy as capturing a video on your phone
Available TODAY in Luma iOS App, Luma Web, as well as the Luma API. Fully commercially usable.
Get Started for Free → lumalabs.ai/interactive-scenes
No need for drones, lidar, expensive real estate cameras, and a crew. Record like you're showing the place to a friend, and hit Generate. All on your iPhone! #LumaFlythroughs #phonenodrone
🪄 Flythroughs is built on Luma's 3D NeRF AI and a brand new path generation model that automatically creates smooth dramatic camera moves. And this is just the beginning!
🚀 Get the app: apps.apple.com/us/app/luma-flythroughs/id6450376609
👉🏽 Learn more: lumalabs.ai/flythroughs
#shorts #realestate #realestatetips #realestateagents #realestateinvesting #realestateinvestor #airbnbhosts
No need for drones, lidar, expensive real estate cameras, and a crew. Record like you're showing the place to a friend, and hit Generate. All on your iPhone! #LumaFlythroughs #phonenodrone
🪄 Flythroughs is built on Luma's 3D NeRF AI and a brand new path generation model that automatically creates smooth dramatic camera moves. And this is just the beginning!
🚀 Get the app: apps.apple.com/us/app/luma-flythroughs/id6450376609
👉🏽 Learn more: lumalabs.ai/flythroughs
🔗 lumalabs.ai/ue
🎮 Support for Unreal Engine 5.2
🖥️ Support for macOS (Apple Silicon) & Linux (Ubuntu)
📐 Crop and exposure controls
🏡 New sample scenes to get started right away
Check out the updated plugin, change-log and sample scenes today!
👥 Community lumalabs.ai/discord
⌨️ Join lumalabs.ai/join
💻 Web lumalabs.ai/web
🤳 iOS lumalabs.ai/ios
☁ API lumalabs.ai/luma-api
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 NeRF, not a proxy. Following that, we will bring Luma's NeRF-RT renderer to other tools 🚀
Announcing the next release of Luma NeRF captures: they are clearer, sharper, and even higher res. And they are here. NOW!
http://lumalabs.ai/ios
Available on the AppStore, today! apps.apple.com/us/app/luma-ai/id1615849914
00:00 - Intro
00:08 - Choosing what to scan
00:25 - Start a Guided Capture
00:32 - Setting up the AR guide
01:20 - Loops and layers
01:57 - Ending a scan early
---
00:00 - Intro
00:09 - Why Freeform?
00:26 - Loops and Layers
00:42 - Enabling Freeform Mode
00:45 - Collecting Data
00:55 - Pausing the Scan
01:05 - Understanding the Reticle
01:15 - Goal of Freeform Mode
01:21 - Correct Distance
01:30 - AR Markers
01:39 - Complex/Multiple Objects
01:48 - Capture Coverage
02:02 - Finishing a Capture
02:12 - Improving Background Quality
02:26 - Reflective Materials
02:50 - Shadows
03:18 - Moving Objects
03:34 - Shooting in
03:49 - Lens Glare


