TUTORIAL: Create Rapid Cinematic 3D Renderings with Luma AI

Overview and Audience

In this workshop, we will capture products and objects using our phones, share these with anyone and anywhere, and create rapid cinematic 3d product renderings.
This tutorial is focused on product designers and design teams working in digital marketing and advertising, and we will focus on learning to make 3D product assets.
We will work directly in Luma AI to do this, meaning no specialized hardware or software is required.
You will need a few tools in this workshop, and we will cover those in a moment.

Objective

At the end of this workshop you will be able to do the following

Use Luma AI to capture lifelike 3D photorealistic assets using a phone.
Quickly generate a diverse range of visual 3D renderings based on different prompts, with the ability to iterate rapidly and efficiently.
Re-contextualize 3D assets for better designs and ad campaigns.

About the AI tool(s):

Luma AI is a tool aimed at

Capturing lifelike 3D photorealistic assets using a phone.
Generating 3D assets from text prompts with their Genie tool.
Iterate by generating a diverse range of visual concepts based on different prompts, enabling you to iterate rapidly and efficiently.

Prerequisite

Before the workshop starts you’ll need to do the following.

Create a free account.
Download the free app from the Google or Apple store.

Agenda

Part 1 - Getting Started With Luma AI (30 minutes)

7 steps - 20 minutes
Quiz & Questions - 10 minutes

Part 2 - Create A Series of 3D product renderings using Luma AI (20 minutes)

13 steps - 20 minutes
Quiz & Questions - 10 minutes

Conclusion & Next Steps

Section 1 - Getting Started With Luma AI

Step 1 - Download the app and signup

Download the app for your smartphone from the Apple store.

Before you get started, make sure that your phone settings are optimal:

If using video capture, it is very important that video stablization is off, since it causes the frames to have unstable camera intrinsics; this is particularly important on Android devices. Also avoid using the "HDR video" option on iOS.
Use fixed exposure if possible, although allowing the exposure to vary can be beneficial for outdoor scenes with varying lighting. You can also upload raw images (although it may be hard to fit many in the size limit for now, see "image zips").

Step 2 - Setup your products for capture

To create a capture you need to film a full 360 of an object.

Start by setting up your object:

Place an object in a space where you have room to move around it. For best results, the object or scene should be captured from as many unique viewpoints as possible. Additionally, it is better to move the phone around (in 3D space) rather than rotating it from a stationary position when capturing. Standing in the same place and capturing outwards in a sphere typically does not work well. The guided capture mode is a good option for ensuring sufficient coverage.

Try to use a medium-sized object. For guided captures any object that can be easily viewed from all angles (including the top and bottom) is a good candidate. For free-form captures anything is fair game, although better coverage will yield better results, so larger objects may be challenging to get a fully clean result.
For best results, try to keep the whole object in the frame while scanning. Doing so will provide the app with more information about reflections and object shape, resulting in a more accurate reconstruction.
Currently, the app struggles with complex reflections (e.g., curved mirror-like surfaces), curved transparent objects (e.g., car windows or plastic water bottles), and very large textureless surfaces (e.g. white walls). Most other materials work well.
Start by opening the app and clicking the blue + icon.
Situate your object in the frame.

Step 3 - Capture

Now, you’re ready to capture.

Be a slow turtle, not a fast rabbit. For best results, move the phone slowly and to try to avoid rapid movements, especially rotation, as much as possible.

The app will instruct you to slowly move around the object.
Follow the arrows and vibrations. It’s actually pretty cool.
Note that any movement in the scene during capture may degrade the quality of the final result. For example, tree leaves moving in the wind may result in loss of detail, and people moving around in the background could introduce artifacts. Please be careful not to get fingers / arms / legs into the frame when capturing.

Step 4 - Upload

Once you have taken a full 360 capture, it is time to upload your video. Luma AI will generate a 3D model of that object.

This can take anywhere from 10 minutes to 30 minutes.

Step 5 - Object Mesh

Diffuse object meshes into GLTF, OBJ, or USDZ.

Step 6 - Sharing Permissions

Your capture is private when you create it but you can make it public for the Luma AI community or share it with anyone.

Section 2 - Create 3D product renderings with Luma AI

In this hands-on tutorial, we are going to create quick 3d product videos in Luma AI.

You are a designer working with Golden Age Sunglasses. They are about to launch a great promotion for the winter ‘sunbird’ vacation season. They want to have a series of product videos of sunglasses that are fun and inspiring for their target demographic of older men (and the women who buy sunglasses for them).

Step 1: Preparing to capture

Let me walk you through creating your first Luma Capture using our Guided Capture mode. Medium-sized objects are a good place to start. You'll need to be in a well-lit environment that allows you to freely move around your entire object.

Avoid scenes where your movement will cast shadows on your object. Always start by making sure your camera lenses are smudge free.
Next, open Luma and tap the plus button to begin a guided capture. To define the object, point the crosshairs at the center of the object you want to capture and confirm with a tap.
Move about 90 degrees around the object. Point the crosshairs toward the center of the object and tap again. Don't worry if the box that was created is incorrect. We can tweak it. The dial along the bottom edge controls rotation and the dial along the right edge controls how high above the ground the box is.
You can increase or decrease the size of the box using the blue arrows. Adjust the box until it roughly encloses the object. Move around your object once more making any required adjustments and then tap confirm.

Step 3: Generate your first capture

Now you're ready to capture. You'll see a series of loops projected around your object. These loops visualize where you'll need to position the phone. The aiming reticle along with the lines pointing inwards from the loops help guide your camera to always point inwards towards the center of the scene.
As you slowly move around the loop, Luma will automatically capture data from the most optimal positions. If the reticle turns orange, you might be going too fast or not looking in the right direction.
Adjust your speed and position until it turns blue again. After you successfully capture a loop, it will fade away allowing you to progress to the next layer of the scan until all loops have been completed.
If for any reason you cannot reach 100% coverage, you may still be able to hit the finish button in the top right hand corner if you have collected enough data to create a scene. You will get the best results when you capture data pointing at the center of your object from all required angles.

Step 4: Upload your capture to Luma

All that's left is to upload the data and let Luma do the rest.
This can take 10 to 30 minutes to generate.

Step 5: Try their new Genie AI text to 3d generator

Finally, we need a mascot for our product. A wolf wearing gold aviators seems perfect.

On the Luma AI website, click on the Genie button in the navigation bar.
In the prompt box, enter, ‘a wolf wearing gold aviator sunglasses.’

I like the one in the bottom right.
You can select it and generate more images or choose a high-definition image to download.

Quiz

What is a crucial setting to turn off when using video capture on Android devices?

A. HDR video option

B. Raw image upload

C. Video stabilization

D. Exposure variation

ANSWER: C

What type of object is recommended for guided captures in the Luma AI app?

A. Small object

B. Medium-sized object

C. Textureless surface

D. Large object

ANSWER: B

What is advised to avoid during the capture process to maintain the quality of the final result?

A. Rapid movements

B. Rotation

C. Stationary position

D. Background artifacts

ANSWER: A

What may result in loss of detail during the capture process in the Luma AI app?

A. Exposure variation

B. Curved mirror-like surfaces

C. Stationary position

D. Tree leaves moving in the wind

ANSWER: D

What format can the object meshes be diffused into in the Luma AI app?

A. GLTF, OBJ, or USDZ

B. PDF or DOCX

C. MP4 or AVI

D. JPEG or PNG

ANSWER: A

What is the main focus of this workshop?

A. Creating 2D product designs

B. Learning to use traditional photography techniques

C. Developing specialized hardware for 3D rendering

D. Capturing lifelike 3D photorealistic assets using a phone

ANSWER: D

Who is the target audience for this workshop?

A. 3D animation enthusiasts

B. Professional photographers

C. Product designers and design teams in digital marketing and advertising

D. Software developers

ANSWER: C

What is the objective of using Luma AI in this workshop?

A. Capturing lifelike 3D photorealistic assets using a phone

B. Editing photos

C. Developing mobile games

D. Creating 2D animations

ANSWER: A

What do participants need to do before the workshop starts?

A. Create a free account and download the free app from the Google or Apple store

B. Enroll in a photography course

C. Install Luma AI software on their computers

D. Purchase specialized hardware for 3D rendering

ANSWER: A

What is the purpose of Luma AI's Genie tool?

A. Developing virtual reality experiences

B. Creating 2D pixel art

C. Generating 3D assets from text prompts

D. Editing videos

ANSWER: C

Conclusion & Next Steps

Here is a recap of what you can now achieve in your day-to-day work using Luma AI:

You can use Luma AI to generate 3D images using camera capture.
You can quickly generate a diverse range of visual concepts based on different prompts, with the ability to iterate rapidly and efficiently.
You can port the results into Illustrator or your preferred image editing tool, and adjust text, colors, and whatever else you need to do from there.
Finally, you can create fantastic ad campaigns with these images in an remarkably fast amount of time.

Homework:

Use what you just learned to create a series of 3D renderings for your company/ favorite client where you create 5 different renderings.

List of References and Links

We used information supplied by Luma AI to write this tutorial.