
While 3D is the lifeblood of many digital artists and animators, we also embrace the beauty of 2D with backgrounds, cutouts and camera placement to provide a world much more complex than we would be able to do using only 3D assets. As we all know, the problem with 3D assets, even those that are optimized, is that they can bring our computers to a crawl causing skipped frames and timing issues that can be missed until they show up in the final render needing more work to correct.
This is problematic for all 3D software applications as the amount of computational overhead for 3D objects is a common problem and has a direct impact on how smoothly our computer can handle the load and not start having hiccups.
Storytelling
Experienced animators know how to work with 2D assets, and a lot of that experience involves layout and camera placement. I’ve said many times that the camera is the animator’s friend in that it can be used to show or not show certain parts of an animation that may not be up to par or even necessary for the story to advance.
In science fiction, particularly space travel, the interiors of cockpits and spaceships of various sorts can be very simple in some cases, but most likely they are filled with eye candy to make the viewer go “Wow” for a few seconds when viewing a scene for the first time. This is a delicate balancing act between wowing the viewer while not distracting them from the story.
This is the point at which I naggingly remind everyone that advancing the story is the most important task in a production. From a one-person operation to a huge team, advancing and enhancing the story with visuals can make or break the production in the eyes of the viewer. Too much eye candy and the focus on the story can be lost but the right amount, at the right time, in the right scene will not only enhance the scene but also draw in the viewer to see all the cool stuff you have put together.
Easy First Scenario – Hallway or Corridor
For our first scenario we’ll look at a very simple use of an image with a character to create a compelling scene. This can involve dialog or another character but, in this instance, we are just going to walk down a 2D hallway with a 3D character.
This one is easy as you just dump a 2D image into the workspace as a background. iClone then provides the perspective or you can force the perspective with scaling to make the character appear to be walking down a hallway. This provides an opportunity for adding eye candy and giving the viewer a glimpse of your sci-fi world.
AI Prompt Focus
Midjourney Prompt: “frontal view of long bulkhead filled with Controls”

When generating the background corridor image, you will want to focus on a prompt that will show the corridor facing forward or at a slight angle. The more forward facing the better.
In this instance I used Midjourney with a very simple prompt of “frontal view of long bulkhead filled with Controls” as referenced above. You may have to experiment with the prompt, but you’ll notice I didn’t use corridor or hallway even though they would be just as appropriate so play around with prompt.
When you’ve used tools like Midjourney enough you should start to get a feel of how it reacts to certain prompts to achieve desired results. As you will see, I rarely use extensive prompts as I usually start with a simple prompt in most cases. There is nothing wrong with a verbose prompt except for those occasional times they start fouling up parts of the image.
Load your character and rotate it to where it faces the opposite direction then pull it back to where it fills most of the screen.

You can turn on the grid initially to get your bearings and line the character up in the walkway of the image if needed. It’s OK if you can’t see the character’s head or legs at this point. iClone will handle the perspective shift.
Just follow the tutorial below to see how simple integrating 2D and 3D can be for a stroll down an ornate hallway, factory catwalk or corridor.
Blending a solid color overlay with low opacity is a simply way to take the edge off of the difference in the lighting and appearance of the background versus the 3D assets and 3D lighting. Add an Image Overlay of a solid color that matches or enhances the scene in this case I used blue to blend and cool the scene. Cover the entire scene with Image Overlay until the overlay is all you can see then go into the texture tab and lower the opacity to “blend” the 3D assets with 2D assets. This is generally 40 percent down to as low as 10 percent, but experimentation is encouraged.
Second Scenario – Space Transit

Midjourney Prompt: “command bridge of a futuristic starship with huge forward screens and brightly lit control panels”
TIP: Sometimes you may need to add “–no seats, benches” (and variations) to get a clean cockpit so you can use your own 3D seats.
Let’s take a look at a simple space transit scene that could serve as an establishing shot or the start of a scene. In this scenario, we will be looking at the inside of a starship cockpit with crew members at consoles while the ship speeds through space. We could make the cockpit simple enough to populate with 3D consoles and props but let’s say the script calls for an impactful image that shows off technology as we might expect on such a ship.
In this case there is no dialog so we can really dig in on the eye candy, using an ai-generated image instead of 3D consoles or a 3D cockpit. The only 3D assets in the scene are the characters, their seats and the particle FX.
The scene looks good, takes little time to set up and can be one of those scenes that sticks in the mind of the viewer due to your choice of image.
Third Scenario – Sci-Fi Base

Midjourney Prompt: “futuristic cyberpunk spaceport landing pad”
We are going to get a bit more ambitious with this scenario with it being a more complex scene using “layers” of AI imagery cut out from the original image. I use the term “layers” loosely here as iClone doesn’t have that type of layer, but we just load our cut-out images into the 3D workspace and re-create the original image with space between the cutout images.
The first two scenarios relied on a fixed background, but this one will rely on image planes and image overlays.
Quick Recap
For this you will need an image editor like Photoshop used in this example and an ai-image generator if one is not built into the editor. A main image is generated then we go into our image editor to mask or cut out the parts of the image we want to separate into layers. If you choose to cut out an object like a large rock or boulder because you want a character to hide behind that object you then need to fill that hole you cut out using a marquee and generative AI as shown in the following tutorial.
If we cut out the foreground of an image to have separation between foreground and background, we will need to fill that hole in the background too. Eventually we will have a background with foreground layers stacked in front of each other for spatial and visual separation. This will help to blend the 2D images with 3D assets.
Overview
- Generate Image
- Cutout Prominent Features
- Use AI–generation to fill up those cut out holes in the background
- Arrange the cut outs so they reproduce the original image with separation between them.
- Add what 3D assets and VFX are necessary and animate!
If you are new to this, don’t panic. This is all demonstrated in the tutorial below. It’s another example of a technique that sounds hard but is in fact very simple to execute once you see what is going on.
Summary
AI-generated images are providing another avenue of visualization that many small studios and home animators have not had access to.
Camera work with 2D imagery can be very tricky for beginners. You soon find out that there is little you can do other than zoom in and then you have to be judicious with it. Camera and imagery can coexist once you understand the concept of using an image plane instead of the background with the camera attached to the image plane, so it moves with it.
That, however, is for another article at another time as we have already covered a lot of ground if you are just starting on your animation journey. Basically, for AI-generated cutouts you need to learn to use the marquee, lasso and related tools in your photo editor and as you saw with the above tutorial sometimes a photo editor can do a good job of separating elements from an image without a lot of interaction from the user.

MD McCallum – WarLord
Digital Artist MD “Mike” McCallum, aka WarLord, is a longtime iClone user. Having authored free tutorials for iClone in its early years and selected to write the iClone Beginners Guide from Packt Publishing in 2011, he was fortunate enough to meet and exchange tricks and tips with users from all over the world and loves to share this information with other users. He has authored hundreds of articles on iClone and digital art in general while reviewing some of the most popular software and hardware in the world. He has been published in many of the leading 3D online and print magazines while staying true to his biggest passion, 3D animation. For more information click here.













































































































































