What is the visual output of this workflow?

Outputs include New Image frames, a WORLD block, a New 3D Block, and SCENE 1 video sequence.

Which inputs drive the scene generation?

Inputs include the Desert/world block, prompts, frame images, and 3D assets used to build the final scene.

Can I modify the frames or prompts during the process?

Yes. You can adjust prompts and regenerates frames (Frame 1–4) to refine the scene before finalizing the video.

How are 3D assets integrated into the scene?

3D blocks derived from image inputs are incorporated into the scene to enrich the final render and perspective.

What platforms or tools are used in this workflow?

The workflow uses a mix of image and video blocks, 3D blocks, and world blocks from compatible AI tools to produce the final scene.

Worlds to Scenes: Gaussian Splatting AI Workflow Template

What's newExplore the latest Raelume updatesRead update

Raelume

Preview canvas

Workflow preview

Explore the canvas

Open full screen

Drag to explore · Use + / − to zoom

100%

Overview

What this workflow unlocks

A concrete workflow example that converts world blocks using Gaussian Splatting into a sequence of scenes. Start from a world block, generate prompts and images, assemble frames, and produce a 3D scene and a video scene sequence. The flow maps inputs (world blocks, prompts, frames) to outputs (new images, a 3D block, and a scene video), illustrating a production AI pipeline for scene creation.

Best for

Where this workflow makes the biggest difference.

Industry: visual effects and animation

Role: 3D artists and VFX supervisors

Use case: world-building to scene rendering

Use case: generating scene sequences from world blocks

Use case: creating 3D assets from image frames

Use case: producing scene videos from prompts

Workflow

From first input to final result

Define the world and initial prompts

Start with a world block (Gaussian Splatting) and an initial prompt to set the scene concept.

Iterate prompts and generate frames

Create new prompt blocks and generate Frame 1–4 images to explore the scene from multiple angles.

Create 3D asset from images

Convert the best frames or combined inputs into a 3D car or other assets using a 3D block.

Assemble into a scene sequence

Bring together images, 3D assets, and a video sequence to form SCENE 1 and related clips.

Produce final scene video

Add a New Video Block and a video-sequencer to render the final scene as an output video.

Models & tools

The models and tools behind this workflow

Everything this template uses, already connected and ready to run.

Nano Banana Pro
Google
model
Marble 1.1
Marble
model
Flux 2 Max
Flux
model
Hunyuan3D v3
Hunyuan3D
model
Seedance 2 Reference
ByteDance
model
Z-Image Turbo
Alibaba
model
Nano Banana 2
Google
model

FAQ

Questions, answered.

More templates

Keep exploring

Continue with another reusable creative workflow.

View library

World Building

World Castle Sequence

An example workflow to use gaussian splatting worlds to scenes

73 views · 9 remixes2

Storyboarding

Multi Angle Photoshoot

Start from one picture, generate multiple shot angles

16 views · 0 remixes0

Product Content

Shopify Product Multiview

Generates a realistic Shopify product hero and multi-view images by following a guided flow: define direction prompts, produce shot prompts, render multiple shot images, and finalize for the lifestyle and hero directions.

48 views · 6 remixes1

Image Editing

Mock Up Generator

Apply any screenshots to custom mockups

14 views · 0 remixes0

Product Content

Product Integration

Integrate any product on any scene

24 views · 3 remixes1

Audio Production

Film Score Generator

Create film scores from one prompt to multiple tracks

14 views · 1 remixes1