OpenArt: Compose a scene using saved library assets

OpenArt Try it →Watch full video →Roboverse · Apr 2026

Demo summary

The user tags multiple saved assets (character, prop, environment, style) in the reference panel to generate a fully consistent composite image.

Step-by-step

Open the reference panel
Tag the four saved assets (character, prop, environment, and style) from your library
Paste your prompt into the generation field
Click Generate

Watch out for

Assets must be pre-built and saved to your library before they can be tagged for composition

Highlights

“That's the kind of result that would normally take hours of trial and error to get right. But here, it only took about 2 minutes because everything was already built and saved in one place.”

All demos from “How to Use OpenArt Better than 99% of People”

1:060:42Compare image generation models in OpenArtThe user demonstrates the visual differences between Nano Banana 2, Cedream 4.5, and Cling 3 Omni models using the same text prompt within OpenArt.OpenArt· AI Image Generator
2:490:27Create a consistent character from text in OpenArtThe video shows how to use the 'Describe your character' feature and Nano Banana Pro model to generate and save a reusable character named Duncan.OpenArt· AI Person Generator
3:190:48Save reusable objects and styles in OpenArtThe demonstrator uploads images of a pocket watch, an alleyway, and a specific aesthetic to save them as reusable 'Object', 'Background', and 'Style' assets in the library.OpenArt· AI Image Generator
4:070:20Compose a scene using saved library assetsCurrentThe user tags multiple saved assets (character, prop, environment, style) in the reference panel to generate a fully consistent composite image.OpenArt· AI Image Combiner
5:270:20Generate video from text with Cling 3A demonstration of the text-to-video workflow using the Cling 3 model to generate a 5-second 1080p cinematic clip.OpenArt· Text to Video
6:020:33Image-to-video generation with Vidu 3.1The user demonstrates how to use a previously generated image as a foundation for video, using the Vidu 3.1 model to animate specific motions.OpenArt· Image to Video
6:380:20Extend video clips using end-frame referencesThe video shows how to take the last frame of a generated clip and use it as the starting point for a new generation to extend the scene.OpenArt· AI Video Editor
Watch “How to Use OpenArt Better than 99% of People” →

AI Image Combiner

14:271:32Place character in a real-world photoThe creator demonstrates the 'place character in image' feature to insert the AI influencer into an uploaded photo of a luxury retail store.Roboverse
10:200:55Multi-subject consistency in movie postersThe video shows the process of dropping 14 different reference images into OpenArt and using Nano Banana 2 to combine them into a single, consistent animated movie poster.Dan Kieft
9:020:58Combine character and background referencesThe tutorial shows how to use the Nano Banana model to composite a character reference into a specific background image.AI Video School
4:070:20Compose a scene using saved library assetsCurrentThe user tags multiple saved assets (character, prop, environment, style) in the reference panel to generate a fully consistent composite image.Roboverse
5:310:43Consistent objects and backgroundsA walkthrough of saving specific objects and backgrounds to a library and then combining them with a saved character to generate a consistent scene.Isa does AI