Tutorial

The Art of In-Context Generation

Keep your characters consistent and your styles uniform using Reference Images.

One of the hardest problems in AI video generation is "subject consistency". You generate a cool astronaut in scene 1, but in scene 2, they have a different helmet and suit.

What is In-Context Generation?

Borrowing from LLM terminology, "In-Context" means providing examples (context) to the model at inference time. For UniVideo, this context comes in the form of Reference Images.

Instead of describing "a futuristic soldier" in text and hoping for the best, you upload an image of the specific soldier you want. UniVideo's MLLM "sees" this image, extracts the features (armor design, color palette, face), and uses them as a hard constraint for the generation process.

How to Use It

1

Upload Reference

In the UniVideo dashboard, select the "In-Context" tab. Drag and drop your character sheet nor reference frame.

2

Define the Action

Type your prompt: "The character is running through a forest." The model knows "The character" refers to your image.

3

Generate

UniVideo generates the motion while locking onto the visual identity of the reference.

Use Cases

Try it with your own images

Upload a photo and make it move.

Open Studio