Scenes

Scenes are the fundamental units of your video project in Dal Nulla. Represented as nodes in the Graph Editor, each scene generates a video clip based on your text prompt and connected references.

Inspector Controls

When you select a Scene Node, the Inspector Panel on the right allows you to fine-tune the generation:

1. Prompt

Input: A text area to describe the action, style, and content of the video scene.
Linked Prompt: If a Text Node is connected, its content appears here. You can Detach it to edit the prompt independently or Expand the editor for more space.

2. Negative Prompt

Input: Specify what you don’t want to see in the video (e.g., “blur”, “distortion”, “text”).

3. Generation Settings

Model: Choose between Pro (higher quality) and Fast (quicker generation). Note: The ‘Fast’ model may not support reference images.
Duration: Select the length of the video clip (e.g., 2s, 4s).
Resolution: Set the output resolution (720p, 1080p).
Aspect Ratio: Define the video’s aspect ratio (16:9, 9:16, etc.).

4. Media Inputs (Modes)

Use the toggle to switch between two ways of controlling visuals:

Refs (References):
- Allows connecting up to 3 Reference Images.
- The AI blends these images to influence the style and content.
Frames:
- Allows setting a specific Start Frame and/or End Frame.
- The AI animates the transition between these exact images.
- Note: Switching to Frames mode limits you to 2 inputs.

5. Context Settings

Use Project Global Context: A checkbox to opt-in/out of the project’s global text and reference nodes. Uncheck this if you want the scene to be completely independent of the rest of the story.

6. Version History

History List: Every time you generate a scene, the previous version is saved here.
Restore: Click a history item to revert the scene to that specific video and prompt.

Actions

Generate Scene: Starts the AI video generation process.
Download Video: Saves the current video clip to your device.
Delete Scene: Removes the node from the canvas.