For the complete documentation index, see llms.txt. This page is also available as Markdown.

Input Controls

An overview of all input controls in Qolaba's Video Generation workspace — prompt, Magic Prompt, reference media uploads, and keywords.

The Input Controls panel sits on the left side of the Video Generation workspace. This is where you define everything that goes into a generation — your prompt, reference media, and keywords. Together these inputs determine the scene, motion, style, and visual direction of your generated video.


What's in the Input Controls Panel

Control
What It Does

Prompt

Describes the scene, subject, motion, and environment in natural language

Magic Prompt

AI-enhanced version of your prompt for better generation results

Initial Image

Sets the first frame of the video

Last Frame Image

Sets the final frame — model generates the motion between both frames

Reference Files

Uploads image, video, or audio as a creative reference (model dependent)

Keywords

Structured controls for motion, focus, lens, lighting, enhancement, and negative exclusions


How Inputs Work Together

Your prompt is the foundation of every generation. Keywords refine and extend what the prompt describes — adding precise cinematic, motion, and stylistic direction that natural language alone cannot reliably produce. Reference media anchors the generation visually, giving the model a concrete starting point, ending point, or stylistic reference to work from.

For best results, combine all three:

  • A clear, descriptive prompt for scene and narrative direction

  • Relevant keywords for motion style, lens type, and visual quality

  • Reference media when visual consistency with existing assets matters


What's in This Section

Last updated