AI video prompt enhancer

Paste a scene draft into Prompt Lab. Choose your video model to refine the action, framing and camera movement.

Refine my prompt
Black platform boots break through a wooden library desk, sending splinters to either side.
Scene draftA girl drops through a skylight and breaks a wooden desk.

Refine your video prompt

Which video model will you use?

Choose the model you plan to use. Switching models keeps your draft.

0 / 5000 characters
Sign in to refine your promptYour text and model are kept. Submit when you return after signing in.

How do you describe the same shot more clearly?

This example adds framing and the order of actions. The actual refinement depends on the model.

Original draft
A girl drops through a skylight and breaks a wooden desk.
Refinement example
Look up from below the skylight and track her feet as she falls. Just before impact, cut to a close-up at tabletop height. Her platform boots hit the desk, the wood splits, and splinters fly to either side.

Frequently Asked Questions

Prompts and models
What changes after refinement?

Original: Outside a convenience store on a rainy night, a delivery rider stops, removes their helmet and checks the last order on their phone.

Refinement turns the scene into model-oriented camera and action instructions, such as framing, camera movement and action order. This is an illustration; the selected model produces the actual result and may add lighting, sound or other details.

Which model should I choose?

Choose Seedance 2.5 for a Seedance video prompt, or MiniMax H3 for a MiniMax video prompt. Switching models does not submit a request or use your allowance. MiniMax uses its native IR service; Seedance uses the existing prompt optimization rules.

Will the result use my original language?

Results keep the model’s native format and may use a different language. MiniMax IR may return structured English descriptions. Both refiners may add camera, lighting, sound or other details. Review the complete result before use. Your original text remains available for editing.

Does Prompt Lab generate videos or create projects?

Prompt Lab refines text only. It does not upload media, generate images or videos, or create projects. Copy the complete prompt when it is ready. The next-step button opens the existing storyboard image composer, where you prepare and submit a separate request.

Usage and credits
How many free refinements do I get each day?

Sign in to refine prompts. Members get 3 free refinements per day; Spark gets 10; Studio gets 20; Director gets 50. Both models share the allowance. It resets at 00:00 UTC (08:00 Taipei).

What happens when I run out, or a request fails?

After the free allowance, members confirm 1 credit for each request. Credits are consumed only after the complete result succeeds. Cancelling the confirmation submits nothing; a confirmed failure releases the reservation. An uncertain result keeps its reservation while the same request is checked. Signing in or returning from credit purchase preserves your draft and model; you submit it yourself.

View all frequently asked questions