Back to prompts

Demo — inputs & output

Ref2VA15s

Prompt structure inspired by Inspired by fal.ai H3 Guide

Multi-Element Scene Editing

Batch localized edits in one pass — props, furniture, effects, and set dressing.

Ref2VA15s16:9editmulti-element

Who this is for

Advanced edit demos showing instruction adherence.

How this prompt is built

Read this first — once you see the pattern, you can write your own without starting from zero.

  1. Edit list

    Enumerated substitutions — model follows literally.

  2. Constraint

    Preserve unmentioned elements.

Adapt it for your project

  • Swap prop list for your scene.
  • Fewer edits for simpler tests.

Where people mess up

  • Vague combine edits — model drifts.
  • Missing preserve clause.

Full prompt (copy & edit)

In the reference video: replace the newspaper with a green hardcover book; replace the chair with a red sofa; remove the subject's sunglasses and reveal a clear face; remove the burning-car effect and restore the vehicle to normal; replace the photograph taken from the coat with a small black notebook; and add a tree on the left side of frame. Keep camera motion and all unlisted elements unchanged.

New to Ref2VA? Read the MiniMax H3 Ref2VA prompt guide

Related prompts

REF2VA10s

Cat-to-Dog Replacement

Video editing with one-line substitution prompt

Prompt structure

Replace the cat in the video with a dog. Keep everything else in the shot stable: background, c…

REF2VA15s

Product, Sign & Dialogue Replacement

Complex multi-swap edit on single clip

Prompt structure

In the reference video, replace the canned drink shown at the beginning with Coca-Cola. Change …

REF2VA15s2× Picture

Subject & Wardrobe Replacement

Two-image + video composite edit

Prompt structure

Replace the child at the back of Video 1 with the golden retriever from @image1. Replace the kh…