# Edit Video With an AI Prompt

> To edit video with an AI prompt, upload a clip to Kenerate Genjutsu, choose Free edit and type the change — "make it a snowy winter night" or "replace the woman with the character from @image1". Prompts run up to 1,500 characters. Everything the prompt doesn't mention — people, motion, camera, timing — is told to stay as filmed.

URL: https://kenerateai.com/edit-video-with-ai-prompt
Publisher: Kenerate AI (https://kenerateai.com)
Last updated: 3 October 2026

## Key facts
- Mode: Free edit (prompt required)
- Prompt: Up to 1,500 characters
- References: @image1… up to 10, or 30 on Seedance 2.5
- Kept: Everything not mentioned
- Enhance prompt: Kenerate tiers
- Not included: Cutting, trimming, captions
- Kenerate Genjutsu (Kenerate): Clip 2–15 s + up to 10 references → 480p, 720p or 1080p · ~2–4 min. Fast prompt edits on short clips, with Enhance prompt for one-line instructions.
- Kenerate Genjutsu Pro (Kenerate): Clip 2–15 s + up to 10 references → 480p, 720p or 1080p · ~3–6 min. Detailed prompts where texture and edges matter, also with Enhance prompt.
- Seedance 2.5 (ByteDance): Clip 4–30 s + up to 30 references → 480p to 4K · ~4–8 min. Long, precise prompts on clips up to 30 s, many references, 4K.

## Steps
1. Upload the clip — MP4, MOV, WebM or M4V up to about 100 MB; 2–15 s, or 4–30 s on Seedance 2.5.
2. Choose Free edit — The open mode: any change, in your own words. A prompt is required here.
3. Add references if a look must match — A character, a product, a place — each becomes @image1, @image2 in the order added.
4. Write the change — Verb + target + new look + what to keep: "Turn the sky stormy and purple, keep the people and the lighting on them."
5. Compare, refine, finish — Watch the synced compare view, rerun with a sharper sentence if needed, then hand off to Add subtitles or Upscale to 4K.

## In depth

### Two kinds of text-based video editing
Transcript editing treats the video as words: delete a sentence from the transcript and the matching footage is cut. Prompt editing treats the video as a scene: describe a change and the footage is re-rendered with it. They solve different problems — pacing versus content — and Genjutsu is only the second. It returns your clip at the same length, with the same cuts, changed inside the frame.

### Anatomy of an edit prompt
Behind every run, Genjutsu adds its own rules: keep everything the instruction doesn't mention, avoid flicker and drifting identities, add no text or watermarks. Your prompt only needs the change.
- Verb: replace, turn, make, move, add.
- Target: which person, object or area.
- New look: words, or "from @image1".
- Boundary: what must stay the same.
- Optional mood: time of day, weather, light.

### Combining edits in one prompt
Free edit can do two jobs at once, as in the neon alley demo: a new lead from @image1 and a new place from @image2 in one sentence. Combining saves a run but gives the engine more to balance; when one part comes out weaker, rerun just that part in its own mode — Replace character or Change background — on the result.

## FAQ
Q: What is text-based video editing?
A: The phrase has two meanings. In transcript editors, it means cutting a video by deleting words from its transcript. In generative tools like Genjutsu, it means changing what's in the frame by describing the edit in text. Genjutsu does the second: it re-renders the clip with your change and keeps the motion, camera and timing — it doesn't cut or rearrange footage.

Q: What can a prompt change in my video?
A: Almost anything you can see: the character, an object, an outfit, the location, the weather, the season or time of day, or several of these at once. Free edit is the open mode for this; the other four modes — Replace character, Swap object, Change outfit and Change background — are presets for the common cases, with a built-in instruction behind each.

Q: How do @image mentions work?
A: Each reference image you add is numbered in order, so the first is @image1, the second @image2. Writing "the character from @image1" tells the engine which picture to copy. Mentions are converted into "reference image 1" before the engine reads them, and a mention past the end of your list is dropped instead of guessed.

Q: How long can my prompt be?
A: Up to 1,500 characters. Short, precise prompts usually work best: a verb, the target and the new look, plus what to keep if it's at risk. On Kenerate Genjutsu and Genjutsu Pro, the Enhance prompt toggle can expand a short instruction into a fuller one for you; Seedance 2.5 reads your words as written.

Q: Can a prompt trim, cut or caption my video?
A: No. Genjutsu changes what appears in the frame and returns the clip at its own length; it doesn't trim, cut, reorder or add captions. For captions, use the Add subtitles hand-off after the result. For assembling several clips, use a timeline editor and bring each finished clip into it.

Q: Why did the edit change more than I asked?
A: Usually because the target was ambiguous or the change implied more — "make it night" affects the light on everyone. Name the target precisely, add "keep the faces and the outfits the same" when they matter, and split big changes into two runs. Genjutsu Pro and Seedance 2.5 are the tiers built for cleaner, more faithful results.

Q: Is it OK to edit any video with a prompt?
A: Only footage you own or are licensed to use, and only with the consent of the people in it. Don't prompt real people into situations that never happened, don't impersonate anyone and never use celebrities. Label AI-edited clips when you share them, especially when they could be mistaken for real events.

## Related pages
- AI Video Editor: https://kenerateai.com/ai-video-editor
- Video to video AI: https://kenerateai.com/video-to-video-ai
- Runway Aleph alternative: https://kenerateai.com/runway-aleph-alternative
- Swap an object in a video: https://kenerateai.com/swap-object-in-video
- Video background changer: https://kenerateai.com/video-background-changer

## Sources
- Kenerate Genjutsu (video editor): https://kenerateai.com/app/genjutsu