We read every Runway Gen-3 / 4 prompt guide so you don't have to.

What Runway Gen-3 / 4 actually rewards

We pulled this from Runway's official guidance and what works in production. The short version:

• →Describe motion (subject + camera) clearly.
• →One core action per prompt.
• →Reinforce key ideas.
• →For image-to-video, describe ONLY what changes — don't re-describe the input image.
• →For character consistency, upload reference image rather than re-describe.

Common mistakes we fix automatically

• Avoid
  NEVER use negative phrasing — produces opposite. Convert 'no camera movement' → 'static shot'.
• Avoid
  Don't pile multiple transformations into one prompt.

Frequently asked questions

Which versions of Runway Gen-3 / 4 does this support?

We support gen-3-alpha, gen-3-alpha-turbo, gen-4, gen-4-turbo. We apply the prompt patterns Runway recommends for each, so the rewrite is tuned to the version you're using.

Is my prompt stored or used for training?

No. Prompts are sent to the rewriter, scored, returned, and discarded. We don't train on them and we don't keep them around.

Do I need to know prompt engineering to use this?

Nope. That's the point. Paste what you have, click Rewrite, get back a version that follows Runway's official guidance.

What makes this different from Runway Gen-3 / 4's own "improve prompt" feature?

Built-in optimizers use the model's own preferences. Ours is built on Runway's official documentation and patterns that consistently produce better results in production. We keep rewrites inside the length window Runway Gen-3 / 4 responds best to.