How to Use RIFE in Gemini CLI
RIFE generates intermediate frames to smooth motion in existing video. Use it for a finishing pass on camera pans, product footage, or animation, and review scene cuts for smearing.
Prompts to try with RIFE in Gemini CLI
Copy an example into Gemini CLI, or ask in your own words.
Use RIFE on the product rotation video in this project's assets. Process a preview first and prepare a comparison with the original.
Find the camera pan in this project's demo video and use RIFE to interpolate it. Keep the original and processed clips available for review.
Use RIFE on the edited walkthrough video in this repository with scene detection enabled. Prepare previews around each cut so I can inspect smearing.
Use RIFE to create a motion preview from the project's rendered animation. Include the section with the most complex movement in the comparison.
Use RIFE on the project's promotional video twice, with scene detection enabled and disabled. Prepare a comparison around the cuts and the lighting change.
How to set up RIFE in Gemini CLI
Pick the way that suits you. Each takes about two minutes.
Use Spiral's MCP server
- Add the server
Or add it to ~/.gemini/settings.json yourself:
gemini mcp add --scope user --transport http spiral https://api.spiral.ai/mcp
- Sign in
Start gemini and run:
/mcp auth spiral
- Check it
In Gemini CLI, run /mcp. From your shell:
gemini mcp list
Use the Spiral skill
- Send Gemini CLI this message
Your agent reads Spiral's skill and sets itself up.
set up https://spiral.ai/SKILL.md
- Sign in or paste a key
Approve Spiral in the browser, or give the agent a key from the console.
Use the Spiral CLI
- Install and sign in
Installs the Spiral CLI, signs you in and adds its skill to your coding agents.
npx -y spiral-cli@latest init
Call the Spiral API
- Create an API key
In the console, under API keys.
- Run RIFE
One request; the result comes back by polling or a webhook.
curl https://api.spiral.ai/v1/runs \ -H "Authorization: Bearer $SPIRAL_API_KEY" \ -H "Content-Type: application/json" \ -H "Idempotency-Key: $(uuidgen)" \ -d '{ "provider": "fal", "model": "fal-ai/rife/video", "input": { "video_url": "https://storage.googleapis.com/falserverless/example_inputs/interpolation-video-input.mp4" } }'
Then paste one of the prompts above: Gemini CLI finds RIFE on Spiral, shows the price and runs it.
RIFE providers and prices
Spiral runs RIFE through fal. Open a card for today's price, with every fee included.
Settings you can ask for
RIFE works from your video URL. Ask Gemini CLI for any of these in your prompt.
| Setting | Allowed values | Default | Description |
|---|---|---|---|
| Number of frames | 1 to 4 | 1 | The number of frames to generate between the input video frames. |
| Use scene detection | on or off | off | If True, the input video will be split into scenes before interpolation. This removes smear frames between scenes, but can result in false positives if the scene detection is not accurate. If False, the entire video will be treated as a single scene. |
| Use calculated FPS | on or off | on | If True, the function will use the calculated FPS of the input video multiplied by the number of frames to determine the output FPS. If False, the passed FPS will be used. |
| Frames per second | 1 to 60 | 8 | Frames per second for the output video. Only applicable if use_calculated_fps is False. |
| Loop | on or off | off | If True, the final frame will be looped back to the first frame to create a seamless loop. If False, the final frame will not loop back. |
Every API field of RIFE · Video Interpolation is on its tool page: open its card above.
What can you do with RIFE in Gemini CLI?
Turn existing project videos into smoother motion previews with RIFE. Have your coding agent select representative sections and prepare comparisons before replacing a video asset.
Product rotation previews
Interpolate an existing turntable video, then compare the product's outline during rotation before using the processed version.
Camera pan cleanup
Test interpolation on a continuous camera pan and compare its motion with the original at normal playback speed.
Animation review
Create a smoother preview from an existing animation clip. Review the result against the original timing before choosing an export.
Generated video finishing
Try an interpolation pass on an existing generated clip. Compare the busiest motion before deciding whether to keep the processed version.
Edited montage review
Process a montage with scene detection, then inspect each cut for smearing and incorrectly detected scene changes.
Rendered walkthrough previews
Test smoother motion on an existing architectural walkthrough. Compare camera movement through doorways and around corners before accepting the result.
More on RIFE and Gemini CLI
Overview
RIFE in other agents
Questions about RIFE in Gemini CLI
Can Gemini CLI use RIFE?
Yes. Add Spiral to Gemini CLI as an MCP server, and Gemini CLI can find and run RIFE like any built-in tool.
How much does RIFE cost in Gemini CLI?
Up to $0.1014 per run at the default inputs for 60 seconds of input. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your Gemini CLI plan is separate.
Do I need a fal account to use RIFE in Gemini CLI?
No. Spiral runs RIFE on its own fal account. You sign in to Spiral once and never paste a key.
How long does it take to set up RIFE in Gemini CLI?
About two minutes: add the server, then sign in, then check it.
Does Gemini CLI wait while RIFE runs?
RIFE runs in the background. Gemini CLI starts the run, checks on it and gives you the video when it's ready.
What does RIFE do to a video?
RIFE generates frames between existing frames. Use it when you want smoother motion in footage you already have.
What should I tell my agent when using RIFE?
Identify the source video and the motion you want to smooth, such as a camera pan or product rotation. Ask for a preview of that section before processing the complete edit.
How should I handle scene cuts?
Try scene detection when your video contains cuts to reduce smearing between shots. Review the result because scene detection can also flag cuts incorrectly.
What footage needs the closest review?
Start with complex motion and changes in lighting, which the RIFE paper identifies as challenges for frame interpolation. Compare those sections with the original before accepting the result.
How should I evaluate whether interpolation helped?
Compare the original and processed video at normal playback speed, then inspect the most difficult motion. For edited footage, include the frames around every scene cut in your review.
Start using RIFE in Gemini CLI
One Spiral account for every tool your agent needs. No subscription; you pay per run.
Paste this into Gemini CLI:
set up https://spiral.ai/SKILL.md


