video-to-video
Luma Modify Video transforms and restyles existing videos with AI-powered modifications, enabling style changes, visual enhancements, and creative edits. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
Idle
Your request will cost $0.095 per run.
For $1 you can run this model approximately 10 times.
One more thing::
ExamplesView all
README
Luma Modify Video
Luma Modify Video is an AI-powered video transformation model that restyles and modifies existing videos using text prompts. Choose from multiple transformation modes — from subtle enhancements to dramatic reimaginations — and let AI transform your footage into something new.
Why Choose This?
-
Flexible transformation modes 9 different modes across 3 categories (Adhere, Flex, Reimagine) to control how closely the output follows your source video.
-
Text-guided modifications Use natural language prompts to guide the video transformation with built-in Prompt Enhancer support.
-
First frame control Optionally provide a modified first frame to guide the entire video transformation style.
-
High-quality output Produces smooth, coherent video modifications with consistent styling throughout.
-
Fast processing Optimized for quick turnaround times.
Parameters
| Parameter | Required | Description |
|---|---|---|
| video | Yes | Source video to modify (max 100MB, max 30 seconds) |
| prompt | No | Text instruction to guide how the video should be modified |
| mode | No | Transformation intensity (default: adhere_1) |
| first_frame | No | Modified first frame image to guide the video transformation |
Mode Options
- Adhere (1-3) — Very close to original, ideal for subtle enhancements and minor adjustments
- Flex (1-3) — Allows stylistic changes while keeping recognizable elements from the source
- Reimagine (1-3) — Loosely follows the source, best for dramatic or transformative changes
Higher numbers within each category indicate stronger effect intensity.
How to Use
- Upload your video — drag and drop or paste a public URL (max 30 seconds, max 100MB).
- Write your prompt — describe the desired transformation or style.
- Select mode — choose from adhere, flex, or reimagine based on how much change you want.
- Add first frame (optional) — upload a modified first frame to guide the overall style.
- Run — submit and download the transformed video.
Pricing
Per-5-second billing with a 5-second minimum.
| Video Duration | Cost |
|---|---|
| Up to 5s | $0.095 |
| 10s | $0.19 |
| 15s | $0.285 |
| 20s | $0.38 |
| 30s (max) | $0.57 |
Billing Rules
- Minimum charge: 5 seconds ($0.095)
- Rate: $0.019 per second ($0.095 per 5 seconds)
- Maximum video length: 30 seconds
Best Use Cases
- Style Transfer — Transform realistic footage into anime, painting, or cinematic styles.
- Visual Effects — Add atmospheric effects, color grading, or artistic filters to videos.
- Content Repurposing — Restyle existing content for different platforms or audiences.
- Creative Exploration — Experiment with dramatic reimaginations of source material.
- Brand Consistency — Apply consistent visual styles across multiple video clips.
Pro Tips
- Start with adhere modes for subtle changes, move to flex or reimagine for more dramatic effects.
- The first_frame parameter can significantly influence the overall style of the output.
- Use clear, descriptive prompts that specify the desired transformation style.
- For best results, use high-quality source videos with good lighting.
Notes
- Maximum video file size is 100MB.
- Maximum video duration is 30 seconds.
- If using a URL, ensure it is publicly accessible.