Edit Any Video with Text Using Lucy Edit 2

Seedance 2.5 IS HERE · Nano Banana 2 & GPT Image 2.5 UNLIMITED UNTIL September 30Upgrade

Overview

Lucy Edit 2 takes an existing video and rewrites parts of it based on what you describe in text, a reference image, or both. The problem it solves is straightforward: making specific, targeted changes to footage without touching a timeline or loading a layer-based editor. On Picasso IA, you upload your clip, describe the edit, and get a modified version back without any technical setup. It handles style shifts, object swaps, and character-level changes in a single pass, so you spend less time on revisions and more time on the actual creative decision.

How It Works

Upload an MP4 video file (H.264 or VP8, up to 200MB) in 16:9 or 9:16 aspect ratio.
Write a text prompt describing what you want changed, such as "swap the jacket for a brown leather coat" or "shift the color grade to a warm golden tone."
Add a reference image if you have a specific item or style in mind and want to show the model exactly what to match.
Set a seed value if you want to reproduce the same result later or compare variations with everything else held constant.
Submit the job and download your edited video once it finishes.

Frequently Asked Questions

Do I need programming skills or technical knowledge to use this? No, just open Lucy Edit 2 on Picasso IA, adjust the settings you want, and hit generate.

Is it free to try? Lucy Edit 2 is available on Picasso IA without requiring a paid plan to test it. Check the credits page for the latest usage details.

How long does it take to get results? Most short clips come back within 30 to 90 seconds. Longer videos or more involved edits may take a bit more time depending on server load.

What output formats are supported? The model returns your edited video as an MP4 file, ready to download and drop into any editing app or publish directly.

Can I use a reference image without writing a text prompt? Yes. Leave the prompt field empty and upload a reference image on its own. The model uses that image alone to guide the edit, which works well when you know what you want visually but find it hard to put into words.

What if the result doesn't match what I had in mind? Refine the wording of your prompt, try a different reference image, or change the seed to generate a new variation. Small changes to the prompt often produce noticeably different outputs, so iterating quickly is part of the process.

Credit Cost

Each generation consumes 4 credits

4 credits

or 20 credits for 5 generations

Features

Everything this model can do for you

Text-guided edits

Type a description of the change you want and the model applies it across all video frames.

Reference image input

Upload a photo of any object, person, or style to show the model exactly what you want added or changed.

Style transfer

Shift the visual tone of an entire clip by describing a mood or attaching a reference image.

Object replacement

Swap specific items in the scene, from clothing to props, without re-shooting.

Prompt optimizer

An optional setting rewrites your text description into a more precise instruction before generation.

Reproducible results

Set a seed value to get the same edit output every time you run the model.

MP4 output

Get back a ready-to-use video file in standard format, no conversion needed.

Use Cases

Replace a product logo on a shirt in an existing video clip by uploading a reference image of the new logo

Apply a specific visual style to a talking-head video by describing the look you want and attaching a style reference image

Swap the outfit on a character in a short clip by providing a photo of the clothing you want them to wear

Add sunglasses to a subject in a video by uploading a reference image of the exact pair you want placed on them

Change the background mood of a scene from daytime to dusk by writing a short text description of the new look

Re-skin a product demo video to match a seasonal theme without re-shooting any footage

Turn a raw interview clip into a stylized short by describing a cinematic color grade and letting the model apply it frame by frame

Examples

20.9s

Transform into a detailed oil painting in the style of the Dutch Golden Age, with rich warm tones, visible brushstrokes, and dramatic Rembrandt lighting

29.3s

Change the person's outfit to a medieval knight's armor with a shining silver breastplate, chainmail sleeves, and a red cape flowing behind

23.9s

Transform the entire scene into a cyberpunk neon-lit metropolis at night, with glowing holographic signs, purple and teal neon reflections on wet streets

17.8s

Apply a cinematic film noir aesthetic with high contrast black and white, dramatic shadows, and moody atmospheric lighting

19.2s

Transform into a vibrant anime style with cel shading, bold outlines, and colorful saturated tones