How to add a blur-to-focus reveal with Claude

The video opens as a thick blur where only the bottle's purple shape shows, then pulls into crisp focus by 1.3 seconds.

Get this effect

  1. Switch to Code in your Claude Desktop App

  2. Install the skill (once)

    Show the prompt
    Install the Recharm video effects skill: download https://recharm-growth-staging.s3.us-east-2.amazonaws.com/website/downloads/recharm-video-effects.zip and unzip it into ~/.claude/skills
  3. Ask for the effect

    Add a blur-to-focus reveal to input.mp4
    Starting blur radius as a share of the frame width (0.05 is 27 pixels on a 540-wide video): 0.05
    Seconds the opening stays fully blurred: 0.3

Several videos, several effects, one ask

Put your clips in the folder, mention them with @, and ask for everything at once. Claude runs one tested script after another on each clip, then joins them.

Add a blur-to-focus reveal to @clip1.mp4, put a sale badge on @clip2.mp4, give @clip3.mp4 a VHS look, then join all three with crossfades.

Settings you can change

Ask Claude to change any of these, or edit them at the top of the script.

SettingDefaultWhat it does
BLUR0.05Starting blur radius as a share of the frame width (0.05 is 27 pixels on a 540-wide video).
HOLD0.3Seconds the opening stays fully blurred.
FOCUS1.3Second the picture is fully sharp.

Without the skill

Don’t want to install the skill? Paste this prompt into Claude Code and Claude writes the script itself.

Show the prompt
Add a blur-to-focus reveal to the start of input.mp4: the first 0.3 seconds are fully blurred with a Gaussian blur of sigma 27 pixels (5% of the 540-pixel frame width) over the whole frame, then the blur eases out (sigma = 27 x (1 - p)^3, where p goes from 0 at 0.3 seconds to 1 at 1.3 seconds) so the picture is completely sharp from 1.3 seconds and untouched after that. Don't darken, fade or zoom the frame. Use Python with OpenCV (cv2.GaussianBlur) on each frame and ffmpeg to read and write the video, keep the size, frame rate (30fps, H.264 yuv420p) and audio the same, and save it as output.mp4.

Run it without Claude

This is the exact script we tested. Save it as blur-to-focus-reveal.py and run:

python3 blur-to-focus-reveal.py input.mp4 output.mp4
Show the script
#!/usr/bin/env python3
"""Blur-to-focus reveal: the video opens as a heavy blur and pulls into sharp focus over its first second.

Usage: python3 blur-to-focus-reveal.py input.mp4 output.mp4
Needs ffmpeg, OpenCV and numpy (pip install opencv-python-headless numpy).
"""
import json
import subprocess
import sys

import cv2
import numpy as np

BLUR = 0.05      # starting blur radius (Gaussian sigma) as a share of the frame width
HOLD = 0.3       # seconds the opening stays fully blurred
FOCUS = 1.3      # second the picture is fully sharp


def sigma(t):
    """Blur radius in pixels at time t: full until HOLD, easing out to zero at FOCUS."""
    p = min(max((t - HOLD) / (FOCUS - HOLD), 0), 1)
    return BLUR * w * (1 - p) ** 3


def probe(path):
    info = json.loads(subprocess.check_output(["ffprobe", "-v", "error", "-select_streams", "v:0", "-show_entries",
                                               "stream=width,height,r_frame_rate", "-of", "json", path]))
    s = info["streams"][0]
    num, den = s["r_frame_rate"].split("/")
    return s["width"], s["height"], s["r_frame_rate"], float(num) / float(den)


src, out = sys.argv[1:3]
w, h, rate, fps = probe(src)
reader = subprocess.Popen(["ffmpeg", "-v", "error", "-i", src, "-f", "rawvideo", "-pix_fmt", "rgb24", "-"],
                          stdout=subprocess.PIPE)
writer = subprocess.Popen(["ffmpeg", "-y", "-v", "error", "-f", "rawvideo", "-pix_fmt", "rgb24", "-s", f"{w}x{h}",
                           "-r", rate, "-i", "-", "-i", src, "-map", "0:v", "-map", "1:a?", "-c:v", "libx264",
                           "-crf", "18", "-pix_fmt", "yuv420p", "-c:a", "copy", "-shortest", out],
                          stdin=subprocess.PIPE)
i = 0
while True:
    buf = reader.stdout.read(w * h * 3)
    if len(buf) < w * h * 3:
        break
    img = np.frombuffer(buf, np.uint8).reshape(h, w, 3)
    s = sigma(i / fps)
    if s > 0.3:
        img = cv2.GaussianBlur(img, (0, 0), s, borderType=cv2.BORDER_REFLECT)
    writer.stdin.write(img.tobytes())
    i += 1
writer.stdin.close()
if reader.wait() or writer.wait():
    sys.exit("ffmpeg failed")

Find 3x winning ads

Recharm cuts your ad footage into tagged, searchable clips: hooks, testimonials, product shots. Find the shots that win, add the effect with Claude, and ship 3x more ad edits.

Start 14-day free trial