--- title: "How to add a crosshatch with Claude (tested prompt and script)" description: "At one second the shot becomes a pen drawing on cream paper: the holographic backdrop turns into bands of parallel diagonal strokes, and the dropper cap and bottle shadows fill in with a dense grid of crossing lines. Install one skill and ask Claude Code, or run the Python script we tested yourself." url: https://www.recharm.com/effects/crosshatch --- # How to add a crosshatch with Claude At one second the shot becomes a pen drawing on cream paper: the holographic backdrop turns into bands of parallel diagonal strokes, and the dropper cap and bottle shadows fill in with a dense grid of crossing lines. Made by the script on this page, from our own test clip. ## Get this effect 1. ### Switch to Code in your [Claude Desktop App](https://claude.com/download) 2. ### Install the skill (once) ``` 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 crosshatch to input.mp4 Second the picture turns into pen lines: 1.0 Pixels between neighboring lines in one layer: 8 ``` ## 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 crosshatch 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. | Setting | Default | What it does | | ---------- | -------------------------------------------------- | ----------------------------------------------------------------------------------------------------------------------- | | `START` | `1.0` | Second the picture turns into pen lines. | | `SPACING` | `8` | Pixels between neighboring lines in one layer. Bigger gives a looser, sketchier drawing. | | `LINE` | `2.2` | Line thickness in pixels. | | `LAYERS` | `[(45, 0.10), (-45, 0.35), (0, 0.60), (90, 0.80)]` | Each layer's line angle and the darkness (0-1) where it starts. More layers or lower thresholds give a heavier drawing. | | `PAPER` | `(245, 240, 225)` | Paper color. | | `INK` | `(30, 30, 45)` | Pen color. | | `CONTRAST` | `(2, 98)` | Brightness percentiles that become solid ink and bare paper. | ## Without the skill Don’t want to install the skill? Paste this prompt into Claude Code and Claude writes the script itself. ``` Give input.mp4 (540x960) a pen crosshatch look from 1.0 seconds to the end; before 1.0 seconds leave it untouched. For each frame from 1.0 s: turn it to grayscale, Gaussian-blur it with a 2 pixel radius, and stretch its brightness so the 2nd percentile is darkness 1 and the 98th percentile is darkness 0. Fill the frame with cream paper (245, 240, 225) and draw dark ink (30, 30, 45) lines in four layers, each a set of parallel straight lines 8 pixels apart and 2.2 pixels thick with a 1 pixel soft edge: lines at 45 degrees wherever the darkness is above 0.10, at -45 degrees above 0.35, horizontal above 0.60 and vertical above 0.80. Fade each layer in over 0.08 of darkness past its threshold so the edges don't flicker, and where layers overlap the ink just stacks (multiply the paper that each layer leaves). No other colors should be left. Use Python with numpy and Pillow for the frames and ffmpeg to read and write the video (don't use ffmpeg's drawtext if you add any text), keep the size, 30fps, the 6 second length and the audio, and save it as output.mp4. ``` ## Run it without Claude This is the exact script we tested. Save it as `crosshatch.py` and run: ``` python3 crosshatch.py input.mp4 output.mp4 ``` ``` #!/usr/bin/env python3 """Crosshatch: at one second the shot is redrawn in pen, with more layers of crossing lines wherever it's darker. Usage: python3 crosshatch.py input.mp4 output.mp4 Needs ffmpeg, Pillow and numpy (pip install pillow numpy). """ import json import subprocess import sys import numpy as np from PIL import Image, ImageFilter START = 1.0 # second the picture turns into pen lines SPACING = 8 # pixels between neighboring lines in one layer LINE = 2.2 # line thickness in pixels LAYERS = [(45, 0.10), (-45, 0.35), (0, 0.60), (90, 0.80)] # (line angle in degrees, darkness where that layer starts) PAPER = (245, 240, 225) # paper color INK = (30, 30, 45) # pen color CONTRAST = (2, 98) # percentiles of the frame's brightness mapped to solid ink and bare paper def crosshatch(img): """Redraw one frame (h, w, 3) as hatching: each layer of lines covers the parts darker than its threshold.""" gray = Image.fromarray(img.astype(np.uint8)).convert("L").filter(ImageFilter.GaussianBlur(2)) luma = np.asarray(gray, np.float32) lo, hi = np.percentile(luma, CONTRAST) dark = 1 - np.clip((luma - lo) / max(hi - lo, 1), 0, 1) paper_left = np.ones_like(dark) for lines, threshold in layers: on = np.clip((dark - threshold) / 0.08, 0, 1) # fade each layer in over a small darkness range paper_left *= 1 - lines * on ink = (1 - paper_left)[..., None] return paper * (1 - ink) + ink_color * ink 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) y, x = np.mgrid[0:h, 0:w].astype(np.float32) layers = [] # (line mask 0-1, darkness threshold) per layer for angle, threshold in LAYERS: a = np.radians(angle) across = x * np.sin(a) - y * np.cos(a) # distance across this layer's lines off_line = np.abs((across % SPACING) - SPACING / 2) # 0 on a line, SPACING/2 halfway between lines layers.append((np.clip(LINE / 2 - off_line + 0.5, 0, 1), threshold)) # 1px soft edge paper, ink_color = np.array(PAPER, np.float32), np.array(INK, np.float32) 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 raw := reader.stdout.read(w * h * 3): img = np.frombuffer(raw, np.uint8).reshape(h, w, 3).astype(np.float32) if i / fps >= START: img = crosshatch(img) writer.stdin.write(np.clip(img, 0, 255).astype(np.uint8).tobytes()) i += 1 writer.stdin.close() if reader.wait() or writer.wait(): sys.exit("ffmpeg failed") ``` ## More stylize and art - [Anime style **Anime style**](https://www.recharm.com/effects/anime-style) - [ASCII art **ASCII art**](https://www.recharm.com/effects/ascii-art) - [Blueprint **Blueprint**](https://www.recharm.com/effects/blueprint) - [Charcoal drawing **Charcoal drawing**](https://www.recharm.com/effects/charcoal-drawing) - [Claymation style **Claymation style**](https://www.recharm.com/effects/claymation-style) ## 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](https://www.recharm.com/get-started)