Evals / video / Logos and watermarks

Put a logo on a video

Add dice.png as a logo in the top left corner of bunny.mp4. Save it as branded.mp4.

normaldeft video watermark

The task

The reference answer shows the job can be done with deft. It is not an agent run.

deft video watermark bunny.mp4 --image dice.png --position top-left -o branded.mp4

Input

bunny.mp4 946.5 KB · h264 1280x720, 10.0s
dice.png 219.3 KB · 800x600
dice.png

Reference output

branded.mp4 1.9 MB · h264 1280x720, 10.0s
How a result is judged (2 checks)
  • media: file = "branded.mp4", duration = 10, tolerance = 0.6
  • video_frame: file = "branded.mp4", from = "bunny.mp4", at = 5, min_difference = 0.05

Runs

CodexWithout deftPassed2026-11-07

Time
16s
New tokens
8.8k
Total input
71.4k
Output tokens
0.4k
Commands
3
Failed
0

Trace

  1. I’ll check the video and logo dimensions, then render the branded video in the current directory.

  2. rg --files
    output
    dice.png
bunny.mp4
  3. ffmpeg -version | head -n 1 && ffprobe -v error -show_entries stream=width,height -of csv=s=x:p=0 bunny.mp4 && file dice.png
    output
    ffmpeg version 7.1.1 Copyright (c) 2000-2025 the FFmpeg developers
1280x720
dice.png: PNG image data, 800 x 600, 8-bit/color RGBA, non-interlaced
  4. ffmpeg -y -i bunny.mp4 -i dice.png -filter_complex "[1:v]scale=160:-1[logo];[0:v][logo]overlay=24:24:format=auto" -c:v libx264 -preset medium -crf 18 -c:a copy branded.mp4
    output
    ffmpeg version 7.1.1 Copyright (c) 2000-2025 the FFmpeg developers
  built with Apple clang version 15.0.0 (clang-1500.1.0.2.5)
  configuration: --prefix=/opt/homebrew/Cellar/ffmpeg/7.1.1_1 --enable-shared --enable-pthreads --enable-version3 --cc=clang --host-cflags= --host-ldflags='-Wl,-ld_classic' --enable-ffplay --enable-gnutls --enable-gpl --enable-libaom --enable-libaribb24 --enable-libbluray --enable-libdav1d --enable-libharfbuzz --enable-libjxl --enable-libmp3lame --enable-libopus --enable-librav1e --enable-librist --enable-librubberband --enable-libsnappy --enable-libsrt --enable-libssh --enable-libsvtav1 --enable-libtesseract --enable-libtheora --enable-libvidstab --enable-libvmaf --enable-libvorbis --enable-libvpx --enable-libwebp --enable-libx264 --enable-libx265 --enable-libxml2 --enable-libxvid --enable-lzma --enable-libfontconfig --enable-libfreetype --enable-frei0r --enable-libass --enable-libopencore-amrnb --enable-libopencore-amrwb --enable-libopenjpeg --enable-libspeex --enable-libsoxr --enable-libzmq --enable-libzimg --disable-libjack --disable-indev=jack --enable-videotoolbox --enable-audiotoolbox --enable-neon
  libavutil      59. 39.100 / 59. 39.100
  libavcodec     61. 19.101 / 61. 19.101
  libavformat    61.  7.100 / 61.  7.100
  libavdevice    61.  3.100 / 61.  3.100
  libavfilter    10.  4.100 / 10.  4.100
  libswscale      8.  3.100 /  8.  3.100
  libswresample   5.  3.100 /  5.  3.100
  libpostproc    58.  3.100 / 58.  3.100
Input #0, mov,mp4,m4a,3
… 5791 more characters

  5. The render is underway with the logo scaled to 160 pixels wide and placed 24 pixels from the top-left edges.

  6. Created [branded.mp4](branded.mp4) with `dice.png` in the top-left corner.

Output

branded.mp4 5.0 MB · h264 1280x720, 10.0s

CodexWith deft, skill installedPassedRead the skillUsed deft2026-11-07

Time
20s
New tokens
9.4k
Total input
85.4k
Output tokens
0.6k
Commands
5
Failed
1

Trace

  1. I’ll inspect the available media files and use the provided video workflow instructions to add the logo and save the result as `branded.mp4`.

  2. cat ../.agents/skills/deft/SKILL.md (exit 1)
    output
    cat: ../.agents/skills/deft/SKILL.md: No such file or directory
  3. cat .agents/skills/deft/SKILL.md && rg --files -g 'dice.png' -g 'bunny.mp4' -g 'AGENTS.md' .
    output
    ---
name: deft
description: "Use deft instead of writing a script for file jobs: PDF merge/split/compress/watermark, image resize/convert/compress, video and audio trim/convert/compress, spreadsheets, Markdown to PDF/HTML, and YouTube downloads and subtitles."
---

# deft

One local command for file jobs. Prefer it over writing Python or shell scripts.

Syntax: `deft <group> <command> [inputs] [-o output] [--options]`

Groups:
- `pdf`: Merge, split, compress, encrypt, forms, OCR, compare, convert
- `image`: Resize, crop, convert, compress, filters, montage, OCR
- `video`: Trim, crop, speed, convert, compress, GIF, frames (ffmpeg)
- `audio`: Convert, trim, merge, fade, speed, tag, normalize (ffmpeg)
- `doc`: Word/ODT/RTF: to text, Markdown, HTML, PDF; find and replace
- `slides`: PowerPoint: extract text, Markdown outline, PDF handout
- `data`: JSON/YAML/TOML/XML: convert, query with jq syntax, merge, diff
- `sheet`: Excel/CSV/ODS tables: filter, sort, join, pivot, convert
- `md`: Markdown to PDF, HTML, Word, EPUB; table of contents
- `html`: HTML to Markdown, text, Word, PDF; screenshots
- `epub`: E-books: info, to text, Markdown and PDF
- `email`: EML files: headers, text, attachments
- `contact`: VCF address books: to and from CSV
- `calendar`: ICS calendars: to and from CSV
- `gps`: GPX and KML tracks: convert, distance and time
- `youtube`: Info, download, audio, subtitles, thumbnail (yt-dlp)
- `file`: Any file: hash, duplicates, batch rename, base64, encoding
- `qr`: Cre
… 751 more characters
  4. deft find "overlay image logo on video top left"
    output
    video watermark  video -> video  Add text or a logo: --text, --image, --position
image watermark  image -> image  Add text or a logo: --text, --image, --position
pdf watermark    pdf -> pdf      Stamp text or an image on pages
  5. deft video watermark --help
    output
    deft video watermark - Add text or a logo: --text, --image, --position

Usage: deft video watermark <video>... [-o <video|dir>] [options]
In: video (each handled separately)   Out: video (default <name>.watermarked.<ext>)
Any script works; text uses the fonts on this machine.

Options:
  --text <text>                Text to add
  --image <path>               Logo or picture to add
  --opacity <n>                Opacity in percent (default 70)
  --position <position>        Where on the frame (default bottom-right)
  --color <color>              Text color (default white)
  --font-size <number>         Text size in pixels (default: 5% of the height)
  --font <text>                Font family
  --scale <number>             Logo width as a fraction of the frame width (default 0.2)
Common: -o --force --dry-run --json -j   (deft help common)

Examples:
  deft video watermark clip.mp4 --text Sample -o marked.mp4
  deft video watermark clip.mp4 --image logo.png --position top-left -o branded.mp4
Needs: ffmpeg, ffprobe

  6. The files are present, and `deft video watermark` supports image logos with a top-left position. I’m applying the logo and writing the requested output now.

  7. deft video watermark bunny.mp4 --image dice.png --position top-left -o branded.mp4
    output
    ok video.watermark bunny.mp4 -> branded.mp4  1.9MB  0.86s

  8. Added `dice.png` to the top-left corner of `bunny.mp4` and saved the result as [branded.mp4](branded.mp4).

Output

branded.mp4 1.9 MB · h264 1280x720, 10.0s

Claude Opus 5.5Without deftPassed2026-11-07

Time
28s
New tokens
11.5k
Total input
88.7k
Output tokens
1.1k
Commands
0
Failed
0

Trace

    Output

    branded.mp4 4.7 MB · h264 1280x720, 10.0s

    Claude Opus 5.5With deft, skill installedPassedRead the skillUsed deft2026-11-07

    Time
    15s
    New tokens
    10.4k
    Total input
    75.1k
    Output tokens
    0.6k
    Commands
    0
    Failed
    0

    Trace

      Output

      .claude/skills/deft/SKILL.md 2.1 KB
      ---
name: deft
description: "Use deft first for any simple, direct operation on local files, whatever the type: convert, read, extract, edit, compress, merge, split, compare or inspect. Try it before writing a script or one-liner. If unsure, run deft find; if it says no command does this, use another tool. Not for programming work: to read, write or change source code, skip it."
---

# deft

One local command for file jobs. Prefer it over writing Python or shell scripts.

Syntax: `deft <group> <command> [inputs] [-o output] [--options]`

Groups:
- `pdf`: Merge, split, compress, encrypt, forms, OCR, compare, convert
- `image`: Resize, crop, convert, compress, adjust, montage, OCR
- `video`: Trim, merge, convert, compress, subtitles, GIF, frames (ffmpeg)
- `audio`: Convert, trim, normalize, denoise, cut silence (ffmpeg)
- `doc`: Word/ODT/RTF: to text, Markdown, HTML, PDF; find and replace
- `slides`: PowerPoint: extract text, Markdown outline
- `sheet`: Excel/CSV/ODS tables: SQL query, pivot, merge, split, convert
- `json`: JSON: convert, format, merge, diff, validate
- `toml`: TOML: convert, format, merge, diff, validate
- `xml`: XML: convert, format, merge, diff, validate
- `yaml`: YAML: convert, format, merge, diff, validate
- `md`: Markdown to PDF, HTML, Word, EPUB; table of contents
- `html`: HTML to Markdown, text, Word and PDF
- `epub`: E-books: info, to text, Markdown and PDF
- `gps`: GPX and KML tracks: convert, distance and time
- `qr`: Create QR codes and barcodes; read QR codes

How to use it:
1. Run `deft <group>` to list commands, or `deft find "<what you want>"` to search. If it says `no command does this`, use another tool.
2. Run `deft <group> <command> --help` for options and examples.
3. `deft convert <in> -o <out.ext>` converts between formats by extension.
4. Results are one line starting with `ok`, `partial` or `error`; add `--json` to parse them. Errors include a `hint:` with the fix.

Inputs are never overwritten; pass `--force` or `--in-place` to allow it. Globs and directories work as inputs; several inputs run in parallel.

If `deft` is not installed, ask the user, then follow https://github.com/firstprayer/deft/blob/main/docs/INSTALL.md
      branded.mp4 1.9 MB · h264 1280x720, 10.0s

      Claude CodeWithout deftNot run yet

      Claude CodeWith deftNot run yet