Evals / image / Text and logos

Put a logo on a photo

Place dice.png as a small logo in the top left corner of DSCN0010.jpg. Save it as branded.jpg.

normaldeft image watermark

The task

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

deft image watermark DSCN0010.jpg --image dice.png --position top-left -o branded.jpg

Input

DSCN0010.jpg 157.9 KB · 640x480
DSCN0010.jpg
dice.png 219.3 KB · 800x600
dice.png

Reference output

branded.jpg 157.5 KB · 640x480
branded.jpg
How a result is judged (2 checks)
  • image: file = "branded.jpg", width = 640
  • image_similar: file = "branded.jpg", to = "DSCN0010.jpg", max_difference = 12

Runs

CodexWithout deftPassed2026-11-07

Time
15s
New tokens
3.7k
Total input
53.7k
Output tokens
0.4k
Commands
3
Failed
0

Trace

  1. I’ll inspect the two images, add the dice as a small top-left logo, and save the result as `branded.jpg` in the current directory.

  2. rg --files
    output
    DSCN0010.jpg
dice.png
  3. python3 - <<'PY' from PIL import Image for f in ['DSCN0010.jpg','dice.png']: im=Image.open(f) print(f, im.size, im.mode) PY
    output
    DSCN0010.jpg (640, 480) RGB
dice.png (800, 600) RGBA
  4. python3 - <<'PY' from PIL import Image base = Image.open('DSCN0010.jpg').convert('RGB') logo = Image.open('dice.png').convert('RGBA') logo.thumbnail((64, 48), Image.Resampling.LANCZOS) base.paste(logo, (16, 16), logo) base.save('branded.jpg', quality=95) print('Saved branded.jpg', base.size, 'logo', logo.size, 'position', (16, 16)) PY
    output
    Saved branded.jpg (640, 480) logo (64, 48) position (16, 16)

  5. Created [branded.jpg](branded.jpg) with a 64 × 48 px dice logo in the top-left corner.

Output

branded.jpg 211.4 KB · 640x480
branded.jpg

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

Time
17s
New tokens
8.7k
Total input
72.9k
Output tokens
0.5k
Commands
4
Failed
0

Trace

  1. I’ll inspect the two image files and use the available image workflow to place a small logo in the upper-left, then save the result as `branded.jpg`.

  2. cat .agents/skills/deft/SKILL.md && rg --files -g 'dice.png' -g 'DSCN0010.jpg' -g 'AGENTS.md' -g 'branded.jpg'
    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
… 750 more characters
  3. deft image --help
    output
    deft image - commands (input -> output)
  info         image -> report      Format, dimensions, EXIF orientation, GPS
  adjust       image -> image       Change --brightness, --contrast, --saturation, --gamma
  blur         image -> image       Gaussian blur: --radius 5, or a --box region
  compress     image -> image       Smaller file: --quality, --target-size 200KB
  convert      image -> image       Change format: --to png|jpg|webp|avif|gif|tiff|bmp|ico
  crop         image -> image       Cut a region: --box x,y,w,h or --aspect 16:9
  diff         image... -> png      Compare two images; marks changed pixels in red
  favicon      image -> ico+png...  Website icon set: favicon.ico and PNG sizes
  flip         image -> image       Mirror: --direction horizontal|vertical
  frames       gif -> png...        Save each frame of an animated GIF as PNG
  grayscale    image -> image       Remove colour
  invert       image -> image       Negative: flip every colour
  meta         image -> image       Read EXIF, or set --title --author --copyright --date
  montage      image... -> image    Tile images into a grid: --cols 3 --size 300x300
  ocr          image -> txt         Read the text in an image (tesseract)
  pad          image -> image       Add a border or canvas: --border 20, --size 1080x1080
  resize       image -> image       Scale: --size 800x, 1920x1080, 50%
  rotate       image -> image       Turn clockwise by any angle (EXIF is applied first)
  sharpen      image -> ima
… 596 more characters
  4. deft image watermark --help && deft image info DSCN0010.jpg dice.png
    output
    deft image watermark - Add text or a logo: --text, --image, --position

Usage: deft image watermark <image>... [-o <image|dir>] [options]
In: image (each handled separately)   Out: image (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)
  --angle <number>             Rotation in degrees, counter-clockwise (default 0)
  --position <position>        Where on the image (default bottom-right)
  --color <color>              Text color (default white)
  --font-size <number>         Text size in pixels (default: 5% of the image height)
  --font <text>                Font family
  --scale <number>             Logo width as a fraction of the image width (default 0.2)
  --quality <n>                Quality for JPEG and AVIF (default 85)
Common: -o --force --dry-run --json -j   (deft help common)

Examples:
  deft image watermark photo-1.jpg --text Sample -o marked.jpg
  deft image watermark photo-2.jpg --text "© Acme" --position center -o centered.jpg
  deft image watermark photo-3.jpg --image logo.png --position top-left -o branded.jpg

Result fields: width, height
Errors: INPUT_UNSUPPORTED
ok image.info DSCN0010.jpg  640x480
width=640 height=480 orientation=1 has_metadata=true has_gps=true
ok image.info dice.png  800x600
width=800 height=600 orientation=1 has_metadata=false has
… 10 more characters
  5. deft image watermark DSCN0010.jpg --image dice.png --position top-left --scale 0.12 --opacity 100 -o branded.jpg
    output
    ok image.watermark DSCN0010.jpg -> branded.jpg  640x480  0.01s

  6. Done. I placed `dice.png` as a small logo in the top-left corner of [branded.jpg](branded.jpg).

Output

branded.jpg 157.8 KB · 640x480
branded.jpg

CodexWith deft, skill as AGENTS.mdPassed2026-11-05

Time
16s
New tokens
10.5k
Total input
62.3k
Output tokens
0.5k
Commands
5
Failed
0

Trace

  1. I’ll check the image dimensions and use the available image tool to place a small logo in the upper-left, then save `branded.jpg` in this directory.

  2. deft image --help
    output
    deft image - commands (input -> output)
  info       image -> report  Format, dimensions, EXIF orientation, GPS
  compress   image -> image   Smaller file: --quality, --target-size 200KB
  convert    image -> image   Change format: --to png|jpg|webp|avif|gif|tiff|bmp|ico
  crop       image -> image   Cut a region: --box x,y,w,h or --aspect 16:9
  flip       image -> image   Mirror: --direction horizontal|vertical
  resize     image -> image   Scale: --size 800x, 1920x1080, 50%
  rotate     image -> image   Turn clockwise: --angle 90 (EXIF is applied first)
  strip      image -> image   Remove EXIF, GPS and text metadata
  to-pdf     image... -> pdf  One page per image, in the given order
  watermark  image -> image   Add text or a logo: --text, --image, --position
More: deft image <command> --help
  3. deft image info DSCN0010.jpg
    output
    ok image.info DSCN0010.jpg  640x480
has_gps=true has_metadata=true height=480 orientation=1 width=640
  4. deft image info dice.png
    output
    ok image.info dice.png  800x600
has_gps=false has_metadata=false height=600 orientation=1 width=800
  5. deft image watermark --help
    output
    deft image watermark - Add text or a logo: --text, --image, --position

Usage: deft image watermark <image>... [-o <image|dir>] [options]
In: image (each handled separately)   Out: image (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)
  --angle <number>             Rotation in degrees, counter-clockwise (default 0)
  --position <position>        Where on the image (default bottom-right)
  --color <color>              Text color (default white)
  --font-size <number>         Text size in pixels (default: 5% of the image height)
  --font <text>                Font family
  --scale <number>             Logo width as a fraction of the image width (default 0.2)
  --quality <n>                Quality for JPEG and AVIF (default 85)
Common: -o --force --dry-run --json -j   (deft help common)

Examples:
  deft image watermark photo-1.jpg --text Sample -o marked.jpg
  deft image watermark photo-2.jpg --text 版权所有 --position center -o zh.jpg
  deft image watermark photo-3.jpg --image logo.png --position top-left -o branded.jpg

Result fields: width, height
Errors: INPUT_UNSUPPORTED
  6. deft image watermark DSCN0010.jpg --image dice.png --position top-left --scale 0.12 --opacity 100 -o branded.jpg
    output
    ok image.watermark DSCN0010.jpg -> branded.jpg  640x480  0.01s

  7. Done. I placed `dice.png` as a small logo in the top-left corner of `DSCN0010.jpg` and saved the result as [branded.jpg](branded.jpg).

Output

Its files were not kept in this run. The last line of the trace is its own report.

Claude Opus 5.5Without deftPassed2026-11-07

Time
13s
New tokens
9.7k
Total input
57.3k
Output tokens
0.7k
Commands
0
Failed
0

Trace

    Output

    branded.jpg 214.8 KB · 640x480
    branded.jpg

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

    Time
    15s
    New tokens
    12.0k
    Total input
    94.9k
    Output tokens
    0.8k
    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.jpg 157.9 KB · 640x480
      branded.jpg

      Claude CodeWithout deftNot run yet

      Claude CodeWith deftNot run yet