[pstorm]

That's a trivial example, sure. Think of saying "make this image more red, flip it vertically, then crop the bottom 25%, and finally output it with 80% compression as a jpg". That would take 15 minutes to figure out how to write that with imagick, or just have an LLM do it for you.

[tough]

I had to try, seems reasonable, haven't tested the code

As an AI language model, I do not have direct access to image editing software, but I can provide you with a shell script that could achieve the described image manipulation using ImageMagick, assuming it is installed on your system.

Here's an example shell script that you could use as a starting point:

bash Copy code #!/bin/bash

# Set the input image filename input_file="input.jpg"

# Set the output image filename output_file="output.jpg"

# Increase the redness of the image convert "$input_file" -modulate 100,150,100 -channel R -evaluate multiply 1.2 +channel temp1.jpg

# Flip the image vertically convert temp1.jpg -flip temp2.jpg

# Crop the bottom 25% of the image convert temp2.jpg -gravity South -chop 0x25% temp3.jpg

# Compress the image to 80% convert temp3.jpg -quality 80 "$output_file"

# Clean up temporary files rm temp*.jpg To use this script, save it to a file (e.g., "image_manipulation.sh"), make it executable (e.g., "chmod +x image_manipulation.sh"), and run it in the same directory as your input image. The output image will be saved in the same directory with the name "output.jpg".

Please note that this is just an example script and may need to be modified depending on your specific image manipulation needs.

[fulafel]

This has lots of lossy encode/decode cycles that will accumulate artifacts. Good anecdote.

[DonHopkins]

This is a prime example of what I mean by my remark above that the original commenter was totally undermining their own argument by using "shell script" instead of "python script".

Shell scripts can't create intermediate bitmap images in memory and operate on them with normal drawing and filtering apis like opencv, without lossily serializing and deserializing them as jpg files, or even operate on json structures directly.

It would be a much stronger argument if your example used python and opencv or any other normal library, instead of incredibly inefficient and hard to write and maintain invocations to full blown unix commands run in separate processes instead of direct library calls to manipulate in-memory images.

There's no reason "AI" code generation has to use the worst possible language and technique to generate code to solve a problem.

It's like having a food replicator from Star Trek: TNG, and asking it to make you rancid dog food instead of lobster.