llm-covers

A simple tool for using local LLMs to generate cover briefs for ebooks.

Requirements

A Mac mini M4 base model (original version) or better M-series computer
Ollama and gemma4:12b-mlx
LuaJIT
calibre

Usage

Create config.json if necessary (see format below).
Run make_cover_briefs.lua once to create necessary directories.
Put ebooks in raw_ebooks.
Run make_cover_briefs.lua

Cover briefs will be placed in cover_briefs. A prompt ready to paste directly into Gemini will be in for_gemini. An extra border is prompted for to make cropping easy to remove the Gemini watermark. (There are other small changes to increase likelihood of Gemini following the prompt correctly and making a good output.)

Config file format

{
  "llm_covers": {
    "calibre_location": "/Applications/calibre.app",
    "default_model": "gemma4:12b-mlx",
    "maximum_bytes": 40000
  }
}

The above are the default settings. If you need something different, you only need to specify the changes.

Gemini Issues

None of this works unless you disable Gemini's personalization/memory, because it pollutes context extremely badly and will randomly add elements and rejections from different conversations everywhere.

If Gemini rejects the prompt, adding Remove any elements that may go against guidelines before generating the image. ⧉ to the opening paragraph can fix that issue.

This suddenly got a lot less effective. I recommend instead telling it to rewrite the prompt and then in a separate conversation, use that instead. I also recommend one retry before modifying it.

Gemini is really bad about adding hardcover seams. Despite being instructed not to, it shows up sometimes. More strong prompting breaks other requested features, so the best way to deal with it is to request its removal after the initial image is generated.

The local model sometimes completely forgets critical details of characters, so it's important you have some familiarity with the work before running the generator to check accuracy.

Tasks

Add timestamps to when a prompt is sent.
Specify ETA when sending a prompt (2.5-8 minutes depending on length). (Show as end time as well as relative time.)
option to delete input files or intermediate files at end of each major operation segment (or after its finisher..)
instead of placeholder directories, mkdir -p should be used to only make them when necessary
make script resumable instead of having to restart per book
dry run to estimate total time before running full script, print starting ETA
Build a list of files to work on and current states before doing anything by looping over source directories
Combine everything into one script to manage things
Allow specifying a filter on what to process
Allow changing the maximum bytes per prompt dynamically (run smaller while I'm doing other things, run full while I'm asleep)
specify config format

3.0 KiB Raw Blame History