From 66037e4a110af4b2d57cb9026eedd525a7bf6bc5 Mon Sep 17 00:00:00 2001 From: tangent Date: Thu, 3 Sep 2026 13:26:05 -0600 Subject: [PATCH] Update ReadMe.md --- ReadMe.md | 33 ++++++++++++++++++--------------- 1 file changed, 18 insertions(+), 15 deletions(-) diff --git a/ReadMe.md b/ReadMe.md index 08d2217..dd56334 100644 --- a/ReadMe.md +++ b/ReadMe.md @@ -14,10 +14,11 @@ A simple tool for using local LLMs to generate cover briefs for ebooks. 4. 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.) +into Gemini will be in `for_gemini`. + +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. ### Config file format ```json @@ -39,22 +40,24 @@ 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. +If you are able to use Gemini Flash or Flash-Lite, it works far better than Pro. +Pro tends to invent additional details, refuse to respond, fail to respond, or +make modifications you didn't ask for. I genuinely cannot understand how it is +*so much worse* at this. Gemini is really bad about adding hardcover seams. Despite being instructed not -to, it shows up sometimes. More strong prompting breaks other requested +to, it shows up often. 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. +If Gemini rejects the prompt, adding +Remove any elements that may go against guidelines before generating the image. + +to the opening paragraph can *sometimes* fix that issue. +- Telling it to rewrite the prompt and then using *that* in a separate + conversation tends to work better. +- I typically just re-send it repeatedly, as it's easier and eventually works + most of the time. ## Tasks - [ ] Add timestamps to when a prompt is sent.