tools/llm-covers
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Update ReadMe.md

Browse Source
This commit is contained in:
tangent
2026-09-03 13:26:05 -06:00
parent acda9e188e
commit 66037e4a11
1 changed files with 18 additions and 15 deletions
Download Patch File Download Diff File Expand all files Collapse all files
ReadMe.md
+18 -15
View File
@@ -14,10 +14,11 @@ A simple tool for using local LLMs to generate cover briefs for ebooks.
4. Run `make_cover_briefs.lua` 4. Run `make_cover_briefs.lua`
Cover briefs will be placed in `cover_briefs`. A prompt ready to paste directly 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 into Gemini will be in `for_gemini`.
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 The local model sometimes completely forgets critical details of characters, so
output.) it's important you have some familiarity with the work before running the
generator to check accuracy.
### Config file format ### Config file format
```json ```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 because it pollutes context extremely badly and will randomly add elements and
rejections from different conversations everywhere. rejections from different conversations everywhere.
If Gemini rejects the prompt, adding If you are able to use Gemini Flash or Flash-Lite, it works far better than Pro.
<code id="d2651e">Remove any elements that may go against guidelines before generating the image.</code> Pro tends to invent additional details, refuse to respond, fail to respond, or
<button onclick="navigator.clipboard.writeText(d2651e.textContent)">⧉</button> make modifications you didn't ask for. I genuinely cannot understand how it is
to the opening paragraph can fix that issue. *so much worse* at this.
- 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 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 features, so the best way to deal with it is to request its removal after the
initial image is generated. initial image is generated.
The local model sometimes completely forgets critical details of characters, so If Gemini rejects the prompt, adding
it's important you have some familiarity with the work before running the <code id="d2651e">Remove any elements that may go against guidelines before generating the image.</code>
generator to check accuracy. <button onclick="navigator.clipboard.writeText(d2651e.textContent)">⧉</button>
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 ## Tasks
- [ ] Add timestamps to when a prompt is sent. - [ ] Add timestamps to when a prompt is sent.