ReadMe.md

@@ -5,31 +5,41 @@ A simple tool for using local LLMs to generate cover briefs for ebooks.
 - A Mac mini M4 base model (original version) or better M-series computer
 - Ollama and `gemma4:12b-mlx`
 - LuaJIT
+- calibre
 
 ## Usage
-1. Use a tool like [audiobook-creator](https://github.com/prakharsr/audiobook-creator) to extract the text of an audiobook.
-2. Place it in `extracted_texts/TITLE by AUTHOR.txt`. (The format of this doesn't matter except that the file name sans extension will be used in the output.)
-3. Run `make_cover_briefs.lua`.
-4. Cover briefs will be placed in `cover_briefs`.
-5. 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.)
+1. Create `config.json` if necessary (see format below).
+2. Run `make_cover_briefs.lua` once to create necessary directories.
+3. Put ebooks in `raw_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.)
 
 ### 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.
+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 <code id="d2651e">Remove any elements that may go against guidelines before generating the image.</code>
+If Gemini rejects the prompt, adding
+<code id="d2651e">Remove any elements that may go against guidelines before generating the image.</code>
 <button onclick="navigator.clipboard.writeText(d2651e.textContent)">⧉</button>
 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.
+- 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.
+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.
+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.
@@ -37,9 +47,9 @@ to check accuracy.
 - [ ] option to delete input files or intermediate files at end of each operation step
 - [x] instead of placeholder directories, `mkdir -p` should be used to only make them when necessary
 - [x] make script resumable instead of having to restart per book
-- [ ] dry run to estimate total time before running full script, print starting ETA
+- [x] dry run to estimate total time before running full script, print starting ETA
 - [x] Build a list of files to work on and current states before doing anything by looping over source directories
 - [x] Combine everything into one script to manage things
-- [ ] Allow specifiying a filter on what to process
+- [ ] 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

lib/timing.lua

@@ -1,34 +1,36 @@
-local timing = {
-  entries = {}
-}
+local timing = {}
+local entries = {}
 
-local function to_minutes(t)   -- floored to tenths
-  return math.floor( t / 60 * 10 ) / 10
+function timing.seconds_to_minutes(seconds)   -- floored to tenths
+  return math.floor( seconds / 60 * 10 ) / 10
 end
 
-function timing:start()
-  -- if not self then self = {} end
-  self.entries[#self.entries + 1] = { start_time = os.time() }
+function timing.start()
+  entries[#entries + 1] = { start_time = os.time() }
 end
 
-function timing:stop()
-  local entry = self.entries[#self.entries]
+function timing.stop()
+  local entry = entries[#entries]
   entry.stop_time = os.time()
+  entry.delta = entry.stop_time - entry.start_time
 
-  return to_minutes(entry.stop_time - entry.start_time)   -- return delta
+  return timing.seconds_to_minutes(entry.delta)
 end
 
-function timing:print_report()
+function timing.print_report()
   local minimum, maximum, sum = math.huge, -math.huge, 0
-  for _, data in pairs(self.entries) do
-    local delta = data.stop_time - data.start_time
+  for _, data in pairs(entries) do
+    local delta = data.delta
     if delta > maximum then maximum = delta end
     if delta < minimum then minimum = delta end
     sum = sum + delta
   end
-  print("Total: " .. to_minutes(sum) .. " minutes.")
-  print("Averge: " .. to_minutes(sum / #self.entries) .. " minutes. Fastest: "
-    .. to_minutes(minimum) .. " minutes. Slowest: " .. to_minutes(maximum) .. " minutes.")
+
+  print("Total: " .. timing.seconds_to_minutes(sum) .. " minutes.")
+  print("Averge: " .. timing.seconds_to_minutes(sum / #entries)
+    .. " minutes. Fastest: " .. timing.seconds_to_minutes(minimum)
+    .. " minutes. Slowest: " .. timing.seconds_to_minutes(maximum)
+    .. " minutes.")
 end
 
 return timing

make_cover_briefs.lua

@@ -50,11 +50,11 @@ local send_prompt = function(text, model)
     file:write(text)
   end)
 
-  timing:start()
+  timing.start()
   -- word wrap breaks the raw output badly, so I need to implement my own for terminal output somehow
   local output = utility.capture_safe("cat " .. tmp_file_name:enquote() .. " | ollama run " .. (model or default_model) .. " --nowordwrap")
   os.execute("ollama stop " .. (model or default_model)) -- NOTE this makes things slower, but more stable
-  local delta = timing:stop()
+  local delta = timing.stop()
 
   print("Took " .. delta .. " minutes.")
   os.execute("rm " .. tmp_file_name)
@@ -267,14 +267,30 @@ local generate_cover_briefs = function(books)
   end
 end
 
+local estimate_time_required = function(books)
+  local sum, count = 0, 0
+  for name, data in pairs(books) do
+    if data.cover_brief_file then return end
+    sum = sum + 60 * (2 + data.extracted_file_size/(config.llm_covers.maximum_bytes/7.5))
+    count = count + 1
+  end
+
+  print(count .. " cover briefs to generate. Estimated time: "
+    .. timing.seconds_to_minutes(sum) .. " minutes.")
+end
+
 make_directories()
 
 local books = get_books()
 convert_ebooks(books)
+
+estimate_time_required(books)
+print("")
+
 generate_cover_briefs(books)
 
 print("")
-timing:print_report()
+timing.print_report()
 
 -- ebook_file, extracted_file, extracted_file_size,
 -- intermediate_file, condensed_intermediate_file, cover_brief_file