Feedback

A search-and-REPLACE option in Codex so we can change the names of characters / objects / locations universally across multiple entries with one click. It would save a lot of time instead of manually updating each separate Codex entry.

Currently, I can chat with a scene, the outline of the entire novel. What about chatting with a chapter?

Ability to insert a graphic element into the narrative or prose to enhance the visual appeal and effectiveness of storytelling within NovelCrafter. For example: relevant images, charts, symbols, or other graphical representations directly alongside the text.

While it’s convenient to select models for each prompt, I generally use the same models across all my prompts. When I need to add a new model or change the parameters, I have to update the model list in every prompt individually. I would prefer to have a general model list that I can manage, containing all the models I want to use. In each prompt, I could then choose to either use an individual prompt model list or the general master model list. This approach would allow for the current flexibility of selecting specific models for a prompt, while also providing a general master list for all prompts. This way, I can update just one list and have it apply to all prompts that use it.

It really sucks that codex progressions are tied to specific scenes in a single book and don’t carry over across books in a series. We all know continuity errors are lethal to a book, and this issue is a major one just waiting to happen. Therefore, it would be desirable if codex progressions did carry over across books in a series. We already have a Series Codex functionality, so why not have progressions in individual books in a series carry over?

This is my very well-missed feature from when I used Scrivener: Snapshots (that can be labeled/titled) to look back at previous versions of drafts. Like before you edited it or cut text. It would be nice to compare the edited version with the original/previous drafts, see all the changes, and have the option to roll back some of them and keep others. I've tried using revision history but since I'm unable to label those they get lost quickly in the log as edits are made.

When working in the Tinker chat window, it would be nice to be able to include snippets (which may contain notes from elsewhere or bits from previous Tinker chats) as part of the current discussion. A workaround for now is to attach something like the following to a custom prompt and then executing that prompt: Our discussion is going to be about the following notes (which in the discussion will be referred to as the "notes"), keeping in mind that this is a work in progress, and that later elements in the notes may supersede earlier ones. Please remember and analyse all the notes below and give me a brief summary of them. <notes>{snippets.get("Notes (original)")}</notes> <notes>{snippets.get("World")}</notes>

Some beat outputs need to be lengthy, others to be short. The only way to adapt now is to have different prompts.with only this value changed. A better way would be to create a new variable available in the prompt system (with a default set in the prompt) and a ruler in the scene beat interface to adjust its value (bonus: a drop-down menu to select words/paragraphs/lines/verses). It could be written like this in the prompt: {length "default=400 words""}

Can we have the option in the character sheet to include the different relations of the characters to each other? Like: Brother, Mother, Father, Cousin, Best Friend, Girlfriend,.... So the AI knows how the characters' relations are. And with that have a family tree function? Overview of characters and how they relate in a chart. If it makes little sense, please delete the feature request :D

In Chinese text processing: Counting Method: Characters are counted individually (e.g. "我们"(we) = 2 characters, not 1 word) Unit Definition: Each Hanzi/Punctuation mark = 1 count Exclusions: Spaces/line breaks not counted (consistent with Chinese typesetting standards)