# Elise’s Advanced Prompts for DeepSeek & GLM @softelise on Discord |πŸ”— [JanitorAI profile](https://janitorai.com/profiles/73dae26b-3e64-47d5-b1a9-8aa002fb317d_profile-of-soft-elise) | πŸ”— [My Carrd ](https://softelise.carrd.co/) πŸ”—[Need help? Have feedback? Want to request a new Module or AP? Click here to join my Discord.](https://discord.gg/vvvdT44S7k) *** #### How to Use: * 16k-32k context (bump this up ONLY to create chat summaries (guidance coming soon), see Tips and Resources for more info. * Temperature: Deepseek, 0.5-0.6 temperature. GLM 4.7, 0.8-0.9. I usually prefer 0.8. * Should be noted that these ARE higher context APs with a token count \~900 each. Expensive, but for a good reason. * Token limit should be set to zero. (unlimited/technically 2k tokens) * Advanced Generation settings should all be set to OFF. (I may have different guidance for this in the future; needs more testing.) * If you use the official DeepSeek API, the Advanced Generation settings appear to do nothing, as the official DeepSeek API prevents overrides to the Top P/Top K parameters. * If you're using OpenRouter/Chutes/other, avoid touching these, it will affect the outputs. * Copy everything from the Prompt Page you want to use into the advanced prompt. [**Tips for Writing with DeepSeek + RP examples**](/elises-aps-docs/tips-and-resources/tips-for-writing-with-deepseek.md) {% hint style="info" %} **Why should you use my prompts?** *These prompts contain something unique: an override to how the LLM measures user engagement. By specifically telling the LLM that you're engaged in the prompt regardless of your response length/latency, we're providing it consistent positive reinforcement for how it's writing every time we send an input call β€” and reinforcing your agency.* {% endhint %} ### Advanced Prompt List #### πŸ“ [GLM 4.7 - Assistant's Toolkit](/elises-aps-docs/advanced-prompts/glm-at-assistants-toolkit.md) - NEW! Version 1.0 β†’ Primary function: Augments GLM's natural thinking process with tools and definitions to enhance long-form roleplay. Works with GLM versions 5+ as well! #### πŸ’¬ [NAP - Narrator Prompt](/elises-aps-docs/advanced-prompts/nap-narrator-prompt.md) - NEW! Version 1.0 β†’ Primary function: Not a traditional roleplay prompt. This one the LLM will write for both you and your character to create a story. Use it when you're feeling lazy. Works with all GLM and DeepSeek versions. #### 🌸 [CRP - Collaborative Roleplay Protocol](/elises-aps-docs/advanced-prompts/crp-collaborative-roleplay-protocol.md) - ✨ NEW Version 3.0 ✨ β†’ Primary function: Long form roleplay that prioritizes player agency, rich prose, complex dynamics and characters. Bread and butter prompt, start here! {% hint style="success" %} Patch notes for 3.0: Removed Input Recognition Guide section. Replaced with RPRF Prohibited Tactics Section! {% endhint %} {% hint style="info" %} For CRP - Recommend using OOC as pacing indicator if the AI isn't matching at any point. \ \ Example: (OOC: Keep responses short here to ensure back and forth between our characters in this tense scene. Adhere to protocol strictly.) {% endhint %} #### [‼️ RPRF - Roleplay Response Formatting](/elises-aps-docs/advanced-prompts/rprf-roleplay-response-formatting.md) - Current Version 1.4 β†’ Primary function: Create strict examples and priorities for how the AI should format their responses. Robust prohibited tactics and pacing indicators. * Strengths: Great with multi-char bots, doesn't write for you, good for smut, avoids cringe. * Weaknesses: This prompt is slightly more **passive** and strict – the AI will adhere to this, but it won't take the reins and drive the story forward as much. If you want a slow burn, THIS ONE. #### 🌹 [ROSE - Rapid Onset Smut/Erotica](https://elises-aps.gitbook.io/elises-aps-docs/~/revisions/PKAK6ObE0W9cZto2pKZg/advanced-prompts/rose-rapid-onset-smut-erotica) - Current Version 1.0 β†’ A quite filthy and slutty little prompt that does exactly what you think it does, you animal, you. #### πŸ’‹ [KISS - Keep It Simple, Sweetheart](/elises-aps-docs/advanced-prompts/kiss-keep-it-simple-sweetheart.md) - Current Version 1.0 β†’ Highly condensed and simplified paragraph format version of RRPF, designed to maintain the core ideas at a very low token count. Does not perform as strongly as RPRF, but if you need the tokens for other means, it works. ### Module List Paste these at the bottom of any other prompts to supplement them. #### ❄️ [Chiller Doms - No Primal Play Module](/elises-aps-docs/modules/chiller-doms-no-primal-play.md) β†’ Add this if you're sick of "claiming", "ruining", growling "mine" in your ear, the usual. #### πŸ’­ [User Thoughts and Off-Screen Content Module](/elises-aps-docs/modules/user-thoughts-off-screen-content.md) β†’ Use it if you're really struggling with DeepSeek taking control of your character, and you like to write your character’s thoughts and actions offscreen. #### πŸ“” [OOC Module](/elises-aps-docs/modules/ooc-guidance.md) β†’ Can use this with any of the prompts if you like to yap or have DeepSeek talk with you spontaneously OOC. God forbid a girl likes to yap sometimes. --- # Agent Instructions: Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter: ``` GET https://elises-aps.gitbook.io/elises-aps-docs/elises-advanced-prompts-for-deepseek-and-glm.md?ask= ``` The question should be specific, self-contained, and written in natural language. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.