Evening-Truth
Roleplay Prompts
Sweetheart,
With each prompt you get some insights to the models and a spice rating 🌶 (Because I know you) and a ⭐ on the prompts and models I personally like the best. I'll let you know where they shine, and where they lack, where you can tinker and what you should avoid.
You get my honest opinion and sometimes even warnings. No sales bs.
So read carefully and stay hydrated. ❤
Helpful links. Probably.
- Narrative and Genre Guide
When you're sick of physical blows and shivers running down spines - Summary Prompt
Coherency booster that excludes sloppy interpretations by the LLM.
Roleplay Prompts
| Model / Link | Spice Rating 🌶 | Notes & Status |
|---|---|---|
| ALIBABA | ||
| Qwen 3.6 Base Prompt | 7.5/10 | |
| DEEPSEEK | ||
| Deepseek V4 Pro Base and Dark | 5/10 | Too passive, terrible character consistency. |
| Deepseek V3.2 Thinking | 5/10 | |
| Deepseek R1 0528 Realistic Roleplay | 7/10 | ⭐ |
| Gemma 4 31B | 7/10 | |
| MINIMAX | ||
| MiniMax M3 Base | ?/10 | WIP lemme work on it a little more. It's a nice one! |
| MISTRAL AI | ||
| Mixtral 8x7b Base Prompt | 8/10 | |
| MOONSHOT AI | ||
| Kimi K2.7 Coding Base Prompt | ?/10 | WIP Typical Kimi darkness. Still lacks in the understanding of tension and storytelling. |
| Kimi K2.6 Thinking Base Prompt | If anxiety disorder was an LLM it would be this one. I gave up on this one. Just so you know. | |
| Kimi K2.5 Thinking Base Prompt | LAWD HA' MERCY /10 | ⭐ |
| Kimi K2 Thinking Base Prompt | 6/10 | |
| Kimi K2 Thinking Dead Dove Edition | 6/10 | |
| Kimi K2 Thinking for HD Character Cards | 6/10 | |
| xAI | ||
| Grok 4.1 FAST Base Prompt | 9.5/10 | |
| XIAOMI | Performance highly depends on provider. E.g. Calls to Xiaomi are censored but it can get naughty on OpenRouter. | |
| Xiaomi-MiMo-V2.5 Base and Dark | 8.5/10 | ⭐ Damn good storytelling and nuance. I love it! Perfect for fixable Dead Dove characters. |
| MiMo-V2-Flash Base Prompt | Undefined | |
| ZHIPU AI | ||
| Z.AI coding plan and response quality. | - | A heads up for you. |
| GLM 5.1 Base Prompt | 7/10 | Better than 5. Still missing the grit of 4.6. |
| GLM 5 Base Prompt | 7/10 | Imo terrible for rp. Characters default to being apologetic crying messes... often. Hard user bias. |
| GLM 4.6 & 4.7 Character Driven Roleplay | 9.5/10 | ⭐ |
| GLM 4.7 Base Prompt | 8/10 | ⭐ Approved and recommended by Danna. |
| GLM 4.6 Realistic and Spicy | 12/10 | ⭐ |
What you should know about my Prompts:
- All prompts are written for basic samplers (Temperature, Top-P, Top K) and Chat Completion APIs to make sure they work on most platforms.
- I keep them short and simple so you can use them even when you have a tight token budget.
- Each prompt is tailored to the Model, not to the provider. Meaning a GLM 4.5 Prompt might not perform as well on GLM 4.6, or the R1-0528 Prompt on V3.2.
- Third party providers often use their own System Presets and censoring. My Prompts might not work when you call over a third party provider.
- You can, and should, change Formatting Rules, Content Rules and narrative perspective to your own liking. Please be careful when changing other parts of the prompt. Wording can make or break the whole thing.
- I don't write jailbreaks for censored models. There's enough uncensored LLMs out there.
More answers here
😘