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.
- Simple Tracker
Adderal for your roleplay. - Grammar Guide
Kills simultaneous actions and em dashes. - 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 | Download 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 | |||
| UPDATED MiniMax M3 | 8.5/10 | It's a nice one! | |
| MISTRAL AI | |||
| Mixtral 8x7b Base Prompt | 8/10 | ||
| MOONSHOT AI | |||
| Kimi K2.7 Coding Base Prompt | Illarin | ?/10 | 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 | Illarin | 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. | ||
| NEW Xiaomi-MiMo-V2.6 | Illarin | 11/10 | ⭐ 🔥 They've been cooking in the house of Xiaomi. |
| Xiaomi-MiMo-V2.5 Base and Dark | Illarin | 8.5/10 | ⭐ Damn good storytelling and nuance. I love it! Perfect for fixable Dead Dove characters. Updated Dark Prompt. Ya'll can't fix 'em with the V2 prompt.😜 |
| MiMo-V2-Flash Base Prompt | Undefined | ||
| ZHIPU AI | |||
| NEW GLM 5.3 Base Prompt | Illarin | meh/10 | General RP ok. Not a big fan though. |
| GLM 5.2 Dark Prompt | 8.5/10 | Character driven rp. Characters don't change easily... and they will be proactive | |
| GLM 5.2 Base Prompt | 8.5/10 | Good for rp steered by yourself | |
| 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 with minimal settings 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. That doesn't mean they won't work on other providers or models... it just means it's unlikely to perform nicely.
- Third party providers often have their own filters and censorship. Keep that in mind.
- 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. My prompts just tickle the models at the right spot. 🫦
More answers here
😘