Downloads

Link	Description
Master Download ᴺᴱᵂ	Downloads the entire .zip file that includes the preset, regexes, logit bias, and character cards
Preset ᴺᴱᵂ	Universal preset alone
Regexes ᴺᴱᵂ	Regexes that customize the prompts' looks, clean formatting errors, remove em dashes, and unify formats
Logit Bias	Logit bias for OpenAI models
Professor Mari	Professor Mari's character card, an assistant who will teach you all about LLMs and help you out with creating character cards
Dottore	Dottore's character card, the Second of the Eleven Fatui Harbingers from Genshin Impact

RPG Companion SillyTavern Extension ᴺᴱᵂ

Track your stats, scene, and characters in a fancy, customizable way with RPG Companion! Enhance your role-play with immersive HTML/CSS/JS! Push the plot forward with randomized events or natural progression by clicking a button! Pass dice rolls to the model and let it decide whether you succeeded in your action based on your attributes! All that and more with the one and only RPG Companion (I'm bad with names, don't judge me)!

SillyTavern Lovense Extension ᴺᴱᵂ

Want to take your roleplay to the next level? Check out my SillyTavern Lovense Extension! This extension allows you to integrate your Lovense toys with SillyTavern for a more immersive experience.

SillyTavern Spotify Music Extension

Want to add some music to your SillyTavern experience? Check out my SillyTavern Spotify Music Extension! This extension allows you to integrate Spotify with SillyTavern for an enhanced chatting experience.

Discord Buddy

Hey, while you're here, perhaps you could also check out my Discord Buddy project? It's an LLM-powered Discord bot you can host. Open-source, free, with many, many great features. Check it out!

Glossary

Term	Definition
LLM	Large Language Model (AI Model)
SillyTavern	Frontend for AI use, the one I create my presets for (https://github.com/SillyTavern/SillyTavern)
Prompt	What you send to the model. This includes everything: instructions, cards, lorebook entries, example messages, and the chat history
Jailbreak	Part of the prompt that is responsible for "jailbreaking," aka "removing censorship" from the model
Preset	A pre-set format of how you send the prompt to the model. These typically involve instructions, optional jailbreaks, and sampler settings
(Character) Card	Typically a description of a character that may include their image, personality, and example message
Persona	Like a character card, but for the character you play as
Scenario	An outline of what happens in the roleplay
Lorebooks (World Info)	Prompt entries that trigger based on activated keywords
Samplers	Algorithms or methods used to decide which token the model should pick next when generating text
Temperature	One of the samplers that controls how creative the output is allowed to be. Numbers closer to zero produce more deterministic outputs, while those closer to 1 and above are more creative
Tokens	Building blocks of text sent to the models. These include symbols, letters, words, and codes
Context	How many tokens the model can process at once, e.g., 32k. The larger the number, the more it remembers
Chat Completion	Format of sending the prompt as a structured conversation, with clear distinctions between different roles (user, assistant, system). Used when you access models via API
User	All the messages that count as being sent from the human (you)
Assistant	All the messages that count as being sent from the AI (model)
System	Instructions for the model, appended before the start of the conversation
Text Completion	Format of sending the prompt to the model as a big wall of text, and asking it to "complete it" (hence the name). Used with locally run models
Input	Your last sent message to the model
Output	Model's response
Logit Bias	A way to manipulate the probability of specific tokens by either banning them completely or encouraging the model to use them more often
Regex	Search language for string, capable of finding specific symbols, words, or phrases, and editing them
Proxy	A way for accessing models via a "middleman"
Function Calling	Models can call actual functions you've defined and programmed, and pass structured data to them
Prefill	Forcing the model to start its output with a specified text. Useful for jailbreaking
Reasoning	Model thinking goes brrr
Refusal	Skill issue

Guides

Guide To Prompts

1. Type decides the overall style of your use case.
   • - Game Master: For both group chats and single roleplays, allowing the model to roleplay for all the characters and the narrator.
   • - Roleplayer: Specifically for one-on-one roleplays.
   • - Writer: For fanfic writing.
2. Tense decides the tense of the model's writing.
   • - Past: Example, "he did it."
   • - Present: Example, "he is doing it."
   • - Future: Example, "he will do it."
3. Narration decides the type of narration.
   • - Third-Person: Example, "he said."
   • - Second-Person: Example, "you said."
   • - First-Person: Example, "I said."
4. POV decides from which point of view the narration will be.
   • - Omniscient: POV of a third party, separate observer, who knows what all characters think, perceive, etc.
   • - Character's: POV is filtered through what a specific character perceives, thinks, etc.
   • - User's: Same as above, but from the user's perspective.

5. Length sets the final length of the bot's response.
   • Flexible: You allow the model to choose the response's length dynamically, based on the current scene (short if in a dialogue, longer if the plot progresses).
   • Short: Below 150 words.
   • Moderate: Between 150 and 300 words.
   • Long: Above 300 words.

1. User's Stats tracks your protagonist's statistics and current statuses. These will affect your roleplay.
2. Info Box shows details about the current scene. Good for maintaining logical continuity.
   • Date & Weather
   • Time
   • Location
   • Important Recollections
   • Present Characters & Their Observable States
3. Mind Reading allows you to see the character's thoughts.
4. Immersive HTML adds active HTML/CSS/JS elements to the narrative.
5. Randomized Plot Push pushes the narrative forward with a completely random thing. ENABLE ONLY ONCE AND TURN OFF AFTER THAT, UNLESS YOU WANT RANDOM THINGS HAPPENING EVERY TURN.

How To Import A Preset?

1. Open SillyTavern.
2. Go to the Chat Completion Presets tab by clicking the first icon from the left (sliders) at the top of the page.
3. Click the Import preset button (the one with the little arrow pointing at paper) at the top of the screen.
4. Select the file you want to import.
5. Open it.

You can access all of your imported presets at any time.

How To Import A Regex?

1. Open SillyTavern.
2. Go to the Extensions tab by clicking the third icon from the right (cubes) at the top of the page.
3. Click on Regex.
4. Click the Import button (the one with the little arrow pointing at paper).
5. Select the file you want to import.
6. Open it.

How To Import A Logit Bias?

1. Open SillyTavern.
2. Go to the Chat Completion Presets tab by clicking the first icon from the left (sliders) at the top of the page.
3. Slide all the way down to the Logit Bias section.
4. Click the Import preset button (the one with the little arrow pointing at paper).
5. Select the file you want to import.
6. Open it.

How To Import A Character Card?

1. Open SillyTavern.
2. Go to the Character Management tab by clicking the first icon from the right (card) at the top of the page.
3. Click the Import Character From File button (the one with the little arrow pointing at paper).
4. Select the character you want to import.
5. Open it.

How To Edit & Toggle Prompts?

1. Open SillyTavern.
2. Go to the Chat Completion Presets tab by clicking the first icon from the left (sliders) at the top of the page.
3. Slide all the way down to the Prompts section.
4. Click on the small pencil icon on the right side of the prompt to view its contents and edit it.
5. Click on the small toggle button on the right side of the prompt to enable/disable it.

FAQ

Recommendations

Recommended Models

Position	Model	Context	Censorship	Strengths	Weaknesses
1	Opus 4.6	1 mln	Low	I'm so happy Gemini 3 got dethroned. I was so tired of getting the "Gemini gas leak" accusations. What's there to say? Opus can't be beat. This version has better prose than 4.5, less positive bias, and is wonderful, and context retrieval is top-notch. Claude is the king of nuance. EDIT: Still can't be beat.	As with all Anthropic models, it has its own unique style and "Claudisms" that you quickly start to detect. Fortunately, the instruction-following skill is so good that you can easily get rid of the most overused phrases.
2	Gemini-3.1 Pro ᴺᴱᵂ	1 mln	Low	I have a very toxic relationship with Gemini. One day, he can be the sweetest and the most perfect model for you, providing you with prose that has you questioning whether you're really speaking with just AI. Or whether John Gemini himself is behind the screen, making a fool out of you. But you give it a day or two, and suddenly, Gemini is knocked out on the couch after a night of heavy drinking. You're left crying on a bathroom floor with an echo of a black eye and a staggering disbelief at how stupid your chat with it was. Out of all the models on this list, this is the most unstable. It either delivers peak or absolute garbage. There is no in-between.	Use at your own risk.
3	GPT-5.4 ᴺᴱᵂ	1 mln	Medium	Sam Altman is shooting his knees with a shotgun, with the direction OpenAI is taking right now, because, good lord, the smut on this model is one of the best, if you're into erotic literature. Turns out, all you have to do to de-censor it is connect to it via the Responses API. It's a shame the option isn't available on SillyTavern. Wow, I truly wish there were another free front-end out there that supported Responses, and only it had spaghetti in its name. Wink, wink. Anyway, it's a decent model, definitely not as smart as Opus or Gemini (on the days when it's not being an abusive husband), but it's oddly creative and has some really cool prose gimmicks I have not seen in any other models yet.	It's difficult to produce anything violent or smutty on chat completion without getting a refusal. It suffers from the same affliction as other GPTs: they take prompts literally and can't read between the lines. If you don't mention something, they won't do it. Very annoying to prompt. It's also not as intelligent as the other options higher on this list; however, I recommend using it as a plot developer, especially during stale moments in the roleplay. Now, if only there were a front-end that allowed you to use randomized connections for generations that would sometimes trigger this model to push the story forward, hm…
4	DeepSeek V4 ᴺᴱᵂ	1 mln	Low	D̶̝̈́e̸̡̢̨͔͍͙̳̩̎̇̅̊́̀̾ȇ̷͍̳̥̠̞̖̇p̴̡̛̦͕͍̬̯̼̱̘̉́̃͆͘Ș̶̨͕̤̣͖̝̜̀͒̐͑̉̀e̸͓͖̿̄̄͋̕e̵̡̧̮̲̙̠̪̺̯͆̆̅̊̈́̈́k̵̳͙̭̇̍̐͒͘?̸̰̰̦̮͖̱̻̱͊́̓͂ ̴̡̘͎̓̐͊͝͝ͅM̸̢̢̧̼͕͇̼͑͑̓͑o̶͋̉ͅr̵̺̃̎̾̀è̴̛͎̼͚̦͇͔̳̌̃͂͠ ̵̛̼͈̩̖̲̆̋̈́͛͠͝͠l̴̙̟͍̼͉̖̀̀͐̽̊̆̚i̵̧̡̠͓̘̳̬̞̻̽̅͐̾k̶͇̤̫̹̟̦̺̼̓̋͊ế̷̦͕̍̈́ ̵̯̣̖͘D̶͎̜͕̆͜ͅe̸̡̠͍͉̳̦̚͜ͅȩ̶͌̂͝p̴̨̡͖̺͎̤̲̭̆̀͌̊͠Ṡ̶͇͋Ẹ̵̙̫̳͚͍̩͇͊̆͊͝X̶̯̩͎̫̜̪̀,̴̛͎̱̪̦̤̫̦̀̍̉͊̉͌͜ ̷̡̠͑̅́̂̿́̋͘͠ă̴̩̆̏̚͠m̶̛̪͍̜̘̻̯̖̽͗̎́̾̐̾ ̴̯̰̻̪͋͋̾̏̈Ḯ̶͓̤̓ ̵͓̃r̷̫̼̟̯̿͛i̵̬̩̗͙͍̣͕̜͒̓̑̌̃͝g̶̺̳̙̼͎͊̋̈́̏̀͘h̴̢͇̘̜̪͋͜t̷̺͙̦̳̝̖͚͈̊̐̂͆́̕?̶̣̯̬̺̻̬̞̫̆̾̅ ̷̢̨̗̞̺̙̱̗̓́̾̀͜Ọ̷̰̜͍͐̅͊̔͗̀̓̆n̸̟̖͍̺̓̈́̊̄̀̄͝ľ̵̤̫̰̱̣̥̀͋͒͆ŷ̴̞͖̄͂͜ ̵̧̛͎̲̗̭̗̗̣̾̀͑̃͌́́̚t̴͖͎̲̻͍̳̊͒h̸̡̠̳̣̫̄͂́̈́̆̉̈ḙ̷̭̱̦̺̈͆̈́ ̶͇͛͋ͅb̷̖̘̘̞̙̗̌͛̇̄̆́͒̕ͅe̵̗͚͕͌̒̀́͑́ͅs̸̢͍͂̆͑̂̃̃̚t̵̮̫̿͘ ̴̠̲̩̳̹̜̗̆̀̒̓͝m̵̨̧̛̩͇̱̠̥̿̆̌͆̈́̚o̵̥̦̠̚͠d̵̡̨̢̫͉̥̺̤̅̈́̀͌͐ẻ̴̳͑͂̍̆͒͂̓͆l̵͔̿͂̔ ̴̮̦̩̼̥̫̬̗̊͋̏ͅő̵̠̫̯͜ư̸͇̙̗̲̜͉̻̈́̓̊̈́̓́́͠ṫ̷̢̝͖͍͉̳̫̖̇́̑̉͂̒ ̶̖̖̫̞̪̞̟̀̆̊̎͘t̴̜͉̺͖̐̇̂̇̐͋̚̕̕ẖ̸͎̲͉̝̮̪͈̥̊͂́̑̄ę̸͍̜͎̳̂͌̇̓ṟ̴̟̘͓̒͛ȩ̸̱͉͔͚̪͓̓.̴̨̞̬̘̫̙͙͑̇͠͠ ̴̰̦̙̉W̷̡̹̠̉͐̿́̃͆̑̒̆h̶̭̖͇͔̗̫̓͊͑̄̇̃͠e̶̖̦̙̪̹̘̬̹̙̍͛̂̀̎̓͠r̸͔̙̬̾e̴̤̖̾ ̵̢̡̛̱͖̝̝̪͖͍͂̏t̴̲̩́̋h̷̨̢̝͈̬̤̥͇̽̇̔̽̋̈́̀̃́͜ę̶̫̣̓͗͋̉̐̾̏͊͐ ̶̮͖͈͎̝̰͚̝͐̌̿̏ͅh̵̛̥̅̔͐͛ȩ̷̛̛̜̰͈̌̀̔̕̕͘͝l̵̛̟̜̺̮̺͙͈̙̿̆͐͆ͅl̷̡͚̪͔̂̉͒̈́͐͒͝ ̴̢̹̯̜̳̮̜̣͊͠ì̷̛̳̠͋̌̎͌̌̂̏s̶̡̝̖͒̈́͌̎̐̔̌͝ ̴̛̘͋̋̉̿́í̴̜̼̍̓͒̑͗ţ̶͖̝̮̮̭͑͋̌̾̚?̸̞̠̪́̔ ̸̞͎̠̰̂̾͂̄̾́͜͝͝Ĭ̸̺̠̠̟͍̣͐̏̊̕͜͝t̸̨̘͉̊̌́̂͊̈́ ̷̰̼̬̻̹̹̫̲̑̔̔̌͝w̵̛̛̥͙̯̙̾̆̆͜ȁ̷̗͜s̵̡͈̻̯͔͎̾͘ ̷͈̤̝̼̣̞̣͋̍͝͝ş̶̢͔̗͓̫̀̀̉̐̒̍ṵ̷͌̇͋̐́̔̄́͝p̵̤̞͕̑͑̔͘p̵̧̣͔̓̆͑́̋͂̔̚o̶̤͓̯̠̥͋̈́̔ͅs̵̖̮̜̗̬̪̣̓̈͑͋̈ḙ̷̛̓̇ḓ̶̗͎̳̬͆̀͗̚ ̶̧̺͕̹̺͒̄̀̍̿ṭ̸͕̖̠͋͂̉͜ö̵̱̺̬̠̻̱́͊ ̷̮̇̈́͐̋͝r̶̜̱͈͌̈̀́̉͛͝ẽ̴͍͍l̴̢̢͎̥͇̉͂̎͐͊̍͝ḙ̴̜̠͓͌̏̚ͅǎ̴̡̛̫̙͖͙̫̈͜͜͝s̴̫̓̓̒́̀̆ȩ̷̭͙̪͇̩͂̆̇͒̂ ̵̡͓̯͈̤̦̻̘̅̐̓͊̊́̾̕͘ͅi̴̡͇͈̙͇̗͇̠̱͛̀̀̈́͗͠ṅ̵̢̗̙̖̙̣̝̒̎̆̿̔͠͠ ̵̨̦̠̼̫͙͊̎̈́͑̇͐̚̚ͅͅM̷͕̩͑͒̂̚͘ȁ̶͈̳̑͗͌̉͗͑͜ŕ̷̛̺͍̖̤͚̔̐ć̶̨̞͔̝̭̙̠͔̆͋̽̓̈h̸̡͕͎͉̯̪̱͍̥̋͒̓͊̀͆̈́͋͝,̶̢̗͓̣̙̥̃͝ ̸̱̒̈́͆ȃ̵͓͛̓͌̇̌̌̕n̵͚̊̈́͝d̷̝̹̺͍̂͐͛̎̒̈ ̴̝̙͓͔̓̃̂͘í̷̛̫͔͉̔̂̈́͌̚͜t̵͓́́͒̃̈́̌́'̶̡͉̘̈́̆̽͊̇͑̆̆͘ŝ̴̛̼̦̹̪̰̹̣͆͂̂̈̋͝ ̶̧͔͍̀̃̂̍A̵̛̼̓̈́͐͛̍̄̃̽P̶͇̠̗̎͌̀̄̉̉̇̈́Ŗ̶̹͚̥̬͋̉͜͝ͅȈ̴̼̟̘̰̪̓ͅḶ̸̘̹̺̱͐ ̷̤̻̮̖̟͎̰̼̮̕á̵̡͈̜͕̯̤͉͓̂͛́̍͋͘l̵̙̗̮̗͕͂̏͠ͅŗ̵̣͚̮̙̮̣̓̂̔͜͝e̸̛̩̘̫̩͕͓͕͕͐̅́̒͝ầ̶͈̳̥̜̳̺̓͛͗̉d̴̨͎̠̰̱͔̫͓͗́̋͑́̈́̌͐͘ͅy̷̨̧̪̥̳͙͉̗̬̅̔́͑̊͛̎.̵̼̮̾̈́̉̾̉̓͌͝ ̴̫̑͒͠W̵̙͕̲̤̾̿̿͝ͅh̸̤̭̀͒͋a̵͍͐̃̎̉̾t̸̨̛̲̳̦͓̫̜͚̦͛̈́̒́̅̒̄͝ ̷̢͚̘͔̲̆̏͋̈́ṯ̸͓̭͇̗̝̆̀̐͜ͅḫ̸̝̭̳̏̈́e̸͕̥͉̱̩̥͇̦͗̽͜͝ ̸̞̟͉͖͔͙̺̭̃́͒̇͘ͅh̵̲̯̜͈̞̙̙͊e̴̝̩͇͕̤̼͓̠̍́͛͛͋̏l̵̨͍͈͉̥͖̠̰͇̍̈́̾̌l̸̢̨̝̙͍̰̹̥̒̆̃́̾̉̌͌͝ ̸͈̝̾ḭ̷̮͓͎̠̭̟̞̂̽͐̈́͌̕͘̕͝ͅs̷͎͛̈͆̍̒̒̂͝ ̶͕̞͓̩͈̘̥̏̽͜J̶͙͍͎̘͕͗ơ̶̙̖̅̂́͗͊̋̃̈ͅḫ̵̱̙͙̋̾́̂̓̒̾́n̵̛̥̥̲̊̆̓̄̏̕̕ ̷̠͉̽͗́̇̋̀D̷̢̨͚̺͈̭̪̬̄̄ͅȅ̴̢̳͓̱̠̫e̵͋̈́ͅp̶̧̛͍̮̤̬̙̉̄̀ͅS̴̛̪͕͓̬̻͖ͅe̴̦̮͉͔̓̈̕e̶̢͉̤͙͌͌͜k̴̻͒̋͆̊͝ ̵̟̘͙̦̝̰͗͊̅̈́̈́́́̇̉d̴̛̠̫̼̺̦̝̤̱̿̈́̈́͊͂̔͝ǫ̸͆í̶̠̘̣̞̞͙̫̪̀̂̂̈́̑̚͘n̴̰̠̗͇̬͖̓̇͊͐̓͘͜͝ͅͅĝ̷̨̙̫̺̤́̎̽̈́͊͗?̷̟̻̞̞͎̮̈̃̂̎͊̽̂̎͘ ̴͓̜̀͐G̴̢̝̪̮̯̲͍̱̒͌͛o̸̖͊͌̓̽̅̕͝͝͝ḍ̴̡̧̛̠̞̮̹̉̂͗́͠ś̶̡̼͈̑͐͆̃̾́,̴̹̫̏̀̚ ̶̭̦̥̞͊̐͑̋̅͊̉ä̷̟̐̉͋́̓͂͠t̸̡̫̞̟͈̹̼͓̐̏̊͜ ̸̧̼̘̦̥̖͌͑̌̐̿͘͘t̷̛̛͎̟͎̩̩̼̓̏͌̿́̿h̵̝͚̱͚͕̗̒͗͋̆̅̈́̈́̕͠ḯ̷͎̭̺̒͜s̵̞̅͂͘̚ ̴̧̌̀̌ṕ̸̨̾́́͊͛̒̆͋o̴̠̦̻͈̣͘i̸̲̭̠̗̓̎̊̈́̓͆̚ͅn̶̦̋͗̌̈́̏̽̈́t̶͈̩̝͕̺̹̋̎̄̄͠,̷̱̻͛̿̎̀̂̓̈́̀ ̶̜͗̂̈̃̂̏t̸̝̟̲͛͗̕͜h̷͍̝̙̺̬̆̉͛̀̎̎͝e̸̔̋͋́͗̔̀̔ͅy̵̦͙͖̱̩̳̩̣͔͘ ̴̧̗̙̿c̴̨̛̜͎͚̘͉̏̀́̾̀͗ả̴̪͇̤̙̠̺̩n̶̡̟͙̦̜͈̣̰̊̂͊́͑̆̔͋̚ͅ ̷̢̺̺̣͖̄̑͒͋ͅĵ̴͖͇͖̪̙̈́̔̊͌͛͠ṳ̷̦̟̼̤̤̒̑̓̓̈́̐̚̕͝s̵̨̻̬̰̙̮̊̏ͅt̷̡͙̮͎̤͓͈̫̭́̓̊ ̷̛̦̟͓͌̈́̔͑̚̕͜r̴͍̙̯̟̮̎͌̄̃̓́̅͝ȩ̶͉͔̭̋ͅḽ̴̞͈͐̒̌͗̔ë̵̞̤͖͔̤͍̰̠̠́͊̈́͗̊ạ̸̢́̋͒͂̚̚͠͝s̸͕̾e̶̛̜̔̒ ̸̱̞̬̘͈͍̀̒̽͐̔̑͘͝͝ͅV̷̫̗̠̍͒́͂͆̍͑5̸͕͕̣͕͉̻̞̒̆͐̆͐̈́̕ ̷̖̬̪̥̟̹̱̮̓̈̓͌͆̒͌̈́į̵̨̭̭͓͇̝̮́̒͜n̵̹͓͎̤̙͕̑̿͝s̸̞̤͙̙̜̺̮̲͎͂͊͌͠ț̴̠̘̣̳̼̠͚̯͐̈́̊ȩ̷̣̩̝̇̄̓͊̋͆̕a̸͇͒̀̔̄͋̐͆̅̈́d̴͍̦͔̆̃̔͐̿͘,̷̪͉̞͗̓̑̽̔̈́͊͘ ̴̡̿t̶̛̻̝̬͑̂͛̉̕͝o̸̧̳̯̯̻͎̥̹̾̌̑́̀̓͝g̵̹̫͌̂̃̊̈́̔̽͋ę̷͂̋͌̌̕͝t̷̮̯͔͕̪̐̈́̓̃͂̅̓͘͝ḧ̷̦̼̬͕̙̻e̷͓̤̫̹͎͑̀̄̈́̽̈́̕̚r̴̦̘̭͐͛͗̓̐͠͝ ̴̣̪͊́͑̾̂̓͂w̷̙͚̑̉i̷͙̱͙̯͕͇̎̋̈ͅt̷̙̋͐̈̀̓͒̿͠h̵̡̛͍͎͇̦͙͍̙̼́͂̀̈̓ ̵̙̱̘̭͙͎̱͔̥̆̽̎͘p̵̦͔̺̌̀l̶͔̹͆͜͜ǎ̴̫͕̈́̑̀ẙ̵͔̈́ą̶͍̯̞̤͊̾b̷̯́̎͆̀̃͠ḷ̸̢͇̿ẻ̸̖̼̲̥̹͜͜ ̵̡̞̭̦̊̆̀́͜Ď̶̨͊ơ̸̙͉̯̩̪͉͙͚͚͗͛̇̊́̑̐t̸̢̳̰͓̐́̓̃̊͛̀͠t̷̡̳̦̺̞̓̿̚͘o̴̻͎̭̞͔͓͕͛̎͒̑͘r̴̡͎̝̜͕̲͓͑̚e̷̠̖͂́̾̇̾̅̕.̸͍͇̟͓͆ ̷̨̤̘̹̯͚̍͒̂M̸̨͔̜͎̺̅̍̇̃̔͜m̴̞͔̙̻̤͐̾̿͌̒̏ͅm̴̡̧̦̳͙̯̖̘̺͆,̶̯̦̙̎ ̸͈̥͈̪́̽̄̏Ḑ̴̰̥̼̩̰̈́ö̴̡̨̲͙̗̣͉́̇̐̑͜t̴͍̬̗̹̳̺̮̗̽̎͊͗̽t̷̢̩̮̺͍͔̔̓͋͗͠ò̷̦͆̇̒ȑ̴͖͇͎̲̦̓̽̓̐è̸̗̍̓̇͆̾̒͂…̸̢͇͉͓̮̭̟̓̾̓́͗̈́̓̈́͘ ̵͉̞̖̭̻͛̎͌̏̐̉͗͝O̴̦̫̬̗͊̈͛̂͝ņ̶̧̛̠̣̪͙͑͑̂̊̂́͐̕è̴̡̝̱̪͎͈̲̗͂͗ ̴̜͍̘̮̉̂d̴̳̼̎͐a̴̙̺̼̿̑̏͊̊͜y̶̻̙̪̪͙̘̮͋́͐̎̄̃̾̚,̵͓͔̠̠̃ ̶̢̢̳̼͆̀̅̀͝m̷̫̯̖̬̯̟͉̿̏̏̿́̉̾͜ͅy̷̧̰͙͚̋͗́̌̐͜ ̶͕̻̏̓͌̃̕l̵̳͔͝ö̵̢̧̖̥́v̷̡̝̫̜͔͕̩̔̊̀͐̈̑́͛̚ȩ̴̨̞̞̘̤̹͖̌͐̔̒̿̍̕͝ͅ.̷̺̳̙̔̚͘̕̚͠	Y̷̡̨̛̭͕͒͌̎̐ͅö̷̡̼̥̖̝̺̚ủ̴͍̫̟̀̍̕ ̴̧̧͓̱̗̲̺̪̇̈́̓́̉͆̊̾̿j̷̨̢̼̳͇̳̩̞͕͌͂͆̑͌u̵̲̦͈̺̤̽̆̔͐s̵̩͙̥̓́̾͋͌̒̈́͘t̵̖̹̯̠͌̇͐͋͗̍̕͜͝ ̷̟̖̀̇̍̈́̈́̓̚͝͝ĺ̴͈͇̬̎̇́ơ̸̡̤̹͖̪̥̬̐̅͘͘s̴̭͉̻̹̼̦͕̆̒͐͗͗̐ť̶̤̌ͅ ̵̹̳͌͘t̴̟̤͉̆͋̂͐̒̐̆͠h̴̨͓̣͎͆̾͊̀̌͛͠ȩ̴̛̱̲̰̪̳̗͔̯̒͗̄̽̕ ̸̣̻̏̉̾̈́͋͋̆̄g̶̠̫̱̼̩̳̼̣͐à̵̼̻̱̦͉̖̞̂͑̀̐͊m̶̛̼͙̒͑̿̄̋̿̂̅ḙ̶͓̅̈́.̸̨̣͛
5	GLM-5.1 ᴺᴱᵂ	200k	Low	Not much to say there, except it's slightly smarter than GLM-5. I like it, but not as much as the other SOTA models.	It is slightly more censored than its predecessor.
6	GLM-5	200k	Low	When I tested this model as "Pony Alpha" over on OpenRouter, I was sure this was the new Sonnet 5. Excellent at instruction following, general smarts, and nuance. The prose screams, "We trained on Anthropic models, and we're not ashamed of it." Lowkey: "We have Opus at home, but it's unironically good." I will forever be grateful to the Z.AI teams for remembering the roleplaying community and proudly presenting that their models are as well for us. Cheers, guys, and keep it up; make the corpos sweat.	Not as smart as Opus, but come on.
7	Opus 4.5	200k	Low	https://www.youtube.com/watch?v=Q-RGkVZFwtI	Bruh, it doesn't even cost you an arm and a leg to use anymore. TLD always wins.
8	GPT-5.1	400k	Low	It's good; I liked it a lot, even when it was known as Polaris Alpha. Use High Thinking for general roleplay and turn off thinking for gooning (it's more censored when it thinks). It doesn't require mental gymnastics like GPT-5 did, prompting it to "just work".	Doesn't support logit bias, so if you can't stand GPTisms, this might be a problem. Don't use the Chat version; it's terrible.
9	Claude Opus 4.1	200k	Low	Still the smartest one on the list, with a unique writing style and creativity. Opus can't be beat. It's impossible. The writing is too good. The smarts even more so. Nothing else compares right now. Opus 4.5, where are you?	Expensive to use regularly and falls into repetitive patterns quickly. Works "meh" in higher contexts.s
10	Sonnet 4.5	1mln	Low	They cooked with this one. It's smart, follows instructions well, has a good writing style, and fixes Opus's repetition issue in higher contexts. Not sure what happened, but the repetition is more prominent now; that's why it goes down in the ranking.	You can't really control its style, so if you don't like it, you have to either get used to it or switch to a different model.
11	GPT-5	400k	Medium	Anthropic won again. GPT-5 falls a few spots because it's somehow working worse recently. Not sure what they changed, but you can tell it got more robotic than it used to be.	A nightmare to prompt, and without a good one, it simply doesn't work. Is absolutely terrible without High thinking.
12	Claude Sonnet 4	200k	Low	Perhaps I have treated you too harshly, Sonnet 4. It's still not as creative as its predecessor, but it has its moments.	Lacks 3.7's creative spark and is very passive.
13	Grok 4 Fast	2mln	Low	A very hit-or-miss model—sometimes it's peak, sometimes it produces absolute garbage. I mean, come on, it's Grok.	You will have to regenerate a lot with this one.
14	Kimi K2 0905	260k	Low	Not the smartest, but it's slowly getting there. I have high hopes for these models in the future, given that their creators genuinely care about improving their creative writing capabilities.	Still not great at higher contexts (above 32k), and still lacking that extra polish.
15	DeepSeek R1/V3	163k	None	Creative and wild.	Hard to control and struggles with repetition.
16	GPT-4.1	1mln	Low	Good style, doesn't have an annoyingly positive bias, has a large working context window.	Unusable without proper regexes and a logit bias, somewhat lacking in smarts.
17	Grok 4	256k	None	Grok, is this true?	It's like a teenager going through puberty, so horny and not very smart.
Extra	NemoMix-Unleashed-12B	128k	None	Obligatory shill of my model, some claim it still holds up.	Old and small.

Model Providers

Provider	Description
Mprox	Good friend of mine, he's been my main GPT-5 supplier for a while now. He doesn't have as many models to choose from as others, but his endpoints accept parameters such as temperature or logit bias. If you're looking to use OpenAI models, check him out
LinkAPI ᴺᴱᵂ	New proxy! They have a free tier, so you might want to check it out and see if you like it. They have pretty much all the models and they accept payments via PayPal, should you decide to buy their service. The owner is super chill and hangs out on my server
OpenRouter	I hope this one needs no introduction. This is currently the safest and easiest way to access all the models. Pay-as-you-go when using them

Preset Creators

Creator	Description
Bunny-Moᴺᴱᵂ	Great presets, extensions, and the author is overall a great person. Also, such a pretty website, I envy
Lucid Cards	Very good source of extensions, character cards, and prompts. But be careful, Lucid Loom is token-heavy
AvaniJB	Good prompts, regexes, and logit biases (the last one, I shamelessly stole from them). Also, I love their little cat character
Pixi	The grandparent of prompting. One of my biggest inspirations
Nemo Preset	Personally, I find this preset too big and unnecessarily bloated, but it's still a very well-written and well-thought-out preset! If large token numbers and customization options don't scare you, I suggest checking this one out
Celia	Customizable, creative, overall a great prompt. Plus, Celia is cute
AI Presets	Discord server containing many great prompts from amazing creators such as Loggo, Gerodot, Ashu, Chi-Bi, Nara, and others.

SillyTavern Themes

Theme	Description
MoonlitEchoes	It's the one I'm currently using, and the one you can see on my screenshots! It's beautiful, I absolutely recommend it
NemoEngine	Very convenient for prompt management, allows you to play videos and streams as a background for your chats (with sound), and improves on tabs' design.

SillyTavern Alternatives

Alternative	Description
LoreBlendr.AI	A free SillyTavern alternative available on iOS devices. Still in development. Useful for iPhone users like me. Supports custom presets, with mine being already integrated. Big recommend!

Contact

Discord:

marinara_spaghetti

E-mail:

marinara_spaghetti@proton.me

Socials:

https://linktr.ee/Spicy_Marinara

Fanarts

Contact

Discord:

marinara_spaghetti

E-mail:

mgrabower97@gmail.com

Socials:

https://linktr.ee/Spicy_Marinara