sillytavern

Publicly shared presets, lorebooks, characters and whatnot.

Presets

Voyage (v5.1)

Links:

• Announcement

• Preset file

• Improved CoT

• Improved NPC interactions
• Improved PbtA rolling conditions
• Improved user agency
• Rewritten to positive prompts
• Reduced looping
• Reduced grammar mistakes
• Removed redundant prompts

Tested extensively with Unsloth's Gemma4-31B-IT QAT Q4_K_XL, MTP enabled, 32K BF16 context. Model download: link

Work with: * Mistral Small 3.2 * Magistral Small (2057/2509) * Gemma 4 (E2B, E4B, 12B, 26B-A4B, 31B) * DeepSeek (v3.2, v4, v4.1) * GLM (4.5/4.6/4.7/5.0/5.2/5.3) * Gemini 4 Argon * ...and many others

Voyage (v5.0)

Links:

• Announcement
• Preset file

Builds off Voyage-v4-exp2.

• Reduced token usage
• Improved world dynamics
• Improved NPC interactions
• Rewritten to positive prompts
• Much better prompt adherance
• ...and many more things

Tested extensively with Unsloth's Gemma4-31B-IT QAT Q4_K_XL, MTP enabled, 32K BF16 context. Model download: link

Work with: * Mistral Small 3.2 * Magistral Small (2057/2509) * Gemma 4 (E2B, E4B, 12B, 26B-A4B, 31B) * DeepSeek (v3.2, v4, v4.1) * GLM (4.5/4.6/4.7/5.0/5.2/5.3) * ...and many others

Voyage (v4.0-exp)

Links:

• Announcement
• Preset file (exp1)
• Preset file (exp2)
• Preset file (exp3)

Experimental releases.

Tested with Unsloth's Gemma4-31B-IT QAT Q4_K_XL, MTP enabled, 32K BF16 context. Model download: link

Might work with other non-Gemma4 models.

Eval (v1.0)

Links:

• Announcement
• Preset file

A playground of various rules to experiment with. Meant as a development resource over normal use.

Tested with Unsloth's Gemma4-31B-IT QAT Q4_K_XL, MTP enabled, 32K BF16 context. Model download: link

Might work with other non-Gemma4 models.

Voyage (v3.0)

Links:

• Announcement
• Preset file

Rebuild from the ground up.

• Reduced token usage
• Reworked skill check
• Improved backstories
• Improved NPC dialogues and interactions between NPCs
• Improved prose
• Fixed many issues.

Tested with MTP enabled, 32K BF16 context on the following models:

• Unsloth's Gemma4 31B IT QAT: link
• Unsloth's Gemma4 26B-A4B IT QAT: link
• Unsloth's Gemma4 12B IT QAT: link
• Unsloth's Gemma4 E4B IT QAT: link
• Unsloth's Gemma4 E2B IT QAT: link

It might work with other non-Gemma4 models.

Voyage (v2.0)

Links:

• Announcement
• Preset file

Based on Voyage, I tried to improve the roleplaying experience by introducing cause-and-effect.

• Bind GM to assistant role instead of "you" to prevent talking as User
• Consolidated NPC / Location / Scenario generation
• Improved tag-based generation (uses cause-and-effect)
• Improved PbtA Core skill check triggering
• Use scenarios instead of events, with clear definition
• Improved writing instructions to reduce slop (staccato overuse, "not x but y")

Tested with Unsloth's Gemma4-31B-IT QAT Q4_K_XL, MTP enabled, 32K BF16 context. Model download: link

It might work with Gemma4-12B-IT QAT, Gemma4-26B-A4B-IT QAT and other non-Gemma4 models.

Voyage (v1.0)

Links:

• lAnnouncement
• Preset file

Based on Moonlight, I turned it into a Powered by the Apocalypse (PbtA) "lite" experience. The idea here is PbtA systems have high-quality prose and a really simple yet effective decision-making framework. By just using it's core, Gemma4 is already writing much better interactions and dialogue.

• Added GM notes functionality
• Added tracking notes
• Added a tag system (akin to Dungeon World's tags and Pathfinder 2e's traits)
• Improved NPC creation (now using tag system)
• Improved location creation (now using tag system)
• Improved writing instructions edge-cases
• Improved model affirmations
• Streamlined naming rules
• Removed Chain-of-Thought (Gemma does it much better by default)

Tested with Bartowski's Gemma4-31B-IT Q6_K_L, 32K Q8_0 context. Model download: link

It might work with Gemma4-12B, Gemma4-26B-A4B and other non-Gemma4 models.

Moonlight (v1.0)

Links:

• Announcement
• Preset file

A simple chat preset which helps improve Gemma 4 31B's prose and adds randomization to swipes.

Tested with Bartowski's Gemma4-31B-IT Q6_K_L, 32K Q8_0 context. Model download: link

It might work with Gemma4-26B-A4B and other non-Gemma4 models.