0.5.31: gpt-5, hot model, bugfix

✨ story mode now supports image generation - prompts are now built to match the current location and characters on screen
✨ new pool location
✨ redesigned location screen with captions
✨ added claude-opus-4.1 (noticeably different from claude-sonnet-3.7, but costs way too much - 5× more, use with caution)
✨ support for gpt-5, gpt-5-chat, gpt-5-mini, gpt-5-nano

🛠 sd:
→ improved prompt generation for images
→ sd server (hot model) now auto-restarts up to 3 times
→ sd doesn’t like long prompts - for auto-generation they’re now forcibly trimmed to 540 chars to avoid crashes
→ max length for negative/user prompts limited to 270 and 180 chars
→ settings now have a “self description” field
→ fields for manually editing clothing and location
→ fixed a bug where the default LoRA was applied at game start, requiring opening settings to load the chosen ones

🛠 local speech synthesis chunk size increased from 200 to 450 chars
🛠 koboldcpp updated to 1.97.4
🛠 fixed openrouter model switching - no restart needed when changing from the popup

→ mega
→ gdrive

for the linux build, sd was compiled with updated libraries, it should work on ubuntu 24, unfortunately I can’t double-check, pls leave a comment if the local image model works for u

gpt-5:
temperature doesn’t work for new models - it’s stuck at 1, and top_p (which was 0.9 in-game) no longer has any effect. censorship hits hard on the “thinking” models (gpt-5, gpt-5-mini, gpt-5-nano), but can be partially bypassed by continuing sexualized plots with them after starting on gemini / claude-3.7 / gpt-4.1.
gpt-5-chat is better - censorship is about the same as gpt-4.1, maybe slightly more vanilla

sd: for better accuracy, raise cfg-scale to 8-9 and use extra LoRAs sparingly - only ones that affect overall style. LoRAs with baked-in poses/characters reduce relevance