NEW: Added Image Inpainting support to StableUI, and merged inpainting support from stable-diffusion.cpp (by @stduhpf)
You can use the built-in StableUI to mask out areas to inpaint when editing with Img2Img (Similar to A1111). API docs for this are updated.
Added slider for setting clip-skip in StableUI.
Other improvements from stable-diffusion.cpp are also merged.
Added Zenity and YAD support for displaying file picker dialogs on linux (by @henk717), if they are installed on your system they will be used. To continue using the previous TKinter file picker, you can select "Use Classic FilePicker" in the extras tab.
Added a new API endpoint /api/extra/json_to_grammar which can be used to convert a JSON schema into GBNF grammar (check API docs for an example).
Added --maxrequestsize flag, you can configure the server max payload size before a HTTP request is dropped (default 32mb).
Can now perform GPU memory estimation using vulkaninfo too (if nvidia-smi is not available).
Merged Llama 4 support from upstream llama.cpp. Qwen3 is technically included too, but until it releases officially we won't know if it actually works.
Fixed not autosetting backend and layers when swapping to new model in admin mode using a template.
Added additional warnings in GUI and terminal when you try to use FlashAttention on Vulkan backend - generally this is discouraged due to performance issues.
Fixed system prompt on gemma3 template
Updated Kobold Lite, multiple fixes and improvements
Added Llama4 prompt format
Consolidated vision dropdown when selecting a vision provider
Fixed think tokens formatting issue with markdown
Merged fixes and improvements from upstream

* NEW
* Add read support for "OOONA json" format - thx Alfonso
* New spectrogram themes + merge spectrogram/waveform UI - thx taylanunver
* Add tool for converting actors between ASSA/brackets/parentheses/colon
* Add OCR via Ollama vision models (granite3.2-vision, gemma3, mistral-small3.1)
* Add Mistral AI translate
* Add KoboldCpp AI translate - thx Oplay66
* Add AvalAI translate - thx JJHACKER
* Add "Chinese traditional" for DeepL - thx rdr44b
* Add voice-over for TTS - thx Chris-656
* Add new shortcut for "Insert unicode symbol" to main text box - thx davidgaryesp
* Add "gemini-2.0-flash" model (and allow custom model name) - thx yawoo
* Allow custom prompt for Gemini + add 'gemini-2.0-flash-lite' - thx LightGrey
* Add video player logo - thx Leon
* IMPROVED:
* Update Korean translation - thx domddol
* Update Greek translation - thx PMitsakis
* Update Chinese translation - thx nkh0472
* Update Polish translation - thx admas
* Update French translation - thx Pierre
* Update Italian translation - thx bovirus
* Update Portuguese translation - thx hugok79
* Update Czech translation - thx Mat?j
* Update Brazilian Portuguese translation - thx igorruckert
* Update Russian translation - thx elfriob
* Update Faster-Whisper-XXL to r245.4 - thx Purfview
* Update Whisper CPP to 1.7.5
* Update ffmpeg to 2025-03-31
* Update yt-dlp to 2025-03-26
* Improvements (speed and fixes) for PaddleOCR - thx timminator/Codling
* Add standalone PaddleOCR (no Python required) - thx timminator
* Make Whisper file list scrollable + auto scroll current item - thx RazyRo
* Minor improvements for "spell check"
* Some additions to dictionaries - thx Zolt?n
* Minor improvements for CSV importer - thx Louie
* Allow loading subtitle from MP4/MKV in file compare - thx FireEmerald
* Add CMD line SUP to SUP without OCR - thx AYColumbia
* Improve "Fix invalid italics" - thx uckthis
* Improve transparent subtitles for Vegas Pro - thx zzzzzz9125/Hintsmth
* Add total-words + total-chars to custom format header/footer - thx Jorge
* More consistent error msg in cmd line convert - thx xylographe/Hlsgs
* Add Brazilian Portuguese for LibreTranslate - thx erickcomcek
* FIXED:
* Fix space character in PAC
* Fix for LRC with MS parsing - thx AverageHoarder
* Fix crash in TTS retry - thx cvrle77
* Fix custom format duration > 1 min - thx bangwb
* Fix WebVTT conversion of color-name to color - thx mbas-rtbf
* Fix unwanted removal of space after colon in format EBU
* Fix duration in DVB subs, support for stuffing type - thx stanislavpetkov
* Fix namespace for textAlign attribute in "SMPTE-TT 2052" - thx palemieux
* Use chosen video extension in "Gen video with transparent subs" - thx Leon
* Do not add comma when merging lines - thx uckthis
* Fix issue with italic in DCinema formats - thx MartinaBerger
* Fix for split line with dialog - thx Yanngo
* Fix for char "?" in Piper TTS model/config