Skip to main content
Choose output settings in the processing selector or Settings → Translation. Koharu captures them when a run starts; edits affect later runs.

​
Language and instructions

Set the target language and concise project-wide guidance for names, terminology, tone, pronouns, formatting, or text that should remain untranslated. Test the instructions on several pages and correct OCR first.

​
Local quantization

GGUF models may offer multiple quantizations. Smaller files need less download space and memory, usually at a quality cost. Larger files can be slower or exceed available memory. Hosted providers control their own serving precision.

​
Generation controls

Start with provider defaults and change one variable at a time. High randomness tends to make names and terminology less consistent.
Thinking can increase latency and token use. Unsupported options may be ignored or rejected by a provider or model.

​
Text and vision inputs

Text-only requests send semantic source text. With Vision input, a capable model also receives the source page image. For a custom OpenAI-compatible server, enable this only after checking image-message support. Generated translations remain editable project data. Review the wording and page layout before export.