From 5000401647e354872a0bc05b11060ddf55d6c179 Mon Sep 17 00:00:00 2001
From: CalamitousFelicitousness <iowasovereign@gmail.com>
Date: Fri, 6 Feb 2026 00:13:06 +0000
Subject: [PATCH] docs(ui): add tooltips for Nunchaku attention and offload
 settings

---
 html/locale_en.json | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/html/locale_en.json b/html/locale_en.json
index 5eb0b9f89..599bf7de5 100644
--- a/html/locale_en.json
+++ b/html/locale_en.json
@@ -337,6 +337,8 @@
   {"id":"","label":"Model Options","localized":"","reload":"","hint":"Settings related to behavior of specific models"},
   {"id":"","label":"Model Offloading","localized":"","reload":"","hint":"Settings related to model offloading and memory management"},
   {"id":"","label":"Model Quantization","localized":"","reload":"","hint":"Settings related to model quantization which is used to reduce memory usage"},
+  {"id":"","label":"Nunchaku attention","localized":"","reload":"","hint":"Replaces default attention with Nunchaku's custom FP16 attention kernel for faster inference on consumer NVIDIA GPUs.<br>Might provide performance improvement on GPUs which have higher FP16 tensor cores throughput than BF16.<br><br>Currently only affects Flux-based models (Dev, Schnell, Kontext, Fill, Depth, etc.). Has no effect on Qwen, SDXL, Sana, or other architectures.<br><br>Disabled by default."},
+  {"id":"","label":"Nunchaku offloading","localized":"","reload":"","hint":"Enables Nunchaku's own per-block CPU offloading with asynchronous CUDA streams to reduce VRAM usage.<br>Uses a ping-pong buffer strategy: while one transformer block computes on GPU, the next block preloads from CPU in the background, hiding most of the transfer latency.<br><br>Can reduce VRAM usage at the cost of slower inference.<br>This replaces SD.Next's pipeline offloading for the transformer component.<br><br>Only useful on low-VRAM GPUs. If your GPU has enough memory to hold the quantized model (16+ GB), keep this disabled for maximum speed.<br>Supports Flux and Qwen models. Not supported for SDXL where this setting is ignored.<br>Disabled by default."},
   {"id":"","label":"Image Metadata","localized":"","reload":"","hint":"Settings related to handling of metadata that is created with generated images"},
   {"id":"","label":"Legacy Options","localized":"","reload":"","hint":"Settings related to legacy options - should not be used"},
   {"id":"","label":"Restart server","localized":"","reload":"","hint":"Restart server"},