add Qwen-Image-2512-SDNQ-4bit-dynamic

Signed-off-by: vladmandic <mandic00@live.com>

CHANGELOG.md

@@ -5,12 +5,13 @@
 - **Models**
   - [Qwen-Image-2512](https://huggingface.co/Qwen/Qwen-Image-2512)  
     Qwen-Image successor, significantly reduces the AI-generated look and adds finer natural detailils and improved text rendering  
-    available in both *original* and sdnq *prequantized* variants  
+    available in both *original*, *sdnq-svd prequantized* and *sdnq-dynamic prequantized*  variants  
 - **Feaures**
   - **SDNQ** now has *19 int* based and *69 float* based quantization types  
     *note*: not all are exposed via ui purely for simplicity, but all are available via api and scripts  
   - allow weights for wildcards, thanks @Tillerz  
   - sampler: add laplace beta schedule  
+    results in better prompt adherence and smoother infills  
 - **UI**
   - kanvas add send-to functionality  
   - kanvas improve support for standardui  
@@ -26,6 +27,7 @@
   - rocm/hip/hipblast detection and initialization improvements  
   - zluda detection and initialization improvements  
   - new env variable `SD_VAE_DEFAULT` to force default vae processing  
+  - update `nunchaku==1.1.0`  
 - **Fixes**
   - extension tab: update checker, date handling, formatting etc., thanks @awsr  
   - controlnet with non-english ui locales  

html/reference.json

@@ -1103,6 +1103,16 @@
     "size": 16.10,
     "date": "2025 December"
   },
+  "Qwen-Image-2512 sdnq-dynamic-uint4": {
+    "path": "Disty0/Qwen-Image-2512-SDNQ-4bit-dynamic",
+    "preview": "Disty0--Qwen-Image-2512-SDNQ-uint4-svd-r32.jpg",
+    "desc": "Quantization of Qwen/Qwen-Image-2512 using SDNQ: sdnq-dynamic 4-bit uint",
+    "skip": true,
+    "tags": "quantized",
+    "extras": "",
+    "size": 16.10,
+    "date": "2026 January"
+  },
   "Qwen-Image-Edit sdnq-svd-uint4": {
     "path": "Disty0/Qwen-Image-Edit-SDNQ-uint4-svd-r32",
     "preview": "Qwen--Qwen-Image-Edit.jpg",

modules/mit_nunchaku.py

@@ -4,7 +4,7 @@ from installer import log, pip
 from modules import devices
 
 
-nunchaku_ver = '1.0.2'
+nunchaku_ver = '1.1.0'
 ok = False