add qwen-image-edit-2511

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

CHANGELOG.md

@@ -1,11 +1,13 @@
 # Change Log for SD.Next
 
-## Update for 2025-12-23
+## Update for 2025-12-24
 
 - **Models**
   - [LongCat Image](https://github.com/meituan-longcat/LongCat-Image) in *Image* and *Image Edit* variants  
     LongCat is a new 8B diffusion base model using Qwen-2.5 as text encoder  
-  - [Qwen Image Layered](https://huggingface.co/Qwen/Qwen-Image-Layered) in *base* and *pre-quantized* variants 
+  - [Qwen-Image-Edit 2511](Qwen/Qwen-Image-Edit-2511) in *base* and *pre-quantized* variants  
+    Key enhancements: mitigate image drift, improved character consistency, enhanced industrial design generation, and strengthened geometric reasoning ability  
+  - [Qwen-Image-Layered](https://huggingface.co/Qwen/Qwen-Image-Layered) in *base* and *pre-quantized* variants 
     Qwen-Image-Layered, a model capable of decomposing an image into multiple RGBA layers  
     *note*: set number of desired output layers in *settings -> model options*  
 - **Features**
@@ -23,8 +25,9 @@
   - mark `python==3.9` as deprecated  
   - extensions improved status indicators, thanks @awsr  
   - additional type-safety checks, thanks @awsr  
-- **Wiki**  
+- **Wiki/Docs/Illustrations**  
   - update models page, thanks @alerikaisattera  
+  - update reference models samples, thanks @liutyi  
 - **Fixes**  
   - generate forever fix loop checks, thanks @awsr  
   - tokenizer expclit use for flux2, thanks @CalamitousFelicitousness  

TODO.md

@@ -21,7 +21,7 @@
 - UI: Lite vs Expert mode  
 - Video tab: add full API support  
 - Control tab: add overrides handling  
-- Engine: TensorRT acceleration
+- Engine: `TensorRT` acceleration
 - Engine: [mmgp](https://github.com/deepbeepmeep/mmgp)
 - Engine: [sharpfin](https://github.com/drhead/sharpfin) instead of `torchvision`
 
@@ -40,6 +40,7 @@
 
 TODO: *Prioritize*!
 
+- [Cosmos-Predict-2.5](https://huggingface.co/nvidia/Cosmos-Predict2.5-2B)
 - [NewBie Image Exp0.1](https://github.com/huggingface/diffusers/pull/12803)
 - [Sana-I2V](https://github.com/huggingface/diffusers/pull/12634#issuecomment-3540534268)
 - [Bria FIBO](https://huggingface.co/briaai/FIBO)

html/reference.json

@@ -200,6 +200,15 @@
     "size": 56.1,
     "date": "2025 September"
   },
+  "Qwen-Image-Edit-2511": {
+    "path": "Qwen/Qwen-Image-Edit-2511",
+    "preview": "Qwen--Qwen-Image-Edit-2509.jpg",
+    "desc": "Key enhancements: mitigate image drift, improved character consistency, enhanced industrial design generation, and strengthened geometric reasoning ability.",
+    "skip": true,
+    "extras": "",
+    "size": 56.1,
+    "date": "2025 December"
+  },
   "Qwen-Image-Layered": {
     "path": "Qwen/Qwen-Image-Layered",
     "preview": "Qwen--Qwen-Image-Edit-2509.jpg",
@@ -1103,6 +1112,16 @@
     "size": 16.10,
     "extras": ""
   },
+  "Qwen-Image-Edit-2511 sdnq-svd-uint4": {
+    "path": "Disty0/Qwen-Image-Edit-2511-SDNQ-uint4-svd-r32",
+    "preview": "Qwen--Qwen-Image-Edit-2509.jpg",
+    "desc": "Quantization of Qwen/Qwen-Image-Edit-2511 using SDNQ: sdnq-svd 4-bit uint with svd rank 32",
+    "skip": true,
+    "tags": "quantized",
+    "date": "2025 December",
+    "size": 16.10,
+    "extras": ""
+  },
   "Qwen-Image-Layered sdnq-svd-uint4": {
     "path": "Disty0/Qwen-Image-Layered-SDNQ-uint4-svd-r32",
     "preview": "Qwen--Qwen-Image-Edit-2509.jpg",

installer.py

@@ -648,7 +648,7 @@ def check_diffusers():
     t_start = time.time()
     if args.skip_all:
         return
-    sha = '262ce19bff6b19e38aed3519fc9eb2d90d24f87a' # diffusers commit hash
+    sha = '52766e6a6939ac6e74375bde5e19c5e0b90d24c1' # diffusers commit hash
     # if args.use_rocm or args.use_zluda or args.use_directml:
     #     sha = '043ab2520f6a19fce78e6e060a68dbc947edb9f9' # lock diffusers versions for now
     pkg = pkg_resources.working_set.by_key.get('diffusers', None)

pipelines/model_qwen.py

@@ -15,7 +15,7 @@ def load_qwen(checkpoint_info, diffusers_load_config=None):
     load_args, _quant_args = model_quant.get_dit_args(diffusers_load_config, module='Model')
     shared.log.debug(f'Load model: type=Qwen model="{checkpoint_info.name}" repo="{repo_id}" offload={shared.opts.diffusers_offload_mode} dtype={devices.dtype} args={load_args}')
 
-    if '2509' in repo_id :
+    if '2509' in repo_id or '2511' in repo_id:
         cls_name = diffusers.QwenImageEditPlusPipeline
         diffusers.pipelines.auto_pipeline.AUTO_TEXT2IMAGE_PIPELINES_MAPPING["qwen-image"] = diffusers.QwenImageEditPlusPipeline
         diffusers.pipelines.auto_pipeline.AUTO_IMAGE2IMAGE_PIPELINES_MAPPING["qwen-image"] = diffusers.QwenImageEditPlusPipeline