diff --git a/CHANGELOG.md b/CHANGELOG.md
index 6978c4e57..3211a4752 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -1,15 +1,18 @@
 # Change Log for SD.Next
 
-## Update for 2024-12-17
+## Update for 2024-12-18
 
 ### New models and integrations
 
 - [NVLabs Sana](https://huggingface.co/Efficient-Large-Model/Sana_1600M_1024px)
-  **Sana** can synthesize high-resolution images with strong text-image alignment by using **Gemma2** as text-encoder  
-  and its *fast* - typically at least **2x** faster than sd-xl even for 1.6B variant  
   support for both 1.6B and 0.6B models  
+  **Sana** can synthesize high-resolution images with strong text-image alignment by using **Gemma2** as text-encoder  
+  and its *fast* - typically at least **2x** faster than sd-xl even for 1.6B variant and maintains performance regardless of resolution  
+  e.g., rendering at 4k is possible in less than 8GB vram  
   to use, select from *networks -> models -> reference* and models will be auto-downloaded on first use  
   *reference values*: sampler: default (or any flow-match variant), width/height: 1024, guidance scale: 4.5  
+  *note* like other LLM-based text-encoders, sana prefers long and descriptive prompts  
+  any short prompt below 300 characters will be auto-expanded using built in Gemma LLM before encoding while long prompts will be passed as-is  
 - [Flux Tools](https://blackforestlabs.ai/flux-1-tools/)  
   **Redux** is actually a tool, **Fill** is inpaint/outpaint optimized version of *Flux-dev*  
   **Canny** & **Depth** are optimized versions of *Flux-dev* for their respective tasks: they are *not* ControlNets that work on top of a model  
diff --git a/installer.py b/installer.py
index c0d3c907d..3dd0f13d5 100644
--- a/installer.py
+++ b/installer.py
@@ -459,7 +459,7 @@ def check_python(supported_minors=[9, 10, 11, 12], reason=None):
 def check_diffusers():
     if args.skip_all or args.skip_requirements:
         return
-    sha = '1524781b88ac1a082e755a030ba9d73cd6948e84' # diffusers commit hash
+    sha = '862a7d5038c1c53641ffcab146a7eeb5ab683656' # diffusers commit hash
     pkg = pkg_resources.working_set.by_key.get('diffusers', None)
     minor = int(pkg.version.split('.')[1] if pkg is not None else 0)
     cur = opts.get('diffusers_version', '') if minor > 0 else ''
diff --git a/modules/processing_args.py b/modules/processing_args.py
index e7f53ba8e..d0afb6722 100644
--- a/modules/processing_args.py
+++ b/modules/processing_args.py
@@ -164,6 +164,11 @@ def set_pipeline_args(p, model, prompts: list, negative_prompts: list, prompts_2
                 args['negative_prompt'] = negative_prompts[0]
             else:
                 args['negative_prompt'] = negative_prompts
+    if 'complex_human_instruction' in possible:
+        chi = any(len(p) < 300 for p in prompts)
+        p.extra_generation_params["CHI"] = chi
+        if not chi:
+            args['complex_human_instruction'] = None
     if prompt_parser_diffusers.embedder is not None and not prompt_parser_diffusers.embedder.scheduled_prompt: # not scheduled so we dont need it anymore
         prompt_parser_diffusers.embedder = None
 
diff --git a/wiki b/wiki
index 4dc357d28..470e75f0c 160000
--- a/wiki
+++ b/wiki
@@ -1 +1 @@
-Subproject commit 4dc357d28956b827eb38df626e834fb6a25ec47c
+Subproject commit 470e75f0c70a22ed3d65187c70f04c131400b35d