diff --git a/CHANGELOG.md b/CHANGELOG.md
index 3f4c804e4..4d44a2f09 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -11,6 +11,7 @@ But there's more than SD3:
 - support for quantized **T5** text encoder in all models that use T5: FP4/FP8/FP16/INT8 (SD3, PixArt-Σ, etc)  
 - support for **PixArt-Sigma** in small/medium/large variants  
 - support for **HunyuanDiT 1.1**  
+- additional **NNCF weights compression** support: SD3, PixArt, ControlNet, Lora
 - (finally) new release of **Torch-DirectML**  
 - additional efficiencies for users with low vram gpus  
 - over 20 overall fixes  
@@ -47,6 +48,7 @@ But there's more than SD3:
 - support for `torch-directml` **0.2.2**, thanks @lshqqytiger!  
   *note*: new directml is finally based on modern `torch` 2.3.1!  
 - xyz grid: add support for LoRA selector
+- vae load: store original vae so it can be restored when set to none
 - extra networks: info display now contains link to source url if model if its known  
   works for civitai and huggingface models  
 - force gc for lowvram users and improve gc logging
@@ -56,11 +58,11 @@ But there's more than SD3:
 - additional torch gc checks, thanks @Disty0!
 
 **Improvements: NNCF**, thanks @Disty0!  
- - SD3 and PixArt support  
- - moved the first compression step to CPU  
- - sequential cpu offload (lowvram) support  
- - Lora support without reloading the model  
- - ControlNet compression support  
+- SD3 and PixArt support  
+- moved the first compression step to CPU  
+- sequential cpu offload (lowvram) support  
+- Lora support without reloading the model  
+- ControlNet compression support  
 
 ### Fixes
 
diff --git a/modules/sd_vae.py b/modules/sd_vae.py
index 94a6c6b49..53b89161f 100644
--- a/modules/sd_vae.py
+++ b/modules/sd_vae.py
@@ -259,6 +259,11 @@ def reload_vae_weights(sd_model=None, vae_file=unspecified):
         vae_file, vae_source = resolve_vae(checkpoint_file)
     else:
         vae_source = "function-argument"
+    if vae_file is None or vae_file == 'None':
+        if hasattr(sd_model, 'original_vae'):
+            sd_models.set_diffuser_options(sd_model, vae=sd_model.original_vae, op='vae')
+            shared.log.info("VAE restored")
+            return None
     if loaded_vae_file == vae_file:
         return None
     if not shared.native and (shared.cmd_opts.lowvram or shared.cmd_opts.medvram):
@@ -276,11 +281,14 @@ def reload_vae_weights(sd_model=None, vae_file=unspecified):
         if vae_file is not None:
             shared.log.info(f"VAE weights loaded: {vae_file}")
     else:
-        if hasattr(shared.sd_model, "vae") and hasattr(shared.sd_model, "sd_checkpoint_info"):
-            vae = load_vae_diffusers(shared.sd_model.sd_checkpoint_info.filename, vae_file, vae_source)
+        if hasattr(sd_model, "vae") and hasattr(sd_model, "sd_checkpoint_info"):
+            vae = load_vae_diffusers(sd_model.sd_checkpoint_info.filename, vae_file, vae_source)
             if vae is not None:
+                if not hasattr(sd_model, 'original_vae'):
+                    sd_model.original_vae = sd_model.vae
+                    sd_models.move_model(sd_model.original_vae, devices.cpu)
                 sd_models.set_diffuser_options(sd_model, vae=vae, op='vae')
-                apply_vae_config(shared.sd_model.sd_checkpoint_info.filename, vae_file, sd_model)
+                apply_vae_config(sd_model.sd_checkpoint_info.filename, vae_file, sd_model)
 
     if not shared.cmd_opts.lowvram and not shared.cmd_opts.medvram:
         sd_models.move_model(sd_model, devices.device)