diff --git a/CHANGELOG.md b/CHANGELOG.md
index 54286e2a9..d4f659b3b 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -8,9 +8,7 @@ BLOCKERS:
 OPTIONAL:
 - pending `diffusers==0.26.0`
 - animatediff `enable_free_init` [pr](https://github.com/huggingface/diffusers/pull/6315)
-- pipeline `diffusers_sag_scale` [pr](https://github.com/huggingface/diffusers/issues/6443)
 - wuerstchen v3 [pr](https://github.com/huggingface/diffusers/pull/6487)
-- adetailer [fix](https://github.com/Bing-su/adetailer/issues/466)
 - control api
 - photomaker api
 - interrogate api
@@ -100,6 +98,10 @@ And it also includes fixes for all reported issues so far
   - new model from TenencentARC using similar concept as IPAdapter, but with different implementation and  
     allowing full concept swaps between input images and generated images using trigger words  
   - note: trigger word must match exactly one term in prompt for model to work  
+- [Self-attention guidance](https://github.com/SusungHong/Self-Attention-Guidance)  
+  - simply select scale in advanced menu  
+  - can drastically improve image coherence as well as reduce artifacts  
+  - note: only compatible with some schedulers  
 - **Improvements**  
   - **ui**  
     - check version and **update** SD.Next via UI  
diff --git a/modules/processing_diffusers.py b/modules/processing_diffusers.py
index d92f06f95..1493f68e9 100644
--- a/modules/processing_diffusers.py
+++ b/modules/processing_diffusers.py
@@ -389,9 +389,14 @@ def process_diffusers(p: StableDiffusionProcessing):
 
     def update_pipeline(sd_model, p: StableDiffusionProcessing):
         if p.sag_scale > 0 and is_txt2img():
-            sd_model = sd_models.switch_diffuser_pipe(sd_model, diffusers.StableDiffusionSAGPipeline)
-            p.extra_generation_params["SAG scale"] = p.sag_scale
-            p.task_args['sag_scale'] = p.sag_scale
+            update_sampler(shared.sd_model)
+            supported = ['DDIMScheduler', 'PNDMScheduler', 'DDPMScheduler', 'DEISMultistepScheduler', 'UniPCMultistepScheduler', 'DPMSolverMultistepScheduler', 'DPMSolverSinlgestepScheduler']
+            if sd_model.scheduler.__class__.__name__ in supported:
+                sd_model = sd_models.switch_diffuser_pipe(sd_model, diffusers.StableDiffusionSAGPipeline)
+                p.extra_generation_params["SAG scale"] = p.sag_scale
+                p.task_args['sag_scale'] = p.sag_scale
+            else:
+                shared.log.warning(f'SAG incompatible scheduler: current={sd_model.scheduler.__class__.__name__} supported={supported}')
         return sd_model
 
     if len(getattr(p, 'init_images', [])) > 0:
diff --git a/modules/ui_sections.py b/modules/ui_sections.py
index e037e13c6..d6083686f 100644
--- a/modules/ui_sections.py
+++ b/modules/ui_sections.py
@@ -108,9 +108,7 @@ def create_advanced_inputs(tab):
                 image_cfg_scale = gr.Slider(minimum=0.0, maximum=30.0, step=0.1, label='Secondary CFG scale', value=6.0, elem_id=f"{tab}_image_cfg_scale")
             with FormRow():
                 diffusers_guidance_rescale = gr.Slider(minimum=0.0, maximum=1.0, step=0.05, label='Guidance rescale', value=0.7, elem_id=f"{tab}_image_cfg_rescale", visible=shared.backend == shared.Backend.DIFFUSERS)
-                # TODO enable SAG once fixed in diffusers
-                # diffusers_sag_scale = gr.Slider(minimum=0.0, maximum=1.0, step=0.05, label='Self-attention guidance', value=0.0, elem_id=f"{tab}_image_sag_scale", visible=shared.backend == shared.Backend.DIFFUSERS)
-                diffusers_sag_scale = gr.Slider(minimum=0.0, maximum=1.0, step=0.05, label='Self-attention guidance', value=0.0, elem_id=f"{tab}_image_sag_scale", visible=False)
+                diffusers_sag_scale = gr.Slider(minimum=0.0, maximum=1.0, step=0.05, label='Self-attention guidance', value=0.0, elem_id=f"{tab}_image_sag_scale", visible=shared.backend == shared.Backend.DIFFUSERS)
             with FormRow():
                 clip_skip = gr.Slider(label='CLIP skip', value=1, minimum=1, maximum=14, step=1, elem_id=f"{tab}_clip_skip", interactive=True)
         with gr.Group():