diff --git a/CHANGELOG.md b/CHANGELOG.md
index a078e6b76..9c8ee13fb 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -1,14 +1,14 @@
 # Change Log for SD.Next
 
-## Update for 2025-11-09
+## Update for 2025-11-10
 
-### Highlights for 2025-11-09
+### Highlights for 2025-11-10
 
 TBD
 
-### Details for 2025-11-09
+### Details for 2025-11-10
 
-- **Features**  
+- **Features**
   - **kanvas**: new module for native canvas-based image manipulation  
     kanvas is a full replacement for *img2img, inpaint and outpaint* controls  
     see [docs](https://vladmandic.github.io/sdnext-docs/Kanvas/) for details  
@@ -18,6 +18,7 @@ TBD
   - **attention**: additional torch attention settings  
   - **lora**: separate fuse setting for native-vs-diffuser implementations  
   - **auth**: strong-enforce auth check on all api endpoints  
+  - **amdgpu**: prefer rocm-on-windows over zluda
 - **Internal**
   - refactor attention handling  
   - remove obsolete video scripts  
@@ -26,9 +27,11 @@ TBD
   - hires: strength save/load in metadata, thanks @awsr  
   - imgi2img: fix initial scale tab, thanks @awsr  
   - log: client log formatting, thanks @awsr  
+  - rocm: check if installed before forcing install  
   - pony-v7: fix text-encoder  
   - detailer: with face-restorers  
   - detailer: using lora in detailer prompt  
+  - detailer: fail on unsupported models instead of corrputing results  
 
 ## Update for 2025-11-06
 
diff --git a/modules/postprocess/yolo.py b/modules/postprocess/yolo.py
index a63cec216..8098b1a7e 100644
--- a/modules/postprocess/yolo.py
+++ b/modules/postprocess/yolo.py
@@ -6,7 +6,7 @@ from copy import copy
 import numpy as np
 import gradio as gr
 from PIL import Image, ImageDraw
-from modules import shared, processing, devices, processing_class, ui_common, ui_components, ui_symbols, images, extra_networks
+from modules import shared, processing, devices, processing_class, ui_common, ui_components, ui_symbols, images, extra_networks, sd_models
 from modules.detailer import Detailer
 
 
@@ -239,6 +239,12 @@ class YoloRestorer(Detailer):
             p.detailer_active = 0
         if np_image is None or p.detailer_active >= p.batch_size * p.n_iter:
             return np_image
+
+        shared.sd_model = sd_models.set_diffuser_pipe(shared.sd_model, sd_models.DiffusersTaskType.INPAINTING)
+        if (sd_models.get_diffusers_task(shared.sd_model) != sd_models.DiffusersTaskType.INPAINTING) and (shared.sd_model.__class__.__name__ not in sd_models.pipe_switch_task_exclude):
+            shared.log.error(f'Detailer: model="{shared.sd_model.__class__.__name__}" not compatible')
+            return np_image
+
         models = []
         if len(shared.opts.detailer_args) > 0:
             models = [m.strip() for m in re.split(r'[\n,;]+', shared.opts.detailer_args)]
@@ -367,6 +373,7 @@ class YoloRestorer(Detailer):
                 if item.mask is None:
                     continue
                 pc.keep_prompts = True
+                shared.sd_model.fail_on_switch_error = True
                 pc.prompt = prompt_lines[i*len(items)+j]
                 pc.negative_prompt = negative_lines[i*len(items)+j]
                 pc.prompts = [pc.prompt]
@@ -382,6 +389,7 @@ class YoloRestorer(Detailer):
                 jobid = shared.state.begin('Detailer')
                 pp = processing.process_images_inner(pc)
                 extra_networks.deactivate(pc, force=True)
+                shared.sd_model.fail_on_switch_error = False
                 shared.state.end(jobid)
 
                 del pc.recursion