add note on qwen blocker

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

CHANGELOG.md

@@ -1,10 +1,14 @@
 # Change Log for SD.Next
 
+## Blockers
+
+- Qwen: <https://github.com/huggingface/diffusers/issues/12066> 
+
 ## Update for 2025-08-04
 
 - **Models**  
   - [Qwen-Image](https://qwenlm.github.io/blog/qwen-image/)  
-    new image foundational model with 20B params and using Qwen-2.5 as text-encoder!  
+    new image foundational model with 20B params DiT and using Qwen-2.5 8B as text-encoder!  
     available for text-to-image workflows, image-editing workflows will follow soon  
     *note*: this model is almost 2x the size of Flux, quantization and offloading are highly recommended!  
     available via *networks -> models -> reference*  

modules/sd_hijack_te.py

@@ -8,10 +8,12 @@ def hijack_encode_prompt(*args, **kwargs):
     t0 = time.time()
     if 'max_sequence_length' in kwargs:
         kwargs['max_sequence_length'] = max(kwargs['max_sequence_length'], os.environ.get('HIDREAM_MAX_SEQUENCE_LENGTH', 256))
+    # if hasattr(shared.sd_model, 'text_encoder') and shared.sd_model.text_encoder is not None:
+    #     sd_models.move_model(shared.sd_model.text_encoder, devices.device)
     try:
         res = shared.sd_model.orig_encode_prompt(*args, **kwargs)
     except Exception as e:
-        shared.log.error(f'Eencode prompt: {e}')
+        shared.log.error(f'Encode prompt: {e}')
         errors.display(e, 'Encode prompt')
         res = None
     t1 = time.time()