Resolve AttributeError on generation without Unet (#224)

* v0.2.0 (#217) * fix typo (#79) * Print correct profile when engine is loaded * Use scripts callbacks * increase max resolution * adding native LoRA support, avoiding model.py import error and some refactoring * more refactoring and added typing * Enable torch fallback * update inastall * change default XL engine * cc independent lora * Update Instrucitons --------- Co-authored-by: Rudra <[email protected]> * Resolve AttributeError on generation without Unet --------- Co-authored-by: Luca <[email protected]> Co-authored-by: Rudra <[email protected]>
NVIDIA · Feb 5, 2024 · cbad067 · cbad067
1 parent 490fa1c
commit cbad067
Showing 1 changed file with 1 addition and 1 deletion.
diff --git a/scripts/trt.py b/scripts/trt.py
@@ -296,7 +296,7 @@ def apply_unet(self, sd_unet_option):
 
     def process_batch(self, p, *args, **kwargs):
         # Called for each batch count
-        if self.torch_unet:
+        if self.torch_unet or not sd_unet.current_unet:
             return super().process_batch(p, *args, **kwargs)
 
         if self.idx != sd_unet.current_unet.profile_idx: