Update app.py

app.py

@@ -38,7 +38,7 @@ taef1 = AutoencoderTiny.from_pretrained("madebyollin/taef1", torch_dtype=dtype).
 good_vae = AutoencoderKL.from_pretrained(base_model, subfolder="vae", torch_dtype=dtype).to(device)
 
 txt2img_pipe = DiffusionPipeline.from_pretrained(base_model, torch_dtype=dtype).to(device)
-txt2img_pipe.__class__.load_lora_into_transformer = classmethod(load_lora_into_transformer)
+# txt2img_pipe.__class__.load_lora_into_transformer = classmethod(load_lora_into_transformer)
 
 # img2img model
 img2img_pipe = AutoPipelineForImage2Image.from_pretrained(base_model, vae=good_vae, transformer=txt2img_pipe.transformer, text_encoder=txt2img_pipe.text_encoder, tokenizer=txt2img_pipe.tokenizer, text_encoder_2=txt2img_pipe.text_encoder_2, tokenizer_2=txt2img_pipe.tokenizer_2, torch_dtype=dtype)
@@ -166,8 +166,13 @@ def run_lora(prompt, image_url, lora_strings_json, image_strength,  cfg_scale, s
     gr.Info("Start to load LoRA ...")
     with calculateDuration("Unloading LoRA"):
         img2img_pipe.unload_lora_weights()
+        img2img_pipe.unload_lora()
         txt2img_pipe.unload_lora_weights()
+        txt2img_pipe.unload_lora()
+        
     print(txt2img_pipe.get_active_adapters())
+    list_adapters_component_wise = txt2img_pipe.get_list_adapters()
+    print(list_adapters_component_wise)
     
     lora_configs = None
     adapter_names = []
@@ -198,6 +203,7 @@ def run_lora(prompt, image_url, lora_strings_json, image_strength,  cfg_scale, s
                         try:
                             if img2img_model:
                                 img2img_pipe.load_lora_weights(lora_repo, weight_name=weights, low_cpu_mem_usage=True,  adapter_name=lora_name)
+                                img2img_pipe.set
                             else:
                                 txt2img_pipe.load_lora_weights(lora_repo, weight_name=weights, low_cpu_mem_usage=True,  adapter_name=lora_name)
                         except:
@@ -234,7 +240,7 @@ def run_lora(prompt, image_url, lora_strings_json, image_strength,  cfg_scale, s
 
     gr.Info("Completed！")
     progress(100, "Completed!")
-
+    torch.cuda.empty_cache() 
     return final_image, seed, json.dumps(result)
 
 # Gradio interface