update

app.py

@@ -27,17 +27,25 @@ torch.manual_seed(1)
 #image  # nice. diffusers are cool. #no need
 finetuned_lora_weights = "./lora_weight.pt"
 
+#global var
+counter = 0
+
 #####
 #my fine tuned weights
 def monkeypatching(alpha): #, prompt, pipe): finetuned_lora_weights
-    monkeypatch_lora(pipe.unet, torch.load(finetuned_lora_weights)) #"./lora_weight.pt")) 
-    tune_lora_scale(pipe.unet, alpha) #1.00)
+    global counter
+    if counter == 0 :
+        monkeypatch_lora(pipe.unet, torch.load("./output_example/lora_weight.pt")) #finetuned_lora_weights
+        tune_lora_scale(pipe.unet, alpha) #1.00)
+        counter +=1
+    else :
+        tune_lora_scale(pipe.unet, alpha) #1.00)
     image = pipe(prompt, num_inference_steps=50, guidance_scale=7).images[0]
     image.save("./illust_lora.jpg") #"./contents/illust_lora.jpg")
     return image
 
 def accelerate_train_lora(steps):
-    print("***********inside accelerate_train_lora 11111***********")
+    print("*********** inside accelerate_train_lora ***********")
     #subprocess.run(accelerate launch {"./train_lora_dreambooth.py"} \
     #subprocess.Popen(f'accelerate launch {"./train_lora_dreambooth.py"} \
     os.system( f'accelerate launch {"./train_lora_dreambooth.py"} \
@@ -52,7 +60,7 @@ def accelerate_train_lora(steps):
       --lr_scheduler="constant" \
       --lr_warmup_steps=0 \
       --max_train_steps={int(steps)}') #,shell=True) #30000
-    print("***********inside accelerate_train_lora 22222***********")
+    print("*********** completing accelerate_train_lora ***********")
     return
     
 with gr.Blocks() as demo: