Update app.py

app.py

@@ -20,13 +20,17 @@ MAX_SEED = np.iinfo(np.int32).max
 MAX_IMAGE_SIZE = 1024
 
 @spaces.GPU(duration=75) #[uncomment to use ZeroGPU]
-def infer(prompt, negative_prompt, seed, randomize_seed, width, height, guidance_scale, true_guidance, num_inference_steps, progress=gr.Progress(track_tqdm=True)):
+def infer(prompt, negative_prompt, seed, randomize_seed, width, height, guidance_scale, true_guidance, num_inference_steps, lora_model, progress=gr.Progress(track_tqdm=True)):
 
     if randomize_seed:
         seed = random.randint(0, MAX_SEED)
         
     generator = torch.Generator().manual_seed(seed)
+    pipe.unload_lora_weights()
     
+    if lora_model is not None: 
+        pipe.load_lora_weights(lora_model)
+        
     image = pipe(
         prompt = prompt, 
         negative_prompt = negative_prompt,
@@ -96,7 +100,7 @@ with gr.Blocks(css=css) as demo:
 
         with gr.Accordion("Advanced Settings", open=False):
             
-            
+            lora_model = gr.Textbox(label="LoRA model id", placeholder="multimodalart/flux-tarot-v1 ")
             
             seed = gr.Slider(
                 label="Seed",
@@ -145,7 +149,7 @@ with gr.Blocks(css=css) as demo:
     gr.on(
         triggers=[run_button.click, prompt.submit, negative_prompt.submit],
         fn = infer,
-        inputs = [prompt, negative_prompt, seed, randomize_seed, width, height, guidance_scale, true_guidance, num_inference_steps],
+        inputs = [prompt, negative_prompt, seed, randomize_seed, width, height, guidance_scale, true_guidance, num_inference_steps, lora_model],
         outputs = [result, seed]
     )