Update app.py

app.py

@@ -26,7 +26,10 @@ def generate(prompt, negative_prompt, width=1024, height=1024, num_inference_ste
         pipe.load_lora_weights(lora_id.strip())
     pipe.to("cuda")
     # apply_first_block_cache(pipe.transformer, FirstBlockCacheConfig(threshold=0.2))
-    apply_cache_on_pipe(pipe)
+    apply_cache_on_pipe(
+        pipe,
+        residual_diff_threshold=0.2,
+    )
     try:
         output = pipe(
             prompt=prompt,