Update app.py

app.py

@@ -4,6 +4,7 @@ import random
 import spaces
 import torch
 from diffusers import  DiffusionPipeline, FlowMatchEulerDiscreteScheduler, AutoencoderTiny, AutoencoderKL
+from para_attn.first_block_cache.diffusers_adapters import apply_cache_on_pipe
 from transformers import CLIPTextModel, CLIPTokenizer,T5EncoderModel, T5TokenizerFast
 from live_preview_helpers import calculate_shift, retrieve_timesteps, flux_pipe_call_that_returns_an_iterable_of_images
 
@@ -47,6 +48,11 @@ def infer(prompt, seed=42, randomize_seed=False, width=1024, height=1024, guidan
         joint_attention_kwargs = {"scale": lora_scale}
     else:
         joint_attention_kwargs = None
+
+    apply_cache_on_pipe(
+        pipe,
+        # residual_diff_threshold=0.2,
+    )
     
     try:
         # Call the custom pipeline function with the correct keyword argument