Update app.py

app.py

@@ -5,7 +5,12 @@ import torch
 import spaces
 
 from PIL import Image
-from diffusers import QwenImageEditPipeline
+# from diffusers import QwenImageEditPipeline
+
+from optimization import optimize_pipeline_
+from qwenimage.pipeline_qwen_image_edit import QwenImageEditPipeline
+from qwenimage.transformer_qwenimage import QwenImageTransformer2DModel
+from qwenimage.qwen_fa3_processor import QwenDoubleStreamAttnProcessorFA3
 
 import os
 import base64
@@ -137,9 +142,13 @@ def api(prompt, img_list, model="qwen-vl-max-latest", kwargs={}):
 # --- Model Loading ---
 dtype = torch.bfloat16
 device = "cuda" if torch.cuda.is_available() else "cpu"
-
-# Load the model pipeline
 pipe = QwenImageEditPipeline.from_pretrained("Qwen/Qwen-Image-Edit", torch_dtype=dtype).to(device)
+pipe.transformer.__class__ = QwenImageTransformer2DModel
+pipe.transformer.set_attn_processor(QwenDoubleStreamAttnProcessorFA3())
+
+
+# --- Ahead-of-time compilation ---
+optimize_pipeline_(pipe, image=Image.new("RGB", (1024, 1024)), prompt="prompt")
 
 # --- UI Constants and Helpers ---
 MAX_SEED = np.iinfo(np.int32).max