Update app.py

app.py

@@ -61,6 +61,7 @@ def init_predictor():
         text_encoder=text_encoder,
         torch_dtype=torch.bfloat16,
     ).to("cpu")
+    pipe.clip_skip=None
     pipe.to(device)
     
 negative_prompt = "Aerial view, aerial view, overexposed, low quality, deformation, a poor composition, bad hands, bad teeth, bad eyes, bad limbs, distortion"
@@ -71,7 +72,7 @@ def generate(segment, image, prompt, size, guidance_scale, num_inference_steps,
     seed = int(random.randrange(4294967294))
     if segment==1:
         prompt_embeds, prompt_attention_mask, negative_prompt_embeds, negative_attention_mask, pooled_prompt_embeds, negative_pooled_prompt_embeds = pipe.encode_prompt(
-        prompt=prompt, do_classifier_free_guidance=True, clip_skip=None, negative_prompt=negative_prompt, device=device
+        prompt=prompt, do_classifier_free_guidance=True, negative_prompt=negative_prompt, device=device
         )
         
         transformer_dtype = pipe.transformer.dtype