Update app.py

app.py

@@ -4,10 +4,11 @@ import random
 
 import spaces
 from diffusers import DiffusionPipeline
-from transformers import T5EncoderModel
+from transformers import T5EncoderModel, CLIPTextModel
 import torch
 
 device = "cuda" if torch.cuda.is_available() else "cpu"
+text_encoder_repo = "silveroxides/diffusers-long-clip"
 text_encoder_3_repo = "silveroxides/t5xxl_flan_enc"
 model_repo_id = "stabilityai/stable-diffusion-3.5-large-turbo"
 
@@ -15,8 +16,9 @@ if torch.cuda.is_available():
     torch_dtype = torch.bfloat16
 else:
     torch_dtype = torch.float32
+text_encoder = CLIPTextModel.from_pretrained(text_encoder_repo, torch_dtype=torch_dtype)
 text_encoder_3 = T5EncoderModel.from_pretrained(text_encoder_3_repo, torch_dtype=torch_dtype)
-pipe = DiffusionPipeline.from_pretrained(model_repo_id, text_encoder_3=text_encoder_3, torch_dtype=torch_dtype)
+pipe = DiffusionPipeline.from_pretrained(model_repo_id, text_encoder=text_encoder, text_encoder_3=text_encoder_3, torch_dtype=torch_dtype)
 pipe = pipe.to(device)
 
 MAX_SEED = np.iinfo(np.int32).max