update

app.py

@@ -5,6 +5,7 @@ import random
 import torch
 import devicetorch
 from diffusers import DiffusionPipeline
+import os
 
 
 # Quant
@@ -46,12 +47,13 @@ def init():
     bfl_repo = "cocktailpeanut/xulf-s"
     te_repo = "comfyanonymous/flux_text_encoders"
 
+
     scheduler = FlowMatchEulerDiscreteScheduler.from_pretrained(bfl_repo, subfolder="scheduler")
     #text_encoder = CLIPTextModel.from_pretrained("openai/clip-vit-large-patch14", torch_dtype=dtype)
-    text_encoder = CLIPTextModel.from_pretrained("./flux_text_encoders/clip_l.safetensors", torch_dtype=dtype)
+    text_encoder = CLIPTextModel.from_pretrained(os.path.join(os.getcwd(), "flux_text_encoders/clip_l.safetensors"), torch_dtype=dtype)
     tokenizer = CLIPTokenizer.from_pretrained("openai/clip-vit-large-patch14", torch_dtype=dtype)
     #text_encoder_2 = T5EncoderModel.from_pretrained(bfl_repo, subfolder="text_encoder_2", torch_dtype=dtype)
-    text_encoder_2 = T5EncoderModel.from_pretrained("./flux_text_encoders/t5xxl_fp8_e4m3fn.safetensors", torch_dtype=dtype)
+    text_encoder_2 = T5EncoderModel.from_pretrained(os.path.join(os.getcwd(), "flux_text_encoders/t5xxl_fp8_e4m3fn.safetensors"), torch_dtype=dtype)
     tokenizer_2 = T5TokenizerFast.from_pretrained(bfl_repo, subfolder="tokenizer_2", torch_dtype=dtype)
     vae = AutoencoderKL.from_pretrained(bfl_repo, subfolder="vae", torch_dtype=dtype)
     transformer = FluxTransformer2DModel.from_pretrained(bfl_repo, subfolder="transformer", torch_dtype=dtype)