Update app_v5.py

app_v5.py

@@ -8,7 +8,9 @@ import datetime
 import io
 import moondream as md
 from transformers import T5EncoderModel
-from diffusers import FluxControlNetPipeline
+from diffusers import FluxControlNetPipeline, FluxPipeline
+from diffusers import BitsAndBytesConfig as DiffusersBitsAndBytesConfig
+from transformers import BitsAndBytesConfig as TransformersBitsAndBytesConfig
 from diffusers.utils import load_image
 from PIL import Image
 from threading import Thread
@@ -18,8 +20,6 @@ from debug import log_params, scheduler, save_image
 logging.set_verbosity_debug()
 from model_loader import safe_model_load
 from huggingface_hub.utils._runtime import dump_environment_info
-from diffusers import BitsAndBytesConfig as DiffusersBitsAndBytesConfig
-from transformers import BitsAndBytesConfig as TransformersBitsAndBytesConfig
 
 def hello(profile: gr.OAuthProfile | None) -> str:
     if profile is None:
@@ -43,16 +43,16 @@ try:
 except Exception as e:
     print(f"Error setting memory usage: {e}")
 
-quant_config = TransformersBitsAndBytesConfig(load_in_8bit=True,)
+quant_config_5_t5 = TransformersBitsAndBytesConfig(load_in_8bit=True,)
 text_encoder_2_8b = T5EncoderModel.from_pretrained(
     "LPX55/FLUX.1-merged_lightning_v2",
     subfolder="text_encoder_2",
-    quantization_config=quant_config,
+    quantization_config=quant_config_5_t5,
     torch_dtype=torch.float16,
 )
 
 quant_config = DiffusersBitsAndBytesConfig(load_in_8bit=True,)
-transformer_8bit = FluxControlNetPipeline.from_pretrained(
+transformer_8bit = FluxPipeline.from_pretrained(
     "LPX55/FLUX.1-merged_lightning_v2",
     subfolder="transformer",
     quantization_config=quant_config,