revert

app.py

@@ -6,26 +6,15 @@ import gradio as gr
 import numpy as np
 import random
 import torch
-from diffusers import FluxPipeline, DiffusionPipeline, FluxTransformer2DModel  # noqa: F401
-from torchao.quantization import quantize_, int8_weight_only
+from diffusers import FluxPipeline
 from sd_embed.embedding_funcs import get_weighted_text_embeddings_flux1
 
 dtype = torch.bfloat16
 device = "cuda" if torch.cuda.is_available() else "cpu"
-
-transformer = FluxTransformer2DModel.from_pretrained(
-    "black-forest-labs/FLUX.1-dev", subfolder="transformer", torch_dtype=torch.bfloat16
-)
-quantize_(transformer, int8_weight_only())
-
-pipe = DiffusionPipeline.from_pretrained(
-    "black-forest-labs/FLUX.1-dev", transformer=transformer, torch_dtype=torch.bfloat16
+pipe = FluxPipeline.from_pretrained(
+    "black-forest-labs/FLUX.1-dev",
+    torch_dtype=dtype,
 )
-
-# pipe = FluxPipeline.from_pretrained(
-#     "black-forest-labs/FLUX.1-dev",
-#     torch_dtype=dtype,
-# )
 pipe.to(device)
 
 MAX_SEED = np.iinfo(np.int32).max