Update app.py

app.py

@@ -6,6 +6,7 @@ import torch
 from diffusers import  DiffusionPipeline, FlowMatchEulerDiscreteScheduler, AutoencoderTiny, AutoencoderKL
 from transformers import CLIPTextModel, CLIPTokenizer,T5EncoderModel, T5TokenizerFast
 from live_preview_helpers import calculate_shift, retrieve_timesteps, flux_pipe_call_that_returns_an_iterable_of_images
+from torchao.quantization.quant_api import Int8WeightOnlyConfig, quantize_
 
 dtype = torch.bfloat16
 device = "cuda" if torch.cuda.is_available() else "cpu"
@@ -13,6 +14,8 @@ device = "cuda" if torch.cuda.is_available() else "cpu"
 taef1 = AutoencoderTiny.from_pretrained("madebyollin/taef1", torch_dtype=dtype).to(device)
 good_vae = AutoencoderKL.from_pretrained("black-forest-labs/FLUX.1-dev", subfolder="vae", torch_dtype=dtype).to(device)
 pipe = DiffusionPipeline.from_pretrained("black-forest-labs/FLUX.1-dev", torch_dtype=dtype, vae=taef1).to(device)
+quantize_(pipe.transformer, Int8WeightOnlyConfig())
+
 torch.cuda.empty_cache()
 
 MAX_SEED = np.iinfo(np.int32).max