Update app.py

app.py

@@ -66,9 +66,9 @@ pipe = StableDiffusion3Pipeline.from_pretrained(
     "ford442/stable-diffusion-3.5-large-bf16",
 #    vae=AutoencoderKL.from_pretrained("ford442/stable-diffusion-3.5-large-fp32", use_safetensors=True, subfolder='vae',token=True),
      #scheduler = FlowMatchHeunDiscreteScheduler.from_pretrained('ford442/stable-diffusion-3.5-large-bf16', subfolder='scheduler',token=True),
-    # text_encoder=CLIPTextModelWithProjection.from_pretrained("ford442/stable-diffusion-3.5-large-bf16", subfolder='text_encoder', token=True),
-  #  text_encoder_2=CLIPTextModelWithProjection.from_pretrained("ford442/stable-diffusion-3.5-large-bf16", subfolder='text_encoder_2',token=True),
-  #  text_encoder_3=T5EncoderModel.from_pretrained("ford442/stable-diffusion-3.5-large-bf16", subfolder='text_encoder_3',token=True),
+    text_encoder=None, #CLIPTextModelWithProjection.from_pretrained("ford442/stable-diffusion-3.5-large-bf16", subfolder='text_encoder', token=True),
+    text_encoder_2=None, #CLIPTextModelWithProjection.from_pretrained("ford442/stable-diffusion-3.5-large-bf16", subfolder='text_encoder_2',token=True),
+    text_encoder_3=None, #T5EncoderModel.from_pretrained("ford442/stable-diffusion-3.5-large-bf16", subfolder='text_encoder_3',token=True),
     #tokenizer=CLIPTokenizer.from_pretrained("ford442/stable-diffusion-3.5-large-bf16", add_prefix_space=True, subfolder="tokenizer", token=True),
     #tokenizer_2=CLIPTokenizer.from_pretrained("ford442/stable-diffusion-3.5-large-bf16", add_prefix_space=True, subfolder="tokenizer_2", token=True),
     tokenizer_3=T5TokenizerFast.from_pretrained("ford442/stable-diffusion-3.5-large-bf16", use_fast=True, subfolder="tokenizer_3", token=True),
@@ -81,6 +81,10 @@ pipe = StableDiffusion3Pipeline.from_pretrained(
 
 pipe.to(device)
 
+text_encoder=CLIPTextModelWithProjection.from_pretrained("ford442/stable-diffusion-3.5-large-bf16", subfolder='text_encoder', token=True).to(device=device, dtype=torch.bfloat16)
+text_encoder_2=CLIPTextModelWithProjection.from_pretrained("ford442/stable-diffusion-3.5-large-bf16", subfolder='text_encoder_2',token=True).to(device=device, dtype=torch.bfloat16)
+text_encoder_3=T5EncoderModel.from_pretrained("ford442/stable-diffusion-3.5-large-bf16", subfolder='text_encoder_3',token=True).to(device=device, dtype=torch.bfloat16)
+    
 upscaler_2 = UpscaleWithModel.from_pretrained("Kim2091/ClearRealityV1").to(torch.device("cuda:0"))
 
 MAX_SEED = np.iinfo(np.int32).max
@@ -111,6 +115,9 @@ def infer(
     image_encoder_path=None,
     progress=gr.Progress(track_tqdm=True),
 ):
+    pipe.text_encoder=text_encoder
+    pipe.text_encoder_2=text_encoder_2
+    pipe.text_encoder_3=text_encoder_3
     upscaler_2.to(torch.device('cpu'))
     torch.set_float32_matmul_precision("highest")
     seed = random.randint(0, MAX_SEED)