uuu

app.py

@@ -3,9 +3,7 @@ import requests
 import torch
 import gradio as gr
 import spaces
-from PIL import Image
 from huggingface_hub import login
-import torchvision.transforms as T
 from diffusers.utils import load_image
 
 from models.transformer_sd3 import SD3Transformer2DModel
@@ -34,6 +32,23 @@ if not token:
     raise ValueError("Hugging Face token not found. Set the 'HF_TOKEN' environment variable.")
 login(token=token)
 
+model_path = 'stabilityai/stable-diffusion-3.5-large'
+ip_adapter_path = './ip-adapter.bin'
+image_encoder_path = "google/siglip-so400m-patch14-384"
+
+transformer = SD3Transformer2DModel.from_pretrained(
+    model_path, subfolder="transformer", torch_dtype=torch.bfloat16
+)
+
+pipe = StableDiffusion3Pipeline.from_pretrained(
+    model_path, transformer=transformer, torch_dtype=torch.bfloat16
+).to("cuda")
+
+pipe.init_ipadapter(
+    ip_adapter_path=ip_adapter_path,
+    image_encoder_path=image_encoder_path,
+    nb_token=64,
+)
 
 
 # ----------------------------
@@ -42,23 +57,6 @@ login(token=token)
 @spaces.GPU
 def gui_generation(prompt, ref_img, guidance_scale, ipadapter_scale):
 
-    model_path = 'stabilityai/stable-diffusion-3.5-large'
-    ip_adapter_path = './ip-adapter.bin'
-    image_encoder_path = "google/siglip-so400m-patch14-384"
-
-    transformer = SD3Transformer2DModel.from_pretrained(
-        model_path, subfolder="transformer", torch_dtype=torch.bfloat16
-    )
-
-    pipe = StableDiffusion3Pipeline.from_pretrained(
-        model_path, transformer=transformer, torch_dtype=torch.bfloat16
-    ).to("cuda")
-
-    pipe.init_ipadapter(
-        ip_adapter_path=ip_adapter_path,
-        image_encoder_path=image_encoder_path,
-        nb_token=64,
-    )
 
     ref_img = load_image(ref_img.name).convert('RGB')