Update app.py

app.py

@@ -1,6 +1,7 @@
 import gradio as gr
 import numpy as np
 import random
+import os
 
 # import spaces #[uncomment to use ZeroGPU]
 from diffusers import DiffusionPipeline
@@ -10,14 +11,11 @@ import torch
 
 from huggingface_hub import login
 
-# Substitua "your_huggingface_token" pelo token gerado
-login(token="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")
-
 
 device = "cuda" if torch.cuda.is_available() else "cpu"
-model_repo_id = "stabilityai/stable-diffusion-xl-base-1.0"  # Replace to the model you would like to use
+model_repo_id = "stabilityai/sdxl-turbo"  # Replace to the model you would like to use
 
-pipe = OnnxRuntimeModel.from_pretrained("sstabilityai/stable-diffusion-xl-base-1.0", provider="CPUExecutionProvider")
+pipe = OnnxRuntimeModel.from_pretrained("stabilityai/sdxl-turbo", provider="CPUExecutionProvider")
 pipe = OnnxRuntimeModel.from_pretrained("model_path", provider="CPUExecutionProvider")
 pipe = DiffusionPipeline.from_pretrained(model_repo_id, torch_dtype=torch.float16)
 pipe.enable_attention_slicing()  # Divide o cálculo de atenção para melhorar o desempenho em dispositivos com menos memória