Update app.py

app.py

@@ -1,31 +1,42 @@
 import gradio as gr
 import numpy as np
 import random
-import spaces
 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 diffusers import DiffusionPipeline, FlowMatchEulerDiscreteScheduler, AutoencoderTiny, AutoencoderKL
+from transformers import CLIPTextModel, CLIPTokenizer, T5EncoderModel, T5TokenizerFast
+from live_preview_helpers import flux_pipe_call_that_returns_an_iterable_of_images
 
+# 檢查設備是否可用 GPU
 dtype = torch.bfloat16
 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)
+# 載入模型，若需要 API Token，請加上 use_auth_token=True
+try:
+    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)
+except Exception as e:
+    print(f"模型載入錯誤: {e}")
+
 torch.cuda.empty_cache()
 
 MAX_SEED = np.iinfo(np.int32).max
 MAX_IMAGE_SIZE = 2048
 
+# 確保 flux_pipe_call_that_returns_an_iterable_of_images 綁定到模型
 pipe.flux_pipe_call_that_returns_an_iterable_of_images = flux_pipe_call_that_returns_an_iterable_of_images.__get__(pipe)
 
-@spaces.GPU(duration=75)
-def infer(prompt, seed=42, randomize_seed=False, width=1024, height=1024, guidance_scale=3.5, num_inference_steps=28, progress=gr.Progress(track_tqdm=True)):
+# 定義推論函數
+@gr.Interface.function(duration=75)
+def infer(prompt, seed=42, randomize_seed=False, width=1024, height=1024, 
+          guidance_scale=3.5, num_inference_steps=28, 
+          progress=gr.Progress(track_tqdm=True)):
     if randomize_seed:
         seed = random.randint(0, MAX_SEED)
     generator = torch.Generator().manual_seed(seed)
-    
+
+    # 逐步生成圖像
     for img in pipe.flux_pipe_call_that_returns_an_iterable_of_images(
             prompt=prompt,
             guidance_scale=guidance_scale,
@@ -36,31 +47,33 @@ def infer(prompt, seed=42, randomize_seed=False, width=1024, height=1024, guidan
             output_type="pil",
             good_vae=good_vae,
         ):
-            yield img, seed
-    
+        yield img, seed
+
+# 預設的範例
 examples = [
     "a tiny astronaut hatching from an egg on the moon",
     "a cat holding a sign that says hello world",
     "an anime illustration of a wiener schnitzel",
 ]
 
-css="""
+css = """
 #col-container {
     margin: 0 auto;
     max-width: 520px;
 }
 """
 
+# 建立 Gradio 介面
 with gr.Blocks(css=css) as demo:
-    
     with gr.Column(elem_id="col-container"):
         gr.Markdown(f"""# FLUX.1 [dev]
 12B param rectified flow transformer guidance-distilled from [FLUX.1 [pro]](https://blackforestlabs.ai/)  
-[[non-commercial license](https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md)] [[blog](https://blackforestlabs.ai/announcing-black-forest-labs/)] [[model](https://huggingface.co/black-forest-labs/FLUX.1-dev)]
+[[non-commercial license](https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md)] 
+[[blog](https://blackforestlabs.ai/announcing-black-forest-labs/)] 
+[[model](https://huggingface.co/black-forest-labs/FLUX.1-dev)]
         """)
         
         with gr.Row():
-            
             prompt = gr.Text(
                 label="Prompt",
                 show_label=False,
@@ -68,72 +81,31 @@ with gr.Blocks(css=css) as demo:
                 placeholder="Enter your prompt",
                 container=False,
             )
-            
             run_button = gr.Button("Run", scale=0)
-        
+
         result = gr.Image(label="Result", show_label=False)
-        
+
         with gr.Accordion("Advanced Settings", open=False):
-            
-            seed = gr.Slider(
-                label="Seed",
-                minimum=0,
-                maximum=MAX_SEED,
-                step=1,
-                value=0,
-            )
-            
+            seed = gr.Slider(label="Seed", minimum=0, maximum=MAX_SEED, step=1, value=0)
             randomize_seed = gr.Checkbox(label="Randomize seed", value=True)
             
             with gr.Row():
-                
-                width = gr.Slider(
-                    label="Width",
-                    minimum=256,
-                    maximum=MAX_IMAGE_SIZE,
-                    step=32,
-                    value=1024,
-                )
-                
-                height = gr.Slider(
-                    label="Height",
-                    minimum=256,
-                    maximum=MAX_IMAGE_SIZE,
-                    step=32,
-                    value=1024,
-                )
-            
+                width = gr.Slider(label="Width", minimum=256, maximum=MAX_IMAGE_SIZE, step=32, value=1024)
+                height = gr.Slider(label="Height", minimum=256, maximum=MAX_IMAGE_SIZE, step=32, value=1024)
+
             with gr.Row():
+                guidance_scale = gr.Slider(label="Guidance Scale", minimum=1, maximum=15, step=0.1, value=3.5)
+                num_inference_steps = gr.Slider(label="Number of inference steps", minimum=1, maximum=50, step=1, value=28)
 
-                guidance_scale = gr.Slider(
-                    label="Guidance Scale",
-                    minimum=1,
-                    maximum=15,
-                    step=0.1,
-                    value=3.5,
-                )
-  
-                num_inference_steps = gr.Slider(
-                    label="Number of inference steps",
-                    minimum=1,
-                    maximum=50,
-                    step=1,
-                    value=28,
-                )
-        
-        gr.Examples(
-            examples = examples,
-            fn = infer,
-            inputs = [prompt],
-            outputs = [result, seed],
-            cache_examples="lazy"
-        )
+        gr.Examples(examples=examples, fn=infer, inputs=[prompt], outputs=[result, seed], cache_examples="lazy")
 
     gr.on(
         triggers=[run_button.click, prompt.submit],
-        fn = infer,
-        inputs = [prompt, seed, randomize_seed, width, height, guidance_scale, num_inference_steps],
-        outputs = [result, seed]
+        fn=infer,
+        inputs=[prompt, seed, randomize_seed, width, height, guidance_scale, num_inference_steps],
+        outputs=[result, seed]
     )
 
-demo.launch()
+# 啟動 Gradio App
+demo.launch(share=True)
+