Update app.py

app.py

@@ -1,51 +1,46 @@
 import gradio as gr
 import numpy as np
 import random
-#import spaces #[uncomment to use ZeroGPU]
-from diffusers import DiffusionPipeline
-import torch
+from transformers import pipeline
+from PIL import Image
+import requests
+from io import BytesIO
 
-device = "cuda" if torch.cuda.is_available() else "cpu"
-model_repo_id = "stabilityai/sdxl-turbo" #Replace to the model you would like to use
-
-if torch.cuda.is_available():
-    torch_dtype = torch.float16
-else:
-    torch_dtype = torch.float32
-
-pipe = DiffusionPipeline.from_pretrained(model_repo_id, torch_dtype=torch_dtype)
-pipe = pipe.to(device)
+# Hugging Faceのモデルをロード
+generator = pipeline('text-to-image', model='dalle-mini/dalle-mini')
 
+# 最大のシード値を定義
 MAX_SEED = np.iinfo(np.int32).max
 MAX_IMAGE_SIZE = 1024
 
-#@spaces.GPU #[uncomment to use ZeroGPU]
+# 画像生成関数
 def infer(prompt, negative_prompt, seed, randomize_seed, width, height, guidance_scale, num_inference_steps, progress=gr.Progress(track_tqdm=True)):
-
     if randomize_seed:
         seed = random.randint(0, MAX_SEED)
         
     generator = torch.Generator().manual_seed(seed)
     
-    image = pipe(
-        prompt = prompt, 
-        negative_prompt = negative_prompt,
-        guidance_scale = guidance_scale, 
-        num_inference_steps = num_inference_steps, 
-        width = width, 
-        height = height,
-        generator = generator
-    ).images[0] 
-    
-    return image, seed
+    # テキストから画像を生成
+    images = generator(prompt)
+
+    # PIL画像オブジェクトとして最初の画像をロード
+    img_url = images[0]['generated_image_url']
+    response = requests.get(img_url)
+    img = Image.open(BytesIO(response.content))
+
+    # 画像を保存してダウンロードリンクを作成
+    img.save("generated_image.png")
 
+    return img, "generated_image.png", seed
+
+# サンプルプロンプト
 examples = [
-    "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k",
-    "An astronaut riding a green horse",
-    "A delicious ceviche cheesecake slice",
+    "ジャングルの中の宇宙飛行士、寒色のパレット、 muted colors、詳細、8k",
+    "緑の馬に乗った宇宙飛行士",
+    "美味しそうなセビーチェチーズケーキスライス",
 ]
 
-css="""
+css = """
 #col-container {
     margin: 0 auto;
     max-width: 640px;
@@ -56,87 +51,85 @@ with gr.Blocks(css=css) as demo:
     
     with gr.Column(elem_id="col-container"):
         gr.Markdown(f"""
-        # Text-to-Image Gradio Template
+        # テキストから画像への生成器
         """)
         
         with gr.Row():
-            
-            prompt = gr.Text(
-                label="Prompt",
+            prompt = gr.Textbox(
+                label="プロンプト",
                 show_label=False,
                 max_lines=1,
-                placeholder="Enter your prompt",
+                placeholder="プロンプトを入力してください",
                 container=False,
             )
             
-            run_button = gr.Button("Run", scale=0)
+            run_button = gr.Button("生成", scale=0)
         
-        result = gr.Image(label="Result", show_label=False)
+        result = gr.Image(label="結果", show_label=False)
+        download_link = gr.File(label="生成された画像をダウンロード")
 
-        with gr.Accordion("Advanced Settings", open=False):
-            
-            negative_prompt = gr.Text(
-                label="Negative prompt",
+        with gr.Accordion("詳細設定", open=False):
+            negative_prompt = gr.Textbox(
+                label="ネガティブプロンプト",
                 max_lines=1,
-                placeholder="Enter a negative prompt",
+                placeholder="ネガティブプロンプトを入力してください",
                 visible=False,
             )
             
             seed = gr.Slider(
-                label="Seed",
+                label="シード",
                 minimum=0,
                 maximum=MAX_SEED,
                 step=1,
                 value=0,
             )
             
-            randomize_seed = gr.Checkbox(label="Randomize seed", value=True)
+            randomize_seed = gr.Checkbox(label="シードをランダム化", value=True)
             
             with gr.Row():
-                
                 width = gr.Slider(
-                    label="Width",
+                    label="幅",
                     minimum=256,
                     maximum=MAX_IMAGE_SIZE,
                     step=32,
-                    value=1024, #Replace with defaults that work for your model
+                    value=1024,
                 )
                 
                 height = gr.Slider(
-                    label="Height",
+                    label="高さ",
                     minimum=256,
                     maximum=MAX_IMAGE_SIZE,
                     step=32,
-                    value=1024, #Replace with defaults that work for your model
+                    value=1024,
                 )
             
             with gr.Row():
-                
                 guidance_scale = gr.Slider(
-                    label="Guidance scale",
+                    label="ガイダンススケール",
                     minimum=0.0,
                     maximum=10.0,
                     step=0.1,
-                    value=0.0, #Replace with defaults that work for your model
+                    value=7.5,
                 )
                 
                 num_inference_steps = gr.Slider(
-                    label="Number of inference steps",
+                    label="推論ステップ数",
                     minimum=1,
                     maximum=50,
                     step=1,
-                    value=2, #Replace with defaults that work for your model
+                    value=20,
                 )
         
         gr.Examples(
-            examples = examples,
-            inputs = [prompt]
+            examples=examples,
+            inputs=[prompt]
         )
+
     gr.on(
         triggers=[run_button.click, prompt.submit],
-        fn = infer,
-        inputs = [prompt, negative_prompt, seed, randomize_seed, width, height, guidance_scale, num_inference_steps],
-        outputs = [result, seed]
+        fn=infer,
+        inputs=[prompt, negative_prompt, seed, randomize_seed, width, height, guidance_scale, num_inference_steps],
+        outputs=[result, download_link, seed]
     )
 
 demo.queue().launch()