Update app.py

app.py

@@ -7,9 +7,6 @@ import os
 from huggingface_hub import hf_hub_download
 from diffusers import StableDiffusionXLPipeline, AutoencoderKL, EulerAncestralDiscreteScheduler
 from compel import Compel, ReturnedEmbeddingsType
-from PIL import Image, PngImagePlugin
-import json
-import io
 
 # =====================================
 # Prompt weights
@@ -215,25 +212,6 @@ def get_embed_new(prompt, pipeline, compel, only_convert_string=False, compel_pr
 
     return merge_embeds([prompt_attention_to_invoke_prompt(i) for i in global_prompt_chanks], compel)
 
-# Add metadata to the image
-def add_metadata_to_image(image, metadata):
-    metadata_str = json.dumps(metadata)
-    
-    # Convert PIL Image to PNG with metadata
-    img_with_metadata = image.copy()
-    
-    # Create a PngInfo object and add metadata
-    png_info = PngImagePlugin.PngInfo()
-    png_info.add_text("parameters", metadata_str)
-    
-    # Save to a byte buffer with metadata
-    buffer = io.BytesIO()
-    img_with_metadata.save(buffer, format="PNG", pnginfo=png_info)
-    
-    # Reopen from buffer to get the image with metadata
-    buffer.seek(0)
-    return Image.open(buffer)
-
 def add_comma_after_pattern_ti(text):
     pattern = re.compile(r'\b\w+_\d+\b')
     modified_text = pattern.sub(lambda x: x.group() + ',', text)
@@ -246,6 +224,7 @@ MAX_SEED = np.iinfo(np.int32).max
 MAX_IMAGE_SIZE = 2048
 
 if torch.cuda.is_available():
+    vae = AutoencoderKL.from_pretrained("madebyollin/sdxl-vae-fp16-fix", torch_dtype=torch.float16)
     token = os.environ.get("HF_TOKEN")  # 从环境变量读取令牌
     model_path = hf_hub_download(
         repo_id="Menyu/Pixel",  # 模型仓库名称（非完整URL）
@@ -254,6 +233,7 @@ if torch.cuda.is_available():
     )
     pipe = StableDiffusionXLPipeline.from_single_file(
         model_path,
+        vae=vae,
         use_safetensors=True,
         torch_dtype=torch.float16,
     )
@@ -292,8 +272,6 @@ def infer(
     # 在 infer 函数中调用 get_embed_new
     if not use_negative_prompt:
         negative_prompt = ""
-    
-    original_prompt = prompt  # Store original prompt for metadata
     prompt = get_embed_new(prompt, pipe, compel, only_convert_string=True)
     negative_prompt = get_embed_new(negative_prompt, pipe, compel, only_convert_string=True)
     conditioning, pooled = compel([prompt, negative_prompt]) # 必须同时处理来保证长度相等
@@ -311,25 +289,7 @@ def infer(
         generator=generator,
         use_resolution_binning=use_resolution_binning,
     ).images[0]
-
-    # Create metadata dictionary
-    metadata = {
-        "prompt": original_prompt,
-        "processed_prompt": prompt,
-        "negative_prompt": negative_prompt,
-        "seed": seed,
-        "width": width,
-        "height": height,
-        "guidance_scale": guidance_scale,
-        "num_inference_steps": num_inference_steps,
-        "model": "MiaoMiaoPixel_V1.0",
-        "use_resolution_binning": use_resolution_binning,
-        "PreUrl": "https://huggingface.co/spaces/Menyu/MiaoPixel"
-    }
-    # Add metadata to the image
-    image_with_metadata = add_metadata_to_image(image, metadata)
-    
-    return image_with_metadata, seed
+    return image, seed
 
 examples = [
     "nahida (genshin impact)",