Update app.py

app.py

@@ -1,11 +1,11 @@
 import gradio as gr
 import os
 import random
-from PIL import Image
 import spaces
 import torch
 from transformers import MllamaForConditionalGeneration, AutoProcessor
 from OmniGen import OmniGenPipeline
+from PIL import Image
 
 from huggingface_hub import login
 Llama32V_HFtoken = os.getenv("Llama32V")
@@ -27,7 +27,8 @@ def predict_clothing(images):
     input_text = processor.apply_chat_template(messages, add_generation_prompt=True)
 
     output_texts = []
-    for image in images:
+    for url in images:
+        image = Image.open(requests.get(url, stream=True).raw)
         print(type(image))
         inputs = processor(image, input_text, add_special_tokens=False, return_tensors="pt").to(model.device)
         with torch.no_grad():
@@ -129,32 +130,32 @@ with gr.Blocks() as demo:
             image_input_2 = gr.Image(label="Top-wear", type="filepath")
             image_input_3 = gr.Image(label="Bottom-wear", type="filepath")
 
-        with gr.Row(equal_height=True):
-            with gr.Column():
-                # sliders
-                max_input_image_size = gr.Slider(label="max_input_image_size", minimum=128, maximum=2048, value=1024, step=16)
-                
-                height_input = gr.Slider(label="Height", minimum=128, maximum=1024, value=512, step=16)
-                width_input = gr.Slider(label="Width", minimum=128, maximum=1024, value=512, step=16)
-        
-                # guidance_scale_input = gr.Slider(label="Guidance Scale", minimum=1.0, maximum=5.0, value=2.5, step=0.1)
-        
-                num_inference_steps = gr.Slider(label="Inference Steps", minimum=1, maximum=128, value=32, step=1)
-        
-                seed_input = gr.Slider(label="Seed", minimum=0, maximum=2147483647, value=42, step=1)
-                randomize_seed = gr.Checkbox(label="Randomize seed", value=True)
+    with gr.Row():
+        with gr.Column():
+            # sliders
+            max_input_image_size = gr.Slider(label="max_input_image_size", minimum=128, maximum=2048, value=1024, step=16)
+            
+            height_input = gr.Slider(label="Height", minimum=128, maximum=1024, value=512, step=16)
+            width_input = gr.Slider(label="Width", minimum=128, maximum=1024, value=512, step=16)
+    
+            # guidance_scale_input = gr.Slider(label="Guidance Scale", minimum=1.0, maximum=5.0, value=2.5, step=0.1)
     
-            with gr.Column():
-                img_guidance_scale_input = gr.Slider(label="img_guidance_scale", minimum=1.0, maximum=2.0, value=1.6, step=0.1)
-                
-                separate_cfg_infer = gr.Checkbox(
-                    label="separate_cfg_infer", info="Whether to use separate inference process for different guidance. This will reduce the memory cost.", value=True,)
-                
-                offload_model = gr.Checkbox(
-                    label="offload_model", info="Offload model to CPU, which will significantly reduce the memory cost but slow down the generation speed. You can cancel separate_cfg_infer and set offload_model=True. If both separate_cfg_infer and offload_model are True, further reduce the memory, but slowest generation", value=False,)
-                
-                use_input_image_size_as_output = gr.Checkbox(
-                    label="use_input_image_size_as_output", info="Automatically adjust the output image size to be same as input image size. For editing and controlnet task, it can make sure the output image has the same size as input image leading to better performance", value=False,)
+            num_inference_steps = gr.Slider(label="Inference Steps", minimum=1, maximum=128, value=32, step=1)
+    
+            seed_input = gr.Slider(label="Seed", minimum=0, maximum=2147483647, value=42, step=1)
+            randomize_seed = gr.Checkbox(label="Randomize seed", value=True)
+
+        with gr.Column():
+            img_guidance_scale_input = gr.Slider(label="img_guidance_scale", minimum=1.0, maximum=2.0, value=1.6, step=0.1)
+            
+            separate_cfg_infer = gr.Checkbox(
+                label="separate_cfg_infer", info="Whether to use separate inference process for different guidance. This will reduce the memory cost.", value=True,)
+            
+            offload_model = gr.Checkbox(
+                label="offload_model", info="Offload model to CPU, which will significantly reduce the memory cost but slow down the generation speed. You can cancel separate_cfg_infer and set offload_model=True. If both separate_cfg_infer and offload_model are True, further reduce the memory, but slowest generation", value=False,)
+            
+            use_input_image_size_as_output = gr.Checkbox(
+                label="use_input_image_size_as_output", info="Automatically adjust the output image size to be same as input image size. For editing and controlnet task, it can make sure the output image has the same size as input image leading to better performance", value=False,)
 
         # generate
         generate_button = gr.Button("Generate Image")