merge CLIPSeg demo

app.py

@@ -1,6 +1,7 @@
 import os
 import torch
 import gradio as gr
+import numpy as np
 from PIL import Image
 import matplotlib.pyplot as plt
 from diffusers import DiffusionPipeline
@@ -38,7 +39,7 @@ def read_content(file_path):
     return content
 
 
-def predict(dict, reference, scale, seed, step):
+def predict(dict, text_query, reference, scale, seed, step):
     width, height = dict["image"].size
     if width < height:
         factor = width / 512.0
@@ -52,6 +53,8 @@ def predict(dict, reference, scale, seed, step):
 
     init_image = dict["image"].convert("RGB").resize((width, height))
     mask = dict["mask"].convert("RGB").resize((width, height))
+    print(np.array(mask))
+    print(text_query)
     generator = torch.Generator('cuda').manual_seed(seed) if seed != 0 else None
     output = pipe(
         image=init_image,
@@ -119,8 +122,9 @@ with image_blocks as demo:
         with gr.Box():
             with gr.Row():
                 with gr.Column():
-                    image = gr.Image(source='upload', tool='sketch', elem_id="image_upload", type="pil", label="Source Image")
-                    reference = gr.Image(source='upload', elem_id="image_upload", type="pil", label="Reference Image")
+                    image = gr.Image(source="upload", tool="sketch", elem_id="image_upload", type="pil", label="Source Image")
+                    text = gr.Textbox(lines=1, placeholder="Clothing item you want to replace...")
+                    reference = gr.Image(source="upload", elem_id="image_upload", type="pil", label="Reference Image")
 
                 with gr.Column():
                     image_out = gr.Image(label="Output", elem_id="output-img").style(height=400)
@@ -146,7 +150,7 @@ with image_blocks as demo:
                 with gr.Column():
                     gr.Examples(ref_list, inputs=[reference],label="Examples - Reference Image",examples_per_page=12)
             
-            btn.click(fn=predict, inputs=[image, reference, guidance, seed, steps], outputs=[image_out, community_icon, loading_icon, share_button])
+            btn.click(fn=predict, inputs=[image, text, reference, guidance, seed, steps], outputs=[image_out, community_icon, loading_icon, share_button])
             share_button.click(None, [], [], _js=share_js)
 
             gr.HTML(