target images

app.py

@@ -198,7 +198,7 @@ device = torch.device('cuda:0' if torch.cuda.is_available() else 'cpu')
 print('Using device:', device)
 model = load_vqgan_model(args.vqgan_config, args.vqgan_checkpoint).to(device)
 perceptor = clip.load(args.clip_model, jit=False)[0].eval().requires_grad_(False).to(device)
-def inference(text, seed, step_size, max_iterations, width, height, init_image, init_weight):
+def inference(text, seed, step_size, max_iterations, width, height, init_image, init_weight, target_images):
     all_frames = []
     size=[width, height]
     texts = text
@@ -207,7 +207,10 @@ def inference(text, seed, step_size, max_iterations, width, height, init_image,
         init_image = init_image.name
     else:
         init_image = ""
-    target_images = ""
+    if target_images:
+        target_images = target_images.name
+    else:
+        target_images = ""
     max_iterations = max_iterations
     model_names={"vqgan_imagenet_f16_16384": 'ImageNet 16384',"vqgan_imagenet_f16_1024":"ImageNet 1024", 'vqgan_openimages_f16_8192':'OpenImages 8912',
                     "wikiart_1024":"WikiArt 1024", "wikiart_16384":"WikiArt 16384", "coco":"COCO-Stuff", "faceshq":"FacesHQ", "sflckr":"S-FLCKR"}
@@ -369,6 +372,7 @@ gr.Interface(
     gr.inputs.Slider(minimum=200, maximum=500, default=256, label='height', step=1),
     gr.inputs.Image(type="file", label="Initial Image", optional=True),
     gr.inputs.Slider(minimum=0.0, maximum=15.0, default=0.0, label='Initial Weight', step=1.0),
+    gr.inputs.Image(type="file", label="Target Image", optional=True)
      ], 
     [gr.outputs.Image(type="numpy", label="Output Image"),gr.outputs.Image(type="file", label="Output GIF")],
     title=title,