Update app.py

app.py

@@ -105,10 +105,14 @@ zs = torch.randn([10000, G.mapping.z_dim], device=device)
 w_stds = G.mapping(zs, None).std(0)
     
     
-def inference(text):
+def inference(text,steps,image):
   all_frames = []
   target = clip_model.embed_text(text)
-  steps = 150
+  if image:
+      target = embed_image(image.name)
+  else:
+      target = clip_model.embed_text(text)
+  steps = steps
   seed = 2
   tf = Compose([
       Resize(224),
@@ -165,7 +169,7 @@ article = "<p style='text-align: center'>colab by https://twitter.com/nshepperd1
 examples = [['elon musk']]
 gr.Interface(
     inference, 
-    "text", 
+    ["text",gr.inputs.Slider(minimum=50, maximum=200, step=1, default=150, label="steps"),gr.inputs.Image(type="pil", label="Image (Optional)", optional=True)], 
     [gr.outputs.Image(type="pil", label="Output"),"playable_video"],
     title=title,
     description=description,