Update app.py

app.py

@@ -114,7 +114,7 @@ normalize = transforms.Normalize(mean=[0.48145466, 0.4578275, 0.40821073],
                                  std=[0.26862954, 0.26130258, 0.27577711])
 lpips_model = lpips.LPIPS(net='vgg').to(device)
     
-def inference(text):
+def inference(text, image, skip_timesteps):
     all_frames = []
     prompts = [text]
     image_prompts = []
@@ -124,8 +124,8 @@ def inference(text):
     range_scale = 50            # Controls how far out of range RGB values are allowed to be.
     cutn = 16
     n_batches = 1
-    init_image = None   # This can be an URL or Colab local path and must be in quotes.
-    skip_timesteps = 0  # This needs to be between approx. 200 and 500 when using an init image.
+    init_image = image.name   # This can be an URL or Colab local path and must be in quotes.
+    skip_timesteps = skip_timesteps  # This needs to be between approx. 200 and 500 when using an init image.
                         # Higher values make the output look more like the init.
     init_scale = 0      # This enhances the effect of the init image, a good value is 1000.
     seed = 0
@@ -214,6 +214,6 @@ def inference(text):
 title = "CLIP Guided Diffusion HQ"
 description = "Gradio demo for CLIP Guided Diffusion. To use it, simply add your text, or click one of the examples to load them. Read more at the links below."
 article = "<p style='text-align: center'> By Katherine Crowson (https://github.com/crowsonkb, https://twitter.com/RiversHaveWings). It uses OpenAI's 256x256 unconditional ImageNet diffusion model (https://github.com/openai/guided-diffusion) together with CLIP (https://github.com/openai/CLIP) to connect text prompts with images. | <a href='https://colab.research.google.com/drive/12a_Wrfi2_gwwAuN3VvMTwVMz9TfqctNj' target='_blank'>Colab</a></p>"
-iface = gr.Interface(inference, inputs="text", outputs=["image","video"], title=title, description=description, article=article, examples=[["coral reef city by artistation artists"]],
+iface = gr.Interface(inference, inputs=["text",gr.inputs.Image(type="file", label='initial image (optional)', optional=True),gr.inputs.Slider(minimum=0, maximum=500, step=1, default=0, label="skip_timesteps")], outputs=["image","video"], title=title, description=description, article=article, examples=[["coral reef city by artistation artists"]],
     enable_queue=True)
 iface.launch()