update

app.py

@@ -7,13 +7,27 @@ os.environ["CUDA_VISIBLE_DEVICES"]="0"
 import torch
 import gradio as gr
 
+best_model_list = [
+    "runwayml/stable-diffusion-v1-5",
+    "CompVis/stable-diffusion-v1-4",
+    "prompthero/openjourney",
+    "dreamlike-art/dreamlike-photoreal-2.0",
+    "dreamlike-art/dreamlike-diffusion-1.0",
+    "stabilityai/stable-diffusion-2-inpainting"
+]
+
+orig_prompt = "Create a relaxing atmosphere with the use of plants and other natural elements. Such as a hanging terrarium or a wall-mounted planter. Include plenty of storage options to keep the space organized and clutter-free. Consider adding a vanity with double sinks and plenty of drawers and cabinets. As well as a wall mounted medicine and towel storage."
+orig_negative_prompt = "lurry, bad art, blurred, text, watermark"
+
 
 def stable_diffusion_zoom_out(
   repo_id="stabilityai/stable-diffusion-2-inpainting",
-  original_prompt="a dog",
-  negative_prompt="a cat",
+  original_prompt,
+  negative_prompt,
   steps=32,
   num_frames=10,
+  image_size=512,
+  fps=16
 ):
   pipe = DiffusionPipeline.from_pretrained(repo_id, torch_dtype=torch.float16, revision="fp16")
   pipe.set_use_memory_efficient_attention_xformers(True)
@@ -21,7 +35,7 @@ def stable_diffusion_zoom_out(
   pipe = pipe.to("cuda")
   pipe.safety_checker = dummy
 
-  current_image = Image.new(mode="RGBA", size=(512, 512))
+  current_image = Image.new(mode="RGBA", size=(image_size,image_size))
   mask_image = np.array(current_image)[:,:,3] # assume image has alpha mask (use .mode to check for "RGBA")
   mask_image = Image.fromarray(255-mask_image).convert("RGB")
   current_image = current_image.convert("RGB")
@@ -38,11 +52,11 @@ def stable_diffusion_zoom_out(
 
   for i in range(num_frames):
     next_image = np.array(current_image.convert("RGBA"))*0
-    prev_image = current_image.resize((512-2*steps,512-2*steps))
+    prev_image = current_image.resize((image_size-2*steps,image_size-2*steps))
     prev_image = prev_image.convert("RGBA")
     prev_image = np.array(prev_image)
     next_image[:, :, 3] = 1
-    next_image[steps:512-steps,steps:512-steps,:] = prev_image
+    next_image[steps:image_size-steps,steps:image_size-steps,:] = prev_image
     prev_image = Image.fromarray(next_image)
     current_image = prev_image
     mask_image = np.array(current_image)[:,:,3] # assume image has alpha mask (use .mode to check for "RGBA")
@@ -58,12 +72,15 @@ def stable_diffusion_zoom_out(
   return save_path
 
 inputs = [
-  gr.Dropdown(["stabilityai/stable-diffusion-2-inpainting"], label="Model"),
-  gr.inputs.Textbox(lines=1, default="a dog", label="Prompt"),
-  gr.inputs.Textbox(lines=1, default="a cat", label="Negative Prompt"),
+  gr.Dropdown(choices=best_model_list,default="stabilityai/stable-diffusion-2-inpainting",label="Model"),
+  gr.inputs.Textbox(lines=1, default=orig_prompt, label="Prompt"),
+  gr.inputs.Textbox(lines=1, default=orig_negative_prompt, label="Negative Prompt"),
   gr.inputs.Slider(minimum=1, maximum=64, default=32, label="Steps"),
-  gr.inputs.Slider(minimum=1, maximum=100, default=10, label="Frames"),
+  gr.inputs.Slider(minimum=1, maximum=500, default=10, step=10, label="Frames"),
+  gr.inputs.Slider(minimum=128, maximum=1024, default=512, step=256, label="Image Size"),
+  gr.inputs.Slider(minimum=1, maximum=100, default=16, step=1, label="FPS")
 ]
+
 output = gr.outputs.Video()
 title = "Stable Diffusion Infinite Zoom Out"