update app

app.py

@@ -27,8 +27,8 @@ prompt = f"A photo of {unique_id} {class_label} in a bucket"
 # image = pipeline(prompt, num_inference_steps=50).images[0]
 
 # generate images
-def infer(prompt):
-    generated_images = pipeline(prompt, guidance_scale=10, num_inference_steps=50, num_images_per_prompt=2)
+def infer(prompt, negative_prompt, guidance_scale=10, num_inference_steps=50):
+    generated_images = pipeline(prompt, guidance_scale=guidance_scale, num_inference_steps=num_inference_steps, num_images_per_prompt=2)
     
     return generated_images.images
     
@@ -37,5 +37,13 @@ output = gr.Gallery(label="Outputs").style(grid=(1,2))
 # customize interface
 title = "KerasCV Stable Diffusion Demo on images of Ace."
 description = "This is a dreambooth model fine-tuned on images of my pug named Ace. To try it, input the concept with `puggieace dog`."
-examples=[["A photo of puggieace dog in space"]]
-gr.Interface(infer, inputs=["text"], outputs=[output], title=title, description=description, examples=examples).queue().launch()
+examples=[
+    ["A photo of puggieace dog in space", "", 50, 10],
+    ["A photo of a cute puggieace dog getting a haircut in a barbershop, ultra realistic, intricate details, highly detailed, photorealistic, octane render, 8 k, unreal engine. art by artgerm and greg rutkowski and charlie bowater and magali villeneuve and alphonse mucha", "", 75, 12],
+    ["Portrait painting of a cute puggieace dog with armor, ultra realistic, concept art, intricate details, eerie, highly detailed, photorealistic, octane render, 8 k, unreal engine. art by artgerm and greg rutkowski and charlie bowater", "", 75, 12],
+]
+gr.Interface(infer, inputs=[gr.Textbox(label="Positive Prompt", value="a photo of puggieace dog getting a haircut"),
+        gr.Textbox(label="Negative Prompt", value="bad anatomy, blurry"),
+        gr.Slider(label='Number of gen image', minimum=1, maximum=4, value=2, step=1),
+        gr.Slider(label="Inference Steps",value=50),
+        gr.Number(label='Guidance scale', value=12),], outputs=[output], title=title, description=description, examples=examples).queue().launch()