Update app.py

app.py

@@ -1,31 +1,43 @@
 import streamlit as st
-from diffusers import StableDiffusionPipeline
+import torch
+from diffusers import StableDiffusionXLPipeline, UNet2DConditionModel, EulerDiscreteScheduler
+from huggingface_hub import hf_hub_download
+from safetensors.torch import load_file
 
-# Define function to generate AI image
-def generate_image(prompt, width, height):
-    pipeline = StableDiffusionPipeline.from_single_file(
-        "https://huggingface.co/Geek7/testing/blob/main/dreamshaper_8.safetensors"
-    )
+# Define a function to generate the image
+def generate_image(prompt, num_inference_steps):
+    base = "stable-diffusion"
+    repo = "Geek7/testing"
+    ckpt = "dreamshaper_8.safetensors" # Use the correct ckpt for your step setting!
 
-    # Generate image using the provided prompt
-    image = pipeline.run(prompt=prompt, width=width, height=height)
+    # Load model.
+    unet = UNet2DConditionModel.from_config(base, subfolder="unet").to("cuda", torch.float16)
+    unet.load_state_dict(load_file(hf_hub_download(repo, ckpt), device="cuda"))
+    pipe = StableDiffusionXLPipeline.from_pretrained(base, unet=unet, torch_dtype=torch.float16, variant="fp16").to("cuda")
+
+    # Ensure sampler uses "trailing" timesteps.
+    pipe.scheduler = EulerDiscreteScheduler.from_config(pipe.scheduler.config, timestep_spacing="trailing")
+
+    # Generate image
+    image = pipe(prompt, num_inference_steps=num_inference_steps, guidance_scale=0).images[0]
 
     return image
 
 # Main function for Streamlit app
 def main():
     st.title("AI Image Generator")
-    
+
     # Input fields
     prompt = st.text_input("Enter prompt")
-    width = st.number_input("Width", min_value=1, step=1)
-    height = st.number_input("Height", min_value=1, step=1)
+    num_inference_steps = st.slider("Number of Inference Steps", min_value=1, max_value=10, value=2)
 
     if st.button("Generate Image"):
         # Check if prompt is provided
         if prompt:
             # Generate image
-            generated_image = generate_image(prompt, width, height)
+            generated_image = generate_image(prompt, num_inference_steps)
+            # Save image
+            generated_image.save("output.png")
             # Display image
             st.image(generated_image, caption='Generated Image', use_column_width=True)
         else: