Update app.py

app.py

@@ -5,23 +5,26 @@ from safetensors.torch import load_file
 import gradio as gr
 import spaces
 
-
 base = "stabilityai/stable-diffusion-xl-base-1.0"
 repo = "ByteDance/SDXL-Lightning"
-ckpt = "sdxl_lightning_1step_unet_x0.safetensors" # Use the correct ckpt for your step setting!
+ckpt = "sdxl_lightning_4step_unet.safetensors" # Use the correct ckpt for your step setting!
+
+# 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 and "sample" prediction type.
-pipe.scheduler = EulerDiscreteScheduler.from_config(pipe.scheduler.config, timestep_spacing="trailing", prediction_type="sample")
+pipe.scheduler = EulerDiscreteScheduler.from_config(pipe.scheduler.config, timestep_spacing="trailing")
+
 # Load model.
 @spaces.GPU
-def generate(prompt):
-    image = pipe(prompt, num_inference_steps=1, guidance_scale=0).images[0]
+def generate(prompt, steps):
+    image = pipe(prompt, num_inference_steps=steps, guidance_scale=0).images[0]
     return image
 
 output_image = gr.Image(type="pil")
-demo = gr.Interface(fn=generate, inputs="text", outputs=output_image)
+demo = gr.Interface(fn=generate, inputs=[gr.Text, gr.slider], outputs=output_image)
 
 if __name__ == "__main__":
     unet = UNet2DConditionModel.from_config(base, subfolder="unet").to("cuda", torch.float16)