Create app.py

app.py

@@ -0,0 +1,28 @@
+import torch
+from diffusers import StableDiffusionXLPipeline, UNet2DConditionModel, EulerDiscreteScheduler
+from huggingface_hub import hf_hub_download
+from safetensors.torch import load_file
+import gradio as gr
+
+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!
+
+# Load model.
+
+def generate():
+    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")
+
+# Ensure using the same inference steps as the loaded model and CFG set to 0.
+
+
+def greet(prompt):
+    image = pipe(prompt, num_inference_steps=1, guidance_scale=0).images[0].save("output.png")
+    return image
+
+demo = gr.Interface(fn=greet, inputs="text", outputs="image")
+demo.launch()