Create new file

app.py

@@ -0,0 +1,59 @@
+import gradio as gr
+import torch
+from PIL import Image
+
+from lambda_diffusers import StableDiffusionImageEmbedPipeline
+
+def main(
+    input_im,
+    scale=3.0,
+    n_samples=4,
+    steps=25,
+    seed=0,
+    ):
+    
+    generator = torch.Generator(device=device).manual_seed(int(seed))
+
+    images_list = pipe(
+        n_samples*[input_im],
+        guidance_scale=scale,
+        num_inference_steps=steps,
+        generator=generator,
+        )
+
+    images = []
+    for i, image in enumerate(images_list["sample"]):
+        if(images_list["nsfw_content_detected"][i]):
+            safe_image = Image.open(r"unsafe.png")
+            images.append(safe_image)
+        else:
+            images.append(image)
+    return images
+
+device = "cuda" if torch.cuda.is_available() else "cpu"
+pipe = StableDiffusionImageEmbedPipeline.from_pretrained(
+    "lambdalabs/sd-image-variations-diffusers",
+    revision="273115e88df42350019ef4d628265b8c29ef4af5",
+    )
+pipe = pipe.to(device)
+
+inputs = [
+    gr.Image(),
+    gr.Slider(0, 25, value=3, step=1, label="Guidance scale"),
+    gr.Slider(1, 4, value=1, step=1, label="Number images"),
+    gr.Slider(5, 50, value=25, step=5, label="Steps"),
+    gr.Number(0, labal="Seed", precision=0)
+]
+output = gr.Gallery(label="Generated variations")
+output.style(grid=2)
+
+demo = gr.Interface(
+    fn=main,
+    title="Stable Diffusion Image Variations",
+    description=description,
+    article=article,
+    inputs=inputs,
+    outputs=output,
+    examples=examples,
+    )
+demo.launch()