Create app.py

app.py

@@ -0,0 +1,49 @@
+import gradio as gr
+import torch
+from diffusers import StableDiffusionImg2ImgPipeline
+from PIL import Image
+
+# Load model (CPU mode)
+model_id = "runwayml/stable-diffusion-v1-5"
+pipe = StableDiffusionImg2ImgPipeline.from_pretrained(model_id, torch_dtype=torch.float32)
+pipe = pipe.to("cpu")
+
+def generate_image(init_image, prompt, strength, guidance_scale, steps):
+    if init_image is None:
+        return None
+
+    init_image = init_image.convert("RGB")
+    init_image = init_image.resize((512, 512))
+
+    images = pipe(
+        prompt=prompt,
+        image=init_image,
+        strength=strength,
+        guidance_scale=guidance_scale,
+        num_inference_steps=steps
+    ).images
+
+    return images[0]
+
+# Gradio UI
+with gr.Blocks() as demo:
+    gr.Markdown("## 🖼️ CPU Image-to-Image Generator")
+
+    with gr.Row():
+        with gr.Column():
+            init_image = gr.Image(label="Upload Gambar", type="pil")
+            prompt = gr.Textbox(label="Prompt", placeholder="Deskripsi gambar...")
+            strength = gr.Slider(0.1, 1.0, value=0.6, step=0.05, label="Denoising Strength")
+            guidance_scale = gr.Slider(1, 20, value=7.5, step=0.5, label="CFG Scale")
+            steps = gr.Slider(10, 50, value=25, step=1, label="Steps")
+            btn = gr.Button("Generate")
+        with gr.Column():
+            output_image = gr.Image(label="Hasil", type="pil")
+
+    btn.click(
+        fn=generate_image,
+        inputs=[init_image, prompt, strength, guidance_scale, steps],
+        outputs=[output_image]
+    )
+
+demo.launch()