Create app.py

app.py

@@ -0,0 +1,52 @@
+import gradio as gr
+import torch
+from diffusers import I2VGenXLPipeline
+from diffusers.utils import export_to_gif, load_image
+import spaces
+
+# Initialize the pipeline
+pipeline = I2VGenXLPipeline.from_pretrained("ali-vilab/i2vgen-xl", torch_dtype=torch.float16, variant="fp16")
+pipeline.enable_model_cpu_offload()
+
+@spaces.GPU
+def generate_gif(image, prompt, negative_prompt, num_inference_steps, guidance_scale, seed):
+    # Load the image
+    image = load_image(image).convert("RGB")
+
+    # Set the generator seed
+    generator = torch.manual_seed(seed)
+
+    # Generate the frames
+    frames = pipeline(
+        prompt=prompt,
+        image=image,
+        num_inference_steps=num_inference_steps,
+        negative_prompt=negative_prompt,
+        guidance_scale=guidance_scale,
+        generator=generator
+    ).frames[0]
+
+    # Export to GIF
+    gif_path = "i2v.gif"
+    export_to_gif(frames, gif_path)
+
+    return gif_path
+
+# Create the Gradio interface
+iface = gr.Interface(
+    fn=generate_gif,
+    inputs=[
+        gr.Image(type="filepath", label="Input Image"),
+        gr.Textbox(lines=2, placeholder="Enter your prompt here...", label="Prompt"),
+        gr.Textbox(lines=2, placeholder="Enter your negative prompt here...", label="Negative Prompt"),
+        gr.Slider(1, 100, step=1, default=50, label="Number of Inference Steps"),
+        gr.Slider(1, 20, step=0.1, default=9.0, label="Guidance Scale"),
+        gr.Number(label="Seed", default=8888)
+    ],
+    outputs=gr.File(label="Generated GIF"),
+    title="I2VGen-XL GIF Generator",
+    description="Generate a GIF from an image and a prompt using the I2VGen-XL model."
+)
+
+# Launch the interface
+iface.launch()