Create ITV.py

ITV.py

@@ -0,0 +1,26 @@
+import torch
+from diffusers import CogVideoXImageToVideoPipeline
+from diffusers.utils import export_to_video, load_image
+
+prompt = "A little girl is riding a bicycle at high speed. Focused, detailed, realistic."
+image = load_image(image="input.jpg")
+pipe = CogVideoXImageToVideoPipeline.from_pretrained(
+    "THUDM/CogVideoX1.5-5B-I2V",
+    torch_dtype=torch.bfloat16
+)
+
+pipe.enable_sequential_cpu_offload()
+pipe.vae.enable_tiling()
+pipe.vae.enable_slicing()
+
+video = pipe(
+    prompt=prompt,
+    image=image,
+    num_videos_per_prompt=1,
+    num_inference_steps=50,
+    num_frames=81,
+    guidance_scale=6,
+    generator=torch.Generator(device="cuda").manual_seed(42),
+).frames[0]
+
+export_to_video(video, "output.mp4", fps=8)