I am currently using google colab to create a video out of spliced Modelscope outputs. When I try to display a video in colab using IPython(from IPython.display import Video), the video doesn’t render at all, which limits me from playing it. When I try to download the .mp4 to my local device, I get the following:
Here is my code for reference
pipe = DiffusionPipeline.from_pretrained("cerspense/zeroscope_v2_576w", torch_dtype=torch.float16)
pipe.scheduler = DPMSolverMultistepScheduler.from_config(pipe.scheduler.config)
pipe.enable_model_cpu_offload()
for index, description in enumerate(slide_descriptions[:-2], start=1):
insert=description.split("-")[-1]
print(f"Slide {index}: {insert}")
prompt = insert
video_frames = pipe(prompt, num_inference_steps=40, height=320, width=576, num_frames=24).frames
#video_frames = pipe(prompt, num_inference_steps=25).frames
video_path = export_to_video(video_frames, output_video_path=f"videos/part{index}.mp4")
files.download("videos/part10.mp4")
Video("videos/part10.mp4")
Let me know if anyone can help me out with this issue! Thanks and Merry Christmas!