diffusers 0.30.3

v0.30.3: CogVideoX Image-to-Video and Video-to-Video

on Python PyPI

import torch
from diffusers import CogVideoXImageToVideoPipeline
from diffusers.utils import export_to_video, load_image

pipe = CogVideoXImageToVideoPipeline.from_pretrained("THUDM/CogVideoX-5b-I2V", torch_dtype=torch.bfloat16)
pipe.to("cuda")

# Optionally, enable memory optimizations.
# If enabling CPU offloading, remember to remove `pipe.to("cuda")` above
pipe.enable_model_cpu_offload()
pipe.vae.enable_tiling()

prompt = "An astronaut hatching from an egg, on the surface of the moon, the darkness and depth of space realised in the background. High quality, ultrarealistic detail and breath-taking movie-like camera shot."
image = load_image(
    "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/astronaut.jpg"
)
video = pipe(image, prompt, use_dynamic_cfg=True)
export_to_video(video.frames[0], "output.mp4", fps=8)

import torch
from diffusers import CogVideoXDPMScheduler, CogVideoXVideoToVideoPipeline
from diffusers.utils import export_to_video, load_video

# Models: "THUDM/CogVideoX-2b" or "THUDM/CogVideoX-5b"
pipe = CogVideoXVideoToVideoPipeline.from_pretrained("THUDM/CogVideoX-5b-trial", torch_dtype=torch.bfloat16)
pipe.scheduler = CogVideoXDPMScheduler.from_config(pipe.scheduler.config)
pipe.to("cuda")

input_video = load_video(
    "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/hiker.mp4"
)
prompt = (
    "An astronaut stands triumphantly at the peak of a towering mountain. Panorama of rugged peaks and "
    "valleys. Very futuristic vibe and animated aesthetic. Highlights of purple and golden colors in "
    "the scene. The sky is looks like an animated/cartoonish dream of galaxies, nebulae, stars, planets, "
    "moons, but the remainder of the scene is mostly realistic."
)

video = pipe(
    video=input_video, prompt=prompt, strength=0.8, guidance_scale=6, num_inference_steps=50
).frames[0]
export_to_video(video, "output.mp4", fps=8)