Custom Diffusion: Creating Video from Frame Using Multiple Diffusion
Project description
Installation
pip install custom_diffusion
Usage
# Importing the required libraries
from custom_diffusion.utils.data_utils import load_images_from_folder
from custom_diffusion import StableDiffusionControlNetGenerator
from custom_diffusion.utils.video_utils import convert_images_to_video
from custom_diffusion.demo import video_pipeline
# Creating a video from a video file
frames_path = video_pipeline(
video_path="test.mp4",
output_path="output.mp4",
start_time=0,
end_time=5,
frame_rate=1,
)
# Creating a video from a folder of images
images_list = load_images_from_folder(frames_path)
prompt = "a anime boy"
negative_prompt = "bad"
list_prompt = [prompt] * len(images_list)
list_negative_prompt = [negative_prompt] * len(images_list)
# Generating images from a list of images
generator = StableDiffusionControlNetGenerator()
generated_image_list = generator.generate_image(
stable_model_path="andite/anything-v4.0",
controlnet_model_path="lllyasviel/control_v11p_sd15_canny",
scheduler_name="EulerAncestralDiscrete",
images_list=images_list,
prompt=list_prompt,
negative_prompt=list_negative_prompt,
height=512,
width=512,
guess_mode=False,
num_images_per_prompt=1,
num_inference_steps=30,
guidance_scale=7.0,
controlnet_conditioning_scale=1.0,
generator_seed=0,
preprocess_type="Canny",
resize_type="center_crop_and_resize",
crop_size=512,
)
# Converting the generated images to a video
frame2video = convert_images_to_video(
image_list=generated_image_list,
output_file="output.mp4",
frame_rate=5,
)
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
custom_diffusion-0.1.9.tar.gz
(17.0 kB
view details)
File details
Details for the file custom_diffusion-0.1.9.tar.gz
.
File metadata
- Download URL: custom_diffusion-0.1.9.tar.gz
- Upload date:
- Size: 17.0 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/4.0.1 CPython/3.9.12
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | 35609dd81f7dc8e5e1a0fe4e037cb0c3d9e1e9405afea57b02d14631f96f31c7 |
|
MD5 | bb8068fa50e466b0c7a12587ec046530 |
|
BLAKE2b-256 | 2fc1946d80681467d18d824d0ae27b43c0ecbeecbf36a3ee4ce45de54fa2d4cb |