<div align="center">
<h2>
Custom Diffusion: Creating Video from Frame Using Diffusion
</h2>
<div>
<a href="https://pepy.tech/project/custom_diffusion"><img src="https://pepy.tech/badge/custom_diffusion" alt="downloads"></a>
<a href="https://badge.fury.io/py/custom_diffusion"><img src="https://badge.fury.io/py/custom_diffusion.svg" alt="pypi version"></a>
<a href="https://huggingface.co/spaces/ArtGAN/Stable-Diffusion-ControlNet-WebUI"><img src="https://huggingface.co/datasets/huggingface/badges/raw/main/open-in-hf-spaces-sm.svg" alt="HuggingFace Spaces"></a>
</div>
</div>
### Installation
```bash
pip install custom_diffusion
```
### Usage
```python
# 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,
)
```
Raw data
{
"_id": null,
"home_page": "https://github.com/kadirnar/Custom-Diffusion",
"name": "custom-diffusion",
"maintainer": "",
"docs_url": null,
"requires_python": ">=3.6",
"maintainer_email": "",
"keywords": "machine-learning,deep-learning,pytorch,diffusion,diffusion models,controlnet,stable diffusion",
"author": "kadirnar",
"author_email": "",
"download_url": "https://files.pythonhosted.org/packages/2f/c1/946d80681467d18d824d0ae27b43c0ecbeecbf36a3ee4ce45de54fa2d4cb/custom_diffusion-0.1.9.tar.gz",
"platform": null,
"description": "<div align=\"center\">\r\n<h2>\r\n Custom Diffusion: Creating Video from Frame Using Diffusion\r\n</h2>\r\n<div>\r\n <a href=\"https://pepy.tech/project/custom_diffusion\"><img src=\"https://pepy.tech/badge/custom_diffusion\" alt=\"downloads\"></a>\r\n <a href=\"https://badge.fury.io/py/custom_diffusion\"><img src=\"https://badge.fury.io/py/custom_diffusion.svg\" alt=\"pypi version\"></a>\r\n <a href=\"https://huggingface.co/spaces/ArtGAN/Stable-Diffusion-ControlNet-WebUI\"><img src=\"https://huggingface.co/datasets/huggingface/badges/raw/main/open-in-hf-spaces-sm.svg\" alt=\"HuggingFace Spaces\"></a>\r\n</div>\r\n</div>\r\n\r\n\r\n### Installation\r\n```bash\r\npip install custom_diffusion\r\n```\r\n\r\n### Usage\r\n```python\r\n\r\n# Importing the required libraries\r\n\r\nfrom custom_diffusion.utils.data_utils import load_images_from_folder\r\nfrom custom_diffusion import StableDiffusionControlNetGenerator\r\nfrom custom_diffusion.utils.video_utils import convert_images_to_video\r\nfrom custom_diffusion.demo import video_pipeline\r\n\r\n# Creating a video from a video file\r\nframes_path = video_pipeline(\r\n video_path=\"test.mp4\",\r\n output_path=\"output.mp4\",\r\n start_time=0,\r\n end_time=5,\r\n frame_rate=1,\r\n)\r\n\r\n# Creating a video from a folder of images\r\nimages_list = load_images_from_folder(frames_path)\r\n\r\nprompt = \"a anime boy\"\r\nnegative_prompt = \"bad\"\r\n\r\nlist_prompt = [prompt] * len(images_list)\r\nlist_negative_prompt = [negative_prompt] * len(images_list)\r\n\r\n# Generating images from a list of images\r\ngenerator = StableDiffusionControlNetGenerator()\r\n\r\ngenerated_image_list = generator.generate_image(\r\n stable_model_path=\"andite/anything-v4.0\",\r\n controlnet_model_path=\"lllyasviel/control_v11p_sd15_canny\",\r\n scheduler_name=\"EulerAncestralDiscrete\",\r\n images_list=images_list,\r\n prompt=list_prompt,\r\n negative_prompt=list_negative_prompt,\r\n height=512,\r\n width=512,\r\n guess_mode=False,\r\n num_images_per_prompt=1,\r\n num_inference_steps=30,\r\n guidance_scale=7.0,\r\n controlnet_conditioning_scale=1.0,\r\n generator_seed=0,\r\n preprocess_type=\"Canny\",\r\n resize_type=\"center_crop_and_resize\",\r\n crop_size=512,\r\n)\r\n\r\n# Converting the generated images to a video\r\nframe2video = convert_images_to_video(\r\n image_list=generated_image_list,\r\n output_file=\"output.mp4\",\r\n frame_rate=5,\r\n)\r\n```\r\n",
"bugtrack_url": null,
"license": "Apache License 2.0",
"summary": "Custom Diffusion: Creating Video from Frame Using Multiple Diffusion",
"version": "0.1.9",
"project_urls": {
"Homepage": "https://github.com/kadirnar/Custom-Diffusion"
},
"split_keywords": [
"machine-learning",
"deep-learning",
"pytorch",
"diffusion",
"diffusion models",
"controlnet",
"stable diffusion"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "2fc1946d80681467d18d824d0ae27b43c0ecbeecbf36a3ee4ce45de54fa2d4cb",
"md5": "bb8068fa50e466b0c7a12587ec046530",
"sha256": "35609dd81f7dc8e5e1a0fe4e037cb0c3d9e1e9405afea57b02d14631f96f31c7"
},
"downloads": -1,
"filename": "custom_diffusion-0.1.9.tar.gz",
"has_sig": false,
"md5_digest": "bb8068fa50e466b0c7a12587ec046530",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.6",
"size": 16958,
"upload_time": "2023-06-20T17:18:35",
"upload_time_iso_8601": "2023-06-20T17:18:35.763774Z",
"url": "https://files.pythonhosted.org/packages/2f/c1/946d80681467d18d824d0ae27b43c0ecbeecbf36a3ee4ce45de54fa2d4cb/custom_diffusion-0.1.9.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2023-06-20 17:18:35",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "kadirnar",
"github_project": "Custom-Diffusion",
"travis_ci": false,
"coveralls": false,
"github_actions": false,
"requirements": [],
"lcname": "custom-diffusion"
}
JSON
