Package Health Score

56 / 100

security
Security review needed
popularity
Small
maintenance
Inactive
community
Sustainable

Explore Similar Packages

caching
42

Popularity

Small

GitHub Stars: 823
Forks: 39
Contributors: 6

Direct Usage Popularity

Based on project statistics from the GitHub repository for the PyPI package DeepCache, we found that it has been starred 823 times.

Security

Security review needed

Security and license risk for latest version

Release Date: Dec 30, 2023
Direct Vulnerabilities: 0
C
0
H
0
M
0
L
Indirect Vulnerabilities: 0
C
0
H
0
M
0
L
License Risk: 0
H
4
M
0
L

All security vulnerabilities belong to production dependencies of direct and indirect packages.

License

Apache-2.0

Security Policy

We found a way for you to contribute to the project! Looks like DeepCache is missing a security policy.

You can connect your project's repository to Snyk to stay up to date on security alerts and receive automatic fix pull requests.

Keep your project free of vulnerabilities with Snyk

Maintenance

Inactive

Commit Frequency

Open Issues: 42
Open PR: 2
Last Release: 12 months ago
Last Commit: 6 months ago

Further analysis of the maintenance status of DeepCache based on released PyPI versions cadence, the repository activity, and other data points determined that its maintenance is Inactive.

We found that DeepCache demonstrates a positive version release cadence with at least one new version released in the past 12 months.

As a healthy sign for on-going project maintenance, we found that the GitHub repository had at least 1 pull request or issue interacted with by the community.

Community

Sustainable

Readme: Yes
Contributing.md: No
Code of Conduct: No
Contributors: 6
Funding: No

This project has seen only 10 or less contributors.

We found a way for you to contribute to the project! Looks like DeepCache is missing a Code of Conduct.

Embed Package Health Score Badge

Keep your project healthy

Check your requirements.txt

Ensure all the packages you're using are healthy and well-maintained

Snyk Vulnerability Scanner

Get health score & security insights directly in your IDE

Package

Python Versions Compatibility: >=3.6

Age: 12 months
Latest Release: 12 months ago
Dependencies: 3 Direct / 28 Total
Versions: 2
Maintainers: 0
Wheels: OS Independent

Readme

DeepCache: Accelerating Diffusion Models for Free

(Results on Stable Diffusion v1.5. Left: 50 PLMS steps. Right: 2.3x acceleration upon 50 PLMS steps)

> DeepCache: Accelerating Diffusion Models for Free
> Xinyin Ma, Gongfan Fang, Xinchao Wang
> Learning and Vision Lab, National University of Singapore
> 🥯[Arxiv]🎄[Project Page]

Why DeepCache

🚀 Training-free and almost lossless
🚀 Support Stable Diffusion, Stable Diffusion XL, Stable Video Diffusion, Stable Diffusion Pipeline / XL Pipeline for Inpainting, Stable Diffusion Img2Img Pipeline, DDPM
🚀 Compatible with sampling algorithms like DDIM and PLMS

Updates

December 26, 2023: 🔥Update a plug-and-play implementation of DeepCache, no longer requiring any modifications of the diffuser's code! Check here for the detailed usage! Big thanks to @yuanshi9815 for contributing the code!
December 25, 2023: A demo is available via Colab
December 21, 2023: Release the code for Stable Video Diffusion and Text2Video-Zero. In the figure below, the upper row shows the original videos generated by SVD-XT, and the lower row is accelerated by DeepCache. For Text2Video-Zero, the results can be found here

(1.7x acceleration of SVD-XT)

December 20, 2023: Release the code for DDPM. See here for the experimental code and instructions.
December 6, 2023: Release the code for Stable Diffusion XL. The results of the stabilityai/stable-diffusion-xl-base-1.0 are shown in the below figure, with the same prompts from the first figure.

(2.6x acceleration of Stable Diffusion XL)

Introduction

We introduce DeepCache, a novel training-free and almost lossless paradigm that accelerates diffusion models from the perspective of model architecture. Utilizing the property of the U-Net, we reuse the high-level features while updating the low-level features in a very cheap way. DeepCache accelerates Stable Diffusion v1.5 by 2.3x with only a 0.05 decline in CLIP Score, and LDM-4-G(ImageNet) by 4.1x with a 0.22 decrease in FID.

Quick Start

Install

pip install DeepCache

Usage

import torch

# Loading the original pipeline
from diffusers import StableDiffusionPipeline
pipe = StableDiffusionPipeline.from_pretrained('runwayml/stable-diffusion-v1-5', torch_dtype=torch.float16).to("cuda:0")

# Import the DeepCacheSDHelper
from DeepCache import DeepCacheSDHelper
helper = DeepCacheSDHelper(pipe=pipe)
helper.set_params(
    cache_interval=3,
    cache_branch_id=0,
)
helper.enable()

# Generate Image
deepcache_image = pipe(
        prompt,
        output_type='pt'
).images[0]
helper.disable()

We here take the Stable Diffusion pipeline as an example. You can replace pipe with any variants of the Stable Diffusion pipeline, including choices like SDXL, SVD, and more. You can find examples in the script. The argument cache_branch_id specifies the selected skip branch. For the skip branches that are deeper, the model will engage them only during the caching steps, and exclude them during the retrieval steps. The argument cache_interval represents the interval for updating the cache.

Scripts

Setup

https://github.com/horseee/DeepCache.git
pip install diffusers transformers

A general script for SD

python main.py --model_type sdxl #Support [sdxl, sd1.5, sd2.1, svd, sd-inpaint, sdxl-inpaint, sd-img2img]

Stable Diffusion XL

python stable_diffusion_xl.py --model stabilityai/stable-diffusion-xl-base-1.0

Output:

Loading pipeline components...: 100%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 7/7 [00:01&lt;00:00,  6.62it/s]
2023-12-06 01:44:28,578 - INFO - Running baseline...
100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 50/50 [00:17&lt;00:00,  2.93it/s]
2023-12-06 01:44:46,095 - INFO - Baseline: 17.52 seconds
Loading pipeline components...: 100%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 7/7 [00:00&lt;00:00,  8.06it/s]
2023-12-06 01:45:02,865 - INFO - Running DeepCache...
100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 50/50 [00:06&lt;00:00,  8.01it/s]
2023-12-06 01:45:09,573 - INFO - DeepCache: 6.71 seconds
2023-12-06 01:45:10,678 - INFO - Saved to output.png. Done!

You can add --refine at the end of the command to activate the refiner model for SDXL.

Stable Diffusion v1.5

python stable_diffusion.py --model runwayml/stable-diffusion-v1-5

Output:

2023-12-03 16:18:13,636 - INFO - Loaded safety_checker as StableDiffusionSafetyChecker from `safety_checker` subfolder of runwayml/stable-diffusion-v1-5.
2023-12-03 16:18:13,699 - INFO - Loaded vae as AutoencoderKL from `vae` subfolder of runwayml/stable-diffusion-v1-5.
Loading pipeline components...: 100%|██████████████████████████████████████████████████████████████████| 7/7 [00:01&lt;00:00,  5.88it/s]
2023-12-03 16:18:22,837 - INFO - Running baseline...
100%|████████████████████████████████████████████████████████████████████████████████████████████████| 50/50 [00:03&lt;00:00, 15.33it/s]
2023-12-03 16:18:26,174 - INFO - Baseline: 3.34 seconds
2023-12-03 16:18:26,174 - INFO - Running DeepCache...
100%|████████████████████████████████████████████████████████████████████████████████████████████████| 50/50 [00:01&lt;00:00, 34.06it/s]
2023-12-03 16:18:27,718 - INFO - DeepCache: 1.54 seconds
2023-12-03 16:18:27,935 - INFO - Saved to output.png. Done!

Stable Diffusion v2.1

python stable_diffusion.py --model stabilityai/stable-diffusion-2-1

Output:

2023-12-03 16:21:17,858 - INFO - Loaded feature_extractor as CLIPImageProcessor from `feature_extractor` subfolder of stabilityai/stable-diffusion-2-1.
2023-12-03 16:21:17,864 - INFO - Loaded scheduler as DDIMScheduler from `scheduler` subfolder of stabilityai/stable-diffusion-2-1.
Loading pipeline components...: 100%|██████████████████████████████████████████████████████████████████| 6/6 [00:01&lt;00:00,  5.35it/s]
2023-12-03 16:21:49,770 - INFO - Running baseline...
100%|████████████████████████████████████████████████████████████████████████████████████████████████| 50/50 [00:14&lt;00:00,  3.42it/s]
2023-12-03 16:22:04,551 - INFO - Baseline: 14.78 seconds
2023-12-03 16:22:04,551 - INFO - Running DeepCache...
100%|████████████████████████████████████████████████████████████████████████████████████████████████| 50/50 [00:08&lt;00:00,  6.10it/s]
2023-12-03 16:22:12,911 - INFO - DeepCache: 8.36 seconds
2023-12-03 16:22:13,417 - INFO - Saved to output.png. Done!

Currently, our code supports the models that can be loaded by StableDiffusionPipeline. You can specify the model name by the argument --model, which by default, is runwayml/stable-diffusion-v1-5.

Stable Video Diffusion

python stable_video_diffusion.py

Output:

Loading pipeline components...: 100%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 5/5 [00:00&lt;00:00,  8.36it/s]
2023-12-21 04:56:47,329 - INFO - Running baseline...
100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 25/25 [01:27&lt;00:00,  3.49s/it]
2023-12-21 04:58:26,121 - INFO - Origin: 98.66 seconds
Loading pipeline components...: 100%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 5/5 [00:00&lt;00:00, 10.59it/s]
2023-12-21 04:58:27,202 - INFO - Running DeepCache...
100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 25/25 [00:49&lt;00:00,  1.96s/it]
2023-12-21 04:59:26,607 - INFO - DeepCache: 59.31 seconds

DDPM and LDM

Please check here for the experimental code of DDPM. The code for LDM will be released soon.

Visualization

Images in the upper line are the baselines, and the images in the lower line are accelerated by DeepCache.

Stable Diffusion v1.5 (2.15x Acceleration)

LDM-4-G for ImageNet (6.96x Acceleration)

DDPM for LSUN Church & Bedroom (1.48x Acceleration)

Quantitative Results

ImageNet

Stable Diffusion v1.5

More results can be found in our paper

Other Implementations and Plugins

We sincerely thank the authors listed below who implemented DeepCache in plugins or other contexts.

OneDiff Integration: https://github.com/Oneflow-Inc/onediff?tab=readme-ov-file#easy-to-use by @Oneflow-Inc. OneDiff also has implementations for DeepCache on SVD, check this for details.
Comfyui: https://gist.github.com/laksjdjf/435c512bc19636e9c9af4ee7bea9eb86 by @laksjdjf
Colab & Gradio: https://github.com/camenduru/DeepCache-colab by @camenduru
WebUI: https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14210 by @aria1th

We warmly welcome contributions from everyone. Please feel free to reach out to us.

Bibtex

@article{ma2023deepcache,
  title={DeepCache: Accelerating Diffusion Models for Free},
  author={Ma, Xinyin and Fang, Gongfan and Wang, Xinchao},
  journal={arXiv preprint arXiv:2312.00858},
  year={2023}
}

DeepCache dependencies

diffusers torch transformers

FAQs

What is DeepCache?

DeepCache: Accelerating Diffusion Models for Free. Visit Snyk Advisor to see a full health score report for DeepCache, including popularity, security, maintenance & community analysis.

Is DeepCache popular?

The python package DeepCache receives a total of 649 weekly downloads. As such, DeepCache popularity was classified as small. Visit the popularity section on Snyk Advisor to see the full health analysis.

Is DeepCache well maintained?

We found indications that DeepCache is an Inactive project. See the full package health analysis to learn more about the package maintenance status.

Is DeepCache safe to use?

While scanning the latest version of DeepCache, we found that a security review is needed. A total of 0 vulnerabilities or license issues were detected. See the full security scan results.

Last updated on 25 December-2024, at 01:01 (UTC).

Build a secure application checklist

Select a recommended open source package

Minimize your risk by selecting secure & well maintained open source packages

DONE

Scan your app for vulnerabilities

Scan your application to find vulnerabilities in your: source code, open source dependencies, containers and configuration files

SCAN NOW

Fix identified vulnerabilities

Easily fix your code by leveraging automatically generated PRs

AUTO FIX

Monitor for new issues

New vulnerabilities are discovered every day. Get notified if your application is affected

MONITOR APP

Package Health Score

Explore Similar Packages

Direct Usage Popularity

Security and license risk for latest version

Commit Frequency

Embed Package Health Score Badge

Keep your project healthy

Check your requirements.txt

Snyk Vulnerability Scanner

Readme

DeepCache: Accelerating Diffusion Models for Free

Why DeepCache

Updates

Introduction

Quick Start

Install

Usage

Scripts

Setup

A general script for SD

Stable Diffusion XL

Stable Diffusion v1.5

Stable Diffusion v2.1

Stable Video Diffusion

DDPM and LDM

Visualization

Stable Diffusion v1.5 (2.15x Acceleration)

LDM-4-G for ImageNet (6.96x Acceleration)

DDPM for LSUN Church & Bedroom (1.48x Acceleration)

Quantitative Results

ImageNet

Stable Diffusion v1.5

Other Implementations and Plugins

Bibtex

DeepCache dependencies

FAQs

What is DeepCache?

Is DeepCache popular?

Is DeepCache well maintained?

Is DeepCache safe to use?

Build a secure application checklist

Select a recommended open source package

Scan your app for vulnerabilities

Source Code

Open Source

Container

Config

Fix identified vulnerabilities

Monitor for new issues