GithubHelp home page GithubHelp logo

beibuwandeluori / drct Goto Github PK

View Code? Open in Web Editor NEW
66.0 66.0 3.0 12.92 MB

The official code of "DRCT: Diffusion Reconstruction Contrastive Training towards Universe Detection of Diffusion Generated Images"

Python 98.37% Shell 1.63%

drct's Introduction

About me

  • 👋 Name: BokingChen (Baoying Chen)
  • 💞️ Graduated from: South China Agricultural University (2015.9-2019.7), Shenzhen University (2019.9-2022.7)
  • 🌱 Research direction: AI-Generated Image/Video/Audio Detection, Multimedia Forensics, Deepfake Detection, Data Security

Awards

Papers

Patents

drct's People

Contributors

beibuwandeluori avatar

Stargazers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

Watchers

 avatar  avatar

drct's Issues

The parameter settings for SD reconstruction

Great work! Could you please share the details of your parameter settings when using the SD model for reconstruction? For example, the prompt, denoising strength and guidance scale?

test on my own dataset?

Hello, if I want to use the pretrained model you provided to test my data sets, is it possible to change the following list to my test data set?
ps:
test1, test2 are my test data sets, their directory structure is consistent with your test data set, train2017, val2017

from:
CLASS2LABEL_MAPPING = {
'real': 0, # 正常图像, MSCOCO, ImageNet等
'ldm-text2im-large-256': 1, # 'CompVis/ldm-text2im-large-256': 'Latent Diffusion', # Latent Diffusion 基础版本
'stable-diffusion-v1-4': 2, # 'CompVis/stable-diffusion-v1-4': 'Stable Diffusion', # 现实版本
'stable-diffusion-v1-5': 3, # 'runwayml/stable-diffusion-v1-5': 'Stable Diffusion', # 现实版本
'stable-diffusion-2-1': 4,
'stable-diffusion-xl-base-1.0': 5,
'stable-diffusion-xl-refiner-1.0': 6,
'sd-turbo': 7,
'sdxl-turbo': 8,
'lcm-lora-sdv1-5': 9,
'lcm-lora-sdxl': 10,
'sd-controlnet-canny': 11,
'sd21-controlnet-canny': 12,
'controlnet-canny-sdxl-1.0': 13,
'stable-diffusion-inpainting': 14,
'stable-diffusion-2-inpainting': 15,
'stable-diffusion-xl-1.0-inpainting-0.1': 16,
}

to:
CLASS2LABEL_MAPPING = {
'real': 0, # 正常图像, MSCOCO, ImageNet等
'test1': 1, # 'CompVis/ldm-text2im-large-256': 'Latent Diffusion', # Latent Diffusion 基础版本
'test2': 2, # 'CompVis/stable-diffusion-v1-4': 'Stable Diffusion', # 现实版本

}

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.