Akomand/CausalDiffAE
Code Repository for CausalDiffAE (ECAI 2024)
This project helps machine learning researchers and practitioners generate high-quality images where specific elements have been altered based on defined causal relationships. You provide an existing image dataset and a causal model (like 'A causes B'), and it outputs new, counterfactual images showing what the original might look like if 'A' were different. It's designed for those exploring how changes to one part of an image causally influence other parts.
No commits in the last 6 months.
Use this if you need to generate realistic image variations by intervening on specific, causally related factors within the image, rather than just random alterations.
Not ideal if you are looking for general-purpose image generation without needing to define and manipulate causal relationships, or if your data isn't high-dimensional image data.
Stars
20
Forks
4
Language
Python
License
—
Category
Last pushed
Oct 19, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/Akomand/CausalDiffAE"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
xie-lab-ml/Golden-Noise-for-Diffusion-Models
[ICCV2025] The code of our work "Golden Noise for Diffusion Models: A Learning Framework".
yulewang97/ERDiff
[NeurIPS 2023 Spotlight] Official Repo for "Extraction and Recovery of Dpatio-temporal Structure...
UNIC-Lab/RadioDiff
This is the code for the paper "RadioDiff: An Effective Generative Diffusion Model for...
pantheon5100/pid_diffusion
This repository is the official implementation of the paper: Physics Informed Distillation for...
zju-pi/diff-sampler
An open-source toolbox for fast sampling of diffusion models. Official implementations of our...