Controllable Face Generation via pretrained Conditional Adversarial Latent Autoencoder (ALAE)
-
Updated
Jun 9, 2020 - Jupyter Notebook
Controllable Face Generation via pretrained Conditional Adversarial Latent Autoencoder (ALAE)
The aim of this work is to generate new face images similar to training ones (the CelebA dataset) according to user specified attributes. To do that we ended up with an implementation of a Versatile Auxiliary Classifier + GAN.
Chinese couplet generation with transformer and simple transformer-based variants.
A partial pytorch implementation of "Latent Constraints: Learning to Generate Conditionally from Unconditional Generative Models" for practice
The code for the NeurIPS 2021 paper "A Unified View of cGANs with and without Classifiers".
Code for the paper "FAME: Fragment-based Conditional Molecular Generation for Phenotypic Drug Discovery", published on SDM 2022.
Few-Shot Diffusion Models
Conditional Generative Adversarial Network for Molecular Dynamics frame generation
Repository for the paper: 'Diffusion-based Conditional ECG Generation with Structured State Space Models'
MSc Thesis on Conditional dMRI Generative AI Models and their applicability in the decreasing scan acquisition times and bettering of patient's quality of life.
Code for "Optimal Transport-Guided Conditional Score-Based Diffusion Model (NeurIPS, 8,7,7,6)"
[ICLR 2022] Toy Experiments for Denoising Likelihood Score Matching for Conditional Score-based Data Generation
ACL'2023: DiffusionBERT: Improving Generative Masked Language Models with Diffusion Models
A Few-shot Personalized Image Editing model utilizing Stable Diffusion to enable precise image modifications based on textual descriptions and reference images (Course Project).
TRGAN: A Time-Dependent Generative Adversarial Network for Synthetic Transactional Data Generation
Forward-backward conditional sampling
[NeurIPS 2023] VPP: Efficient Conditional 3D Generation via Voxel-Point Progressive Representation
Official PyTorch implementation of "Stochastic Conditional Diffusion Models for Robust Semantic Image Synthesis" (ICML 2024).
This is the official implementation of our neural-network-based fast diffuse room impulse response generator (FAST-RIR) for generating room impulse responses (RIRs) for a given acoustic environment.
Update-to-data resources for conditional content generation, including human motion generation, image or video generation and editing.
Add a description, image, and links to the conditional-generation topic page so that developers can more easily learn about it.
To associate your repository with the conditional-generation topic, visit your repo's landing page and select "manage topics."