Open-source alternatives to Disco Diffusion

IF is a text-to-image diffusion system that translates natural language descriptions into visual imagery. The project provides a generative pipeline for creating images, an inpainting tool for modifying specific image sections, and a super-resolution upscaler to increase pixel density and clarity. The system includes a concept fine-tuning framework that allows for the teaching of new visual concepts by updating a small set of parameters. It also supports image style transfer to apply the aesthetic characteristics of a reference image to a new output.

CLIP FFT/DWT/RGB = text to image/video

This project is a generative adversarial network implementation and research framework. It provides the tools and hyperparameters necessary to train and evaluate generative models across various datasets, specifically designed to reproduce results from academic research. The framework includes a Parzen density likelihood estimator to calculate model log likelihood. This allows for the quantitative evaluation of generative distributions and the measurement of overall model performance. The codebase covers machine learning research capabilities, focusing on the training of adversarial networks

Invertible conditional GANs for image editing

Pytorch implementation

Official Pytorch Implementation of Residual Vision Transformers(ResViT) which is described in the following paper:

Official repository for ABC-GAN

Adversarially Learned Inference

Toward Multimodal Image-to-Image Translation

CycleGAN is a generative adversarial network framework designed for unpaired image-to-image translation. It enables the conversion of images between two distinct visual domains using datasets that do not require direct one-to-one matching examples. The project implements a deep learning style transfer tool capable of artistic style transfer, object transfiguration, and domain-to-domain conversion. It uses a dual-generator architecture and cycle-consistency loss to ensure that images translated to a target domain and back recover their original state. The framework covers core machine learnin

iGAN is a framework for producing synthetic images using generative adversarial networks. It provides a web-based interface for interactively creating and editing imagery across categories such as landscapes, architecture, and fashion using pre-trained models. The system enables precise control over visual output through latent space exploration, interpolation, and projection. Users can guide the generative process using an interactive editor featuring sketching, coloring, and warping brushes to refine specific regions or shapes in real-time. The project supports both automated scripted gene

Image Deblurring using Generative Adversarial Networks

TIP'19 AttGAN: Facial Attribute Editing by Only Changing What You Want

Lucid Sonic Dreams syncs GAN-generated visuals to music. By default, it uses NVLabs StyleGAN2, with pre-trained models lifted from Justin Pinkney's consolidated repository. Custom weights and other GAN architectures can be used as well.

pix2pixHD is a conditional generative adversarial network designed to transform semantic label maps into high-resolution photorealistic images. It functions as a high-resolution image synthesizer and an image-to-image translation model capable of producing synthetic images at 2048x1024 resolution. The system includes a semantic image editor that allows for the modification of high-resolution visuals by updating the underlying semantic label maps. This enables interactive image editing and the generation of photorealistic images based on source images or discrete label maps. The framework pro

Point-e is a system for 3D model synthesis that generates three-dimensional point clouds from natural language descriptions and two-dimensional images. It utilizes diffusion models to synthesize these spatial representations based on text prompts or source images. The project includes specialized tools for refining these outputs, such as a point cloud upsampler to increase the density and resolution of low-resolution models. It also provides a mesh converter that uses distance function regression to transform raw point cloud data into structured 3D meshes. The broader capability surface cove

pix2pix is a framework for image-to-image translation using conditional generative adversarial networks. It functions as a supervised trainer and visual domain mapper designed to learn a mapping between input and output images for style and domain transfer. The system utilizes a U-Net encoder-decoder architecture combined with a PatchGAN local discriminator to enforce high-frequency local consistency. It employs L1 loss regularization to ensure generated outputs remain structurally close to the ground truth. The project covers a broad range of computer vision capabilities, including semantic

Pixray is an image generation system. It combines previous ideas including:

Generative Adversarial Text-to-Image Synthesis

Learning What and Where to Draw

We propose a novel approach to translate unpaired contrast computed tomography (CT) scans to non-contrast CT scans and the other way around. In addition, we introduce a novel data set, Coltea-Lung-CT-100W, containing 3D triphasic lung CT scans (with a total of 37,290 images) collected from 100…

Generate images from texts. In Russian

This code is for our paper "VTGAN: Semi-supervised Retinal Image Synthesis and Disease Prediction using Vision Transformers" which is part of the supplementary materials for ICCV 2021 Workshop on Computer Vision for Automated Medical Diagnosis. The paper has since been accpeted and presented at…

NeurIPS 2024 Official code for PuLID: Pure and Lightning ID Customization via Contrastive Alignment

This project is an implementation of the Generative Adversarial Network proposed in our CVPR 2017 paper - DeLiGAN : Generative Adversarial Networks for Diverse and Limited Data. DeLiGAN is a simple but effective modification of the GAN framework and aims to improve performance on datasets which are diverse yet small in size.

Official Chainer implementation of GP-GAN: Towards Realistic High-Resolution Image Blending (ACMMM 2019, oral)