Dominic Rampas

Q-Align. ③[ICML2024] [IQA, IAA, VQA] All-in-one Foundation Model for visual scoring. Can efficiently fine-tune to downstream datasets.

ml-flextok. FlexTok: Resampling Images into 1D Token Sequences of Flexible Length

skits. scikit-learn-inspired time series

managers-playbook. :book: Heuristics for effective management

OneIG-Benchmark. [NeurIPS 2025 DB] OneIG-Bench is a meticulously designed comprehensive benchmark framework for fine-grained evaluation of T2I models across multiple dimensions, including subject-element alignment, text rendering precision, reasoning-generated content, stylization, and diversity.

discrete-flow-matching-pytorch. Discrete Flow Matching implemented in PyTorch

HunyuanImage-3.0. HunyuanImage-3.0: A Powerful Native Multimodal Model for Image Generation

spinningup. An educational resource to help anyone learn deep reinforcement learning.

vjepa2. PyTorch code and models for VJEPA2 self-supervised learning from video.

owl-vaes. Weird autoencoder experiments

GeodesicDiffusion. Offical implementation for "Probability Density Geodesics in Image Diffusion Latent Space" (CVPR2025)

RADIO. Official repository for "AM-RADIO: Reduce All Domains Into One"

lucid-v1. realtime latent world model inference demo

reimei. Jupyter Notebook

REPA-E. [ICCV 2025] Official implementation of the paper: REPA-E: Unlocking VAE for End-to-End Tuning of Latent Diffusion Transformers

Pyramid-Flow. [ICLR 2025] Pyramidal Flow Matching for Efficient Video Generative Modeling

OmniEdit. Official Repo for Paper "OmniEdit: Building Image Editing Generalist Models Through Specialist Supervision" [ICLR2025]

LuminaBrush. Illumination Drawing Tools for Text-to-Image Diffusion Models

LTX-Video. Official repository for LTX-Video

deepcompressor. Model Compression Toolbox for Large Language Models and Diffusion Models

nunchaku. [ICLR2025 Spotlight] SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models

Manim-Tutorials-2021. Python

OmniGen. OmniGen: Unified Image Generation. https://arxiv.org/pdf/2409.11340

efficientvit. Efficient vision foundation models for high-resolution generation and perception.

MF_Tools. Collection of helpful utilities for Manim. Now dual compatible with both editions!

ComfyUI. The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.

tqdm. :zap: A Fast, Extensible Progress Bar for Python and CLI

flux. Official inference repo for FLUX.1 models

jepa. PyTorch code and models for V-JEPA self-supervised learning from video.

llama3. The official Meta Llama 3 GitHub site

pykan. Kolmogorov Arnold Networks

llama. Inference code for Llama models

VAR. [NeurIPS 2024 Best Paper Award][GPT beats diffusion🔥] [scaling laws in visual generation📈] Official impl. of "Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction". An *ultra-simple, user-friendly yet state-of-the-art* codebase for autoregressive image generation!

vmaf. Perceptual video quality assessment based on multi-method fusion.

optimum-quanto. A pytorch quantization backend for optimum

Hotshot-XL. ✨ Hotshot-XL: State-of-the-art AI text-to-GIF model trained to work alongside Stable Diffusion XL

CascadeTuner. Implements a minimalistic version of Stable Cascade training

stable_cascade_easy. Text to Img with Stable Cascade(on gradio interface), required less vram than original example on official Hugginface

InstantID. InstantID: Zero-shot Identity-Preserving Generation in Seconds 🔥

eclipse-inference. [CVPR 2024] Official PyTorch implementation of "ECLIPSE: Revisiting the Text-to-Image Prior for Efficient Image Generation"

score_sde_pytorch. PyTorch implementation for Score-Based Generative Modeling through Stochastic Differential Equations (ICLR 2021, Oral)

w-plus-adapter. [CVPR 2024] When StyleGAN Meets Stable Diffusion: a W+ Adapter for Personalized Image Generation

gdf. Python

GaussianEditor. [CVPR 2024] GaussianEditor: Swift and Controllable 3D Editing with Gaussian Splatting

KandinskyVideo. KandinskyVideo — multilingual end-to-end text2video latent diffusion model

InstaFlow. :zap: InstaFlow! One-Step Stable Diffusion with Rectified Flow (ICLR 2024)

RetNet. An implementation of "Retentive Network: A Successor to Transformer for Large Language Models"

WorldModel. WorldModel is a MaskGIT model trained on 8x8x8 Minecraft voxel volumes. Beyond generating blocks from scratch, it excels in filling spaces based on neighboring blocks, ensuring seamless integration in Minecraft worlds

minSDXL. Huggingface-compatible SDXL Unet implementation that is readily hackable

DiffBIR. [ECCV 2024] codes of DiffBIR: Towards Blind Image Restoration with Generative Diffusion Prior

IP-Adapter. The image prompt adapter is designed to enable a pretrained text-to-image diffusion model to generate images with image prompt.

im2im. Python

StarlightVision. A multi-modal AI Model that can generate high quality novel videos with text, images, or video clips.

oft. Official implementation of "Controlling Text-to-Image Diffusion by Orthogonal Finetuning".

LyCORIS. Lora beYond Conventional methods, Other Rank adaptation Implementations for Stable diffusion.

ManimML. ManimML is a project focused on providing animations and visualizations of common machine learning concepts with the Manim Community Library.

sd-scripts. Python

I2SB. Python

shap-e. Generate 3D objects conditioned on text or images

generative-models. Generative Models by Stability AI

open-muse. Open reproduction of MUSE for fast text2image generation.

Wuerstchen. Official implementation of Würstchen: Efficient Pretraining of Text-to-Image Models

GenerateCT. ECCV 2024 & GenerateCT: Text-Conditional Generation of 3D Chest CT Volumes

Wuerstchen. Official implementation of Würstchen: Efficient Pretraining of Text-to-Image Models

fastcomposer. [IJCV] FastComposer: Tuning-Free Multi-Subject Image Generation with Localized Attention

ImageBind. ImageBind One Embedding Space to Bind Them All

pytorch-tools. Useful PyTorch functions and modules that are not implemented in PyTorch by default

diffusion. Python

transformers. 🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

MUSE-Pytorch. An in-context conditioning version of MUSE with pre-trained checkpoints.

SDGAN. SDGAN: Tuning Stable Diffusion with an adversarial network

consistency-mnist. A simple consistency model for MNIST.

k-diffusion. Karras et al. (2022) diffusion models for PyTorch

consistency-models. A JAX implementation of the continuous time formulation of Consistency Models

IF. Python

Open-Assistant. OpenAssistant is a chat-based assistant that understands tasks, can interact with third-party systems, and retrieve information dynamically to do so.

DiffFit-pytorch. Implementation of "DiffFit: Unlocking Transferability of Large Diffusion Models via Simple Parameter-Efficient Fine-Tuning"

agd. Automatic gradient descent

novelai-aspect-ratio-bucketing. Implementation of aspect ratio bucketing for training generative image models as described in: https://blog.novelai.net/novelai-improvements-on-stable-diffusion-e10d38db82ac

svdiff-pytorch. Implementation of "SVDiff: Compact Parameter Space for Diffusion Fine-Tuning"

Kandinsky-2. Kandinsky 2 — multilingual text2image latent diffusion model

ColossalAI. Making large AI models cheaper, faster and more accessible

align_sd. Better Aligning Text-to-Image Models with Human Preference. ICCV 2023

alpaca-lora. Instruct-tune LLaMA on consumer hardware

lion-pytorch. 🦁 Lion, new optimizer discovered by Google Brain using genetic algorithms that is purportedly better than Adam(w), in Pytorch

Paella. Official Implementation of Paella https://arxiv.org/abs/2211.07292v2

cc2dataset. Easily convert common crawl to a dataset of caption and document. Image/text Audio/text Video/text, ...

manim-2x2-matrix-multiplication. Python

byt5. Python

ControlNet. Let us control diffusion models!

stylegan-t. [ICML'23] StyleGAN-T: Unlocking the Power of GANs for Fast Large-Scale Text-to-Image Synthesis

magvit. Official JAX implementation of MAGVIT: Masked Generative Video Transformer

LoRA. Code for loralib, an implementation of "LoRA: Low-Rank Adaptation of Large Language Models"

chatgpt-google-extension. This project is deprecated. Check my new project ChatHub:

diffusers. 🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch.

Arroz-Con-Cosas. Experimental LDM uses of Paella's architecture

Versatile-Diffusion. Versatile Diffusion: Text, Images and Variations All in One Diffusion Model, arXiv 2022 / ICCV 2023

Diffusion-Models-pytorch. Pytorch implementation of Diffusion Models (https://arxiv.org/pdf/2006.11239.pdf)

phenaki-pytorch. Implementation of Phenaki Video, which uses Mask GIT to produce text guided videos of up to 2 minutes in length, in Pytorch

webvid. Large-scale text-video dataset. 10 million captioned short videos.

video2dataset. Easily create large video dataset from video urls

XPretrain. Multi-modality pre-training

prompt-to-prompt. Jupyter Notebook

efficient-prompt-to-prompt. Jupyter Notebook

cycle-diffusion. [ICCV 2023] A latent space for stochastic diffusion models

phenaki. A phenaki reproduction using pytorch.

Diffusion-Models-pytorch. Pytorch implementation of Diffusion Models (https://arxiv.org/pdf/2006.11239.pdf)

open_clip. An open source implementation of CLIP.

DDPMs-Pytorch. Implementation of various DDPM papers to understand how they work

coyo-dataset. COYO-700M: Large-scale Image-Text Pair Dataset

dream-bench. A tool for benchmarking image generation models.

Cold-Diffusion-Models. Official implementation of Cold-Diffusion for different transformations in pytorch.

long-video-gan. Official PyTorch implementation of LongVideoGAN

pytorch-fid. Compute FID scores with PyTorch.

stable-diffusion. A latent text-to-image diffusion model

textual_inversion. Jupyter Notebook

simple-tar-dataset. An unopinionated replacement for PyTorch's Dataset and ImageFolder, that handles Tar archives

loss-landscape. Code for visualizing the loss landscape of neural nets

DDPM. PyTorch DDPM implementation

pytorch_diffusion. PyTorch reimplementation of Diffusion Models

diffusion. Denoising Diffusion Probabilistic Models

VQ-Diffusion. Official implementation of VQ-Diffusion

CogVideo. text and image to video generation: CogVideoX (2024) and CogVideo (ICLR 2023)

SDEdit. PyTorch implementation for SDEdit: Image Synthesis and Editing with Stochastic Differential Equations

Imagen-pytorch. Python

imagen-pytorch. Implementation of Imagen, Google's Text-to-Image Neural Network, in Pytorch

majesty-diffusion. Majesty Diffusion by @Dango233(@Dango233max) and @apolinario (@multimodalart)

E2FGVI. Official code for "Towards An End-to-End Framework for Flow-Guided Video Inpainting" (CVPR2022)

img2dataset. Easily turn large sets of image urls to an image dataset. Can download, resize and package 100M urls in 20h on one machine.

webdataset. A high-performance Python-based I/O system for large (and small) deep learning problems, with strong support for PyTorch.

super-resolution. This is the LAION repository for creating open super-resolution models with the help of LAION-5B subsets.

laion-dreams. Aim for the moon. If you miss, you may hit a star.

BSRGAN. Designing a Practical Degradation Model for Deep Blind Image Super-Resolution (ICCV, 2021) (PyTorch) - We released the training code!

big_vision. Official codebase used to develop Vision Transformer, SigLIP, MLP-Mixer, LiT and more.

Barbershop. Barbershop: GAN-based Image Compositing using Segmentation Masks (SIGGRAPH Asia 2021)

CogView2. official code repo for paper "CogView2: Faster and Better Text-to-Image Generation via Hierarchical Transformers"

DALLE2-pytorch. Implementation of DALL-E 2, OpenAI's updated text-to-image synthesis neural network, in Pytorch

Neighborhood-Attention-Transformer. Neighborhood Attention Transformer, arxiv 2022 / CVPR 2023. Dilated Neighborhood Attention Transformer, arxiv 2022

surgeon-pytorch. A library to inspect and extract intermediate layers of PyTorch models.

pytorch-optimizer. torch-optimizer -- collection of optimizers for Pytorch

anyres-gan. Python

Centipede_Diffusion. Jupyter Notebook

enhancing-transformers. An unofficial implementation of both ViT-VQGAN and RQ-VAE in Pytorch

rudalle-aspect-ratio. Python

rq-vae-transformer. The official implementation of Autoregressive Image Generation using Residual Quantization (CVPR '22)

dalle-mini. DALL·E Mini - Generate images from a text prompt

TATS. Official PyTorch implementation of TATS: A Long Video Generation Framework with Time-Agnostic VQGAN and Time-Sensitive Transformer (ECCV 2022)

maskgit. Official Jax Implementation of MaskGIT

denoising-diffusion-gan. Tackling the Generative Learning Trilemma with Denoising Diffusion GANs https://arxiv.org/abs/2112.07804

latent-diffusion. High-Resolution Image Synthesis with Latent Diffusion Models

glid-3. combination of OpenAI GLIDE and Latent Diffusion

VQ-Diffusion. Python

cloob-training. CLOOB training (JAX) and inference (JAX and PyTorch)

conceptual-12m. Conceptual 12M is a dataset containing (image-URL, caption) pairs collected for vision-and-language pre-training.

Awesome-Text-to-Image. (ෆ`꒳´ෆ) A Survey on Text-to-Image Generation/Synthesis.

vector-quantize-pytorch. Vector (and Scalar) Quantization, in Pytorch

my-gen-clip. In-progress implementation of GEN-CLIP

awesome-generative-ai. A curated list of Generative AI tools, works, models, and references

denoising-diffusion-pytorch. Implementation of Denoising Diffusion Probabilistic Model in Pytorch

ru-dalle. Generate images from texts. In Russian

RealBasicVSR. Official repository of "Investigating Tradeoffs in Real-World Video Super-Resolution"

improved-diffusion. Release for Improved Denoising Diffusion Probabilistic Models

VAN-Classification. Python

VQGAN-pytorch. Pytorch implementation of VQGAN (Taming Transformers for High-Resolution Image Synthesis) (https://arxiv.org/pdf/2012.09841.pdf)

sahi. Framework agnostic sliced/tiled inference + interactive ui + error analysis plots

feed_forward_vqgan_clip. Feed forward VQGAN-CLIP model, where the goal is to eliminate the need for optimizing the latent space of VQGAN for each input prompt

ffcv. FFCV: Fast Forward Computer Vision (and other ML workloads!)

MaskGIT-pytorch. Pytorch implementation of MaskGIT: Masked Generative Image Transformer (https://arxiv.org/pdf/2202.04200.pdf)

deep-image-prior. Image restoration with neural networks but without learning.

VQGAN-CLIP. Just playing with getting VQGAN+CLIP running locally, rather than having to use colab.

ghost. A new one shot face swap approach for image and video domains

instant-ngp. Instant neural graphics primitives: lightning fast NeRF and more

explaining-in-style. Jupyter Notebook

ConvNeXt. Code release for ConvNeXt model

ru-dolph. RUDOLPH: One Hyper-Tasking Transformer can be creative as DALL-E and GPT-3 and smart as CLIP

mae. PyTorch implementation of MAE https//arxiv.org/abs/2111.06377

v-diffusion-pytorch. v objective diffusion inference code for PyTorch.

glide-text2im. GLIDE: a diffusion-based text-conditional image synthesis model

poolformer. PoolFormer: MetaFormer Is Actually What You Need for Vision (CVPR 2022 Oral)

TensorRT. PyTorch/TorchScript/FX compiler for NVIDIA GPUs using TensorRT

TensorRT. NVIDIA® TensorRT™ is an SDK for high-performance deep learning inference on NVIDIA GPUs. This repository contains the open source components of TensorRT.

deep-stabilization. Python

gangealing. Official PyTorch Implementation of "GAN-Supervised Dense Visual Alignment" (CVPR 2022 Oral, Best Paper Finalist)

pytorch-image-models. The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (ViT), MobileNetV4, MobileNet-V3 & V2, RegNet, DPN, CSPNet, Swin Transformer, MaxViT, CoAtNet, ConvNeXt, and more

clean-fid. PyTorch - FID calculation with proper image resizing and quantization steps [CVPR 2022]

lama. 🦙 LaMa Image Inpainting, Resolution-robust Large Mask Inpainting with Fourier Convolutions, WACV 2022

ProjectedGAN-pytorch. Pytorch implementation of ProjectedGAN (https://arxiv.org/abs/2111.01007)

Vector-Quantization. A collection of implementations for papers using vector quantization.

taming-transformers. Taming Transformers for High-Resolution Image Synthesis

mle-hyperopt. Lightweight Hyperparameter Optimization 🚂

Paper-Implemenations. A collection of implemented papers from the DL/ML field.

ByteTrack. [ECCV 2022] ByteTrack: Multi-Object Tracking by Associating Every Detection Box

stylegan3. Official PyTorch implementation of StyleGAN3

DeepFaceLive. Real-time face swap for PC streaming or video calls

fairseq. Facebook AI Research Sequence-to-Sequence Toolkit written in Python.

muzic. Muzic: Music Understanding and Generation with Artificial Intelligence

awesome-multiple-object-tracking. Resources for Multiple Object Tracking (MOT)

CodeGenX. Code Generation using GPT-J!

speechbrain. A PyTorch-based Speech Toolkit

dino. PyTorch code for Vision Transformers training with the Self-Supervised learning method DINO