mikkel

tiktoken

tiktoken is a fast BPE tokeniser for use with OpenAI's models.

Open-Sora-Plan

This project aim to reproduce Sora (Open AI T2V model), we wish the open source community contribute to this project.

AnyText

Official implementation code of the paper <AnyText: Multilingual Visual Text Generation And Editing>

researchgpt

A LLM based research assistant that allows you to have a conversation with a research paper

PyTorch-StudioGAN

StudioGAN is a Pytorch library providing implementations of representative Generative Adversarial Networks (GANs) for conditional/unconditional image generation.

imgclsmob

Sandbox for training deep learning networks

sglang

SGLang is a structured generation language designed for large language models (LLMs). It makes your interaction with models faster and more controllable.

LayerDiffuse

Transparent Image Layer Diffusion using Latent Transparency

InstantStyle

InstantStyle: Free Lunch towards Style-Preserving in Text-to-Image Generation 🔥

DeepPrivacy

DeepPrivacy: A Generative Adversarial Network for Face Anonymization

PixArt-sigma

PixArt-Σ: Weak-to-Strong Training of Diffusion Transformer for 4K Text-to-Image Generation

SPIN

The official implementation of Self-Play Fine-Tuning (SPIN)

VILA

VILA - a multi-image visual language model with training, inference and evaluation recipe, deployable from cloud to edge (Jetson Orin and laptops)

sliders

Concept Sliders for Precise Control of Diffusion Models

MergeLM

Codebase for Merging Language Models (ICML 2024)

erasing

Erasing Concepts from Diffusion Models

Magic-Me

Codes for ID-Specific Video Customized Diffusion

dora

Implementation of DoRA

wgan-gp

Pytorch implementation of Wasserstein GANs with Gradient Penalty

ComfyUI-SVD

Experimental use of stable-video-diffusion in ComfyUI

Implicit-Competitive-Regularization

Code for: Implicit Competitive Regularization in GANs

Diffusion-RWKV

Scaling RWKV-Like Architectures for Diffusion Models

safetensors-merge-supermario

Merge safetensor files using the technique described in "Language Models are Super Mario: Absorbing Abilities from Homologous Models as a Free Lunch"

tpuDCGAN

Train DCGAN with TPUs on Google Cloud

CGD

This repository contains the Julia code for the paper "Competitive Gradient Descent"

gan-flow

diffusion-evolver

Evolve diffusion models by merging.

JARE

Code for Towards a Better Understanding and Regularization of GAN Training Dynamics

SRGANs

Image Generation on ImageNet Based on ImageNet

split-nano

A dashboard for creating Nano cryptocurrency accounts that automatically forward to multiple addresses.