hjk6688
Follow
Stars
Hackable and optimized Transformers building blocks, supporting a composable construction.
[ICLR2024] Official repo for paper "PnP Inversion: Boosting Diffusion-based Editing with 3 Lines of Code"
The image prompt adapter is designed to enable a pretrained text-to-image diffusion model to generate images with image prompt.
Implementation of Dreambooth (https://arxiv.org/abs/2208.12242) with Stable Diffusion
pytorch structural similarity (SSIM) loss
A novel method that provides greater control over generated images by guiding the internal representations of the pre-trained Stable Diffusion.
LPIPS metric. pip install lpips
Official Pytorch Implementation for “Plug-and-Play Diffusion Features for Text-Driven Image-to-Image Translation” (CVPR 2023)
Official implementation of CVPR 2024 paper: "FreeControl: Training-Free Spatial Control of Any Text-to-Image Diffusion Model with Any Condition"
EfficientSAM: Leveraged Masked Image Pretraining for Efficient Segment Anything
Efficient vision foundation models for high-resolution generation and perception.
FreeU: Free Lunch in Diffusion U-Net (CVPR2024 Oral)
Code for loralib, an implementation of "LoRA: Low-Rank Adaptation of Large Language Models"
Implementation of the LLaMA language model based on nanoGPT. Supports flash attention, Int8 and GPTQ 4bit quantization, LoRA and LLaMA-Adapter fine-tuning, pre-training. Apache 2.0-licensed.
collection of diffusion model papers categorized by their subareas
🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch and FLAX.
Taming Transformers for High-Resolution Image Synthesis
High-Resolution Image Synthesis with Latent Diffusion Models
This is an official implementation for "Swin Transformer: Hierarchical Vision Transformer using Shifted Windows".
Library of deep learning models and datasets designed to make deep learning more accessible and accelerate ML research.
Spring Authorization Server
An API Gateway built on Spring Framework and Spring Boot providing routing and more.