[ECCV 24] Code for "EraseDraw: Learning to Insert Objects by Erasing Them from Images"

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

Get up and running with Llama 3.2, Mistral, Gemma 2, and other large language models.

Officail Implementation for "ReNoise: Real Image Inversion Through Iterative Noising"

A beautiful, simple, clean, and responsive Jekyll theme for academics

1-shot image segmentation using Stable Diffusion

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

LayerDiffuse in pure diffusers without any GUI

[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.

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

Open neural machine translation models and web services

Official implemention of "Make It Count: Text-to-Image Generation with an Accurate Number of Objects"

This is the official repository of our paper "What If We Recaption Billions of Web Images with LLaMA-3 ?"

Code for DesignEdit

Transparent Image Layer Diffusion using Latent Transparency

Official PyTorch Implementation of "The Hidden Attention of Mamba Models"

✂️ Automated high-quality background removal framework for an image using neural networks. ✂️

Official code for "Style Aligned Image Generation via Shared Attention"

Pythonic HTML Parsing for Humans™

Pyrallis is a framework for structured configuration parsing from both cmd and files. Simply define your desired configuration structure as a dataclass and let pyrallis do the rest!

Official Pytorch Implementation for "TokenFlow: Consistent Diffusion Features for Consistent Video Editing" presenting "TokenFlow" (ICLR 2024)

RWKV is an RNN with transformer-level LLM performance. It can be directly trained like a GPT (parallelizable). So it's combining the best of RNN and transformer - great performance, fast inference,…

A multipurpose tool for medical physics.

Implementation of Key-Locked Rank One Editing, from Nvidia AI

Subject-Diffusion:Open Domain Personalized Text-to-Image Generation without Test-time Fine-tuning

ICLR 2023 DeCap: Decoding CLIP Latents for Zero-shot Captioning

Audio fix and tipps for Asus K6500ZE

Open Vocabulary Referring Expressions Generation with Discriminative CLIP