world modeling challenge for humanoid robots

Official implementation of HumanVid, NeurIPS D&B Track 2024

This is the official reproduction of FancyVideo.

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

Hiera: A fast, powerful, and simple hierarchical vision transformer.

A PyTorch implementation of MAGE: MAsked Generative Encoder to Unify Representation Learning and Image Synthesis

Ultra-low Bitrate Image Semantic Compression Driven by Large Multimodal Model

[LMM + codec] A new paradigm of visual signal compression!

Code for "Hierarchical World Models as Visual Whole-Body Humanoid Controllers"

Code for "Unleashing Large-Scale Video Generative Pre-training for Visual Robot Manipulation"

[ECCV 2024] Official implementation of the paper "Semantic-SAM: Segment and Recognize Anything at Any Granularity"

code for "Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusion"

Kolors Team

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

[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 …

[ECCV 2024, Oral] DynamiCrafter: Animating Open-domain Images with Video Diffusion Priors

PyTorch implementation of RCG https://arxiv.org/abs/2312.03701

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

Official JAX implementation of MAGVIT: Masked Generative Video Transformer

Reference implementation for DPO (Direct Preference Optimization)

[COLM 2024] LoraHub: Efficient Cross-Task Generalization via Dynamic LoRA Composition

A quick guide (especially) for trending instruction finetuning datasets

An automatic evaluator for instruction-following language models. Human-validated, high-quality, cheap, and fast.