Highlights
- Pro
Stars
Human Preference Score v2: A Solid Benchmark for Evaluating Human Preferences of Text-to-Image Synthesis
📪 idealclover 的新个人主页,基于 Astro 和 Tailwind CSS 构建。灵感来自于 bento.me
Hunyuan-DiT : A Powerful Multi-Resolution Diffusion Transformer with Fine-Grained Chinese Understanding
FlexiFilm: Long Video Generation with Flexible Conditions
⏰ Collaboratively track deadlines of conferences recommended by CCF (Website, Python Cli, Wechat Applet) / If you find it useful, please star this project, thanks~
Official implementation of MCVD: Masked Conditional Video Diffusion for Prediction, Generation, and Interpolation (https://arxiv.org/abs/2205.09853)
FlexiFilm: Long Video Generation with Flexible Conditions
TensorFlow implementation for our paper "Learning Long-Term Reward Redistribution via Randomized Return Decomposition"
Best Practices on Recommendation Systems
The latest paper list of large language model (LLM) for recommendation
Train transformer language models with reinforcement learning.
Leveraging BERT and c-TF-IDF to create easily interpretable topics.
Fast EMD for Python: a wrapper for Pele and Werman's C++ implementation of the Earth Mover's Distance metric
Reference BLEU implementation that auto-downloads test sets and reports a version string to facilitate cross-lab comparisons
Official inference library for Mistral models
Open Academic Research on Improving LLaMA to SOTA LLM
Open-Sora: Democratizing Efficient Video Production for All
You can easily calculate FVD, PSNR, SSIM, LPIPS for evaluating the quality of generated or predicted videos.
Quick scripts to calculate CLIP text-image similarity
Latte: Latent Diffusion Transformer for Video Generation.
LaVIT: Empower the Large Language Model to Understand and Generate Visual Content
Peak signal-to-noise ratio and The structural similarity calculation tool
Measures and metrics for image2image tasks. PyTorch.
[ICLR 2024] Code for FreeNoise based on VideoCrafter
Fine-Grained Open Domain Image Animation with Motion Guidance