Text-to-3D & Image-to-3D & Mesh Exportation with NeRF + Diffusion.

Zero-1-to-3: Zero-shot One Image to 3D Object (ICCV 2023)

Cambrian-1 is a family of multimodal LLMs with a vision-centric design.

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

Vision utilities for web interaction agents 👀

✨✨Woodpecker: Hallucination Correction for Multimodal Large Language Models. The first work to correct hallucinations in MLLMs.

DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

Autoregressive Model Beats Diffusion: 🦙 Llama for Scalable Image Generation

CosmicMan: A Text-to-Image Foundation Model for Humans (CVPR 2024)

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

Animate Anyone: Consistent and Controllable Image-to-Video Synthesis for Character Animation

[CVPR2024 Highlight] VBench - We Evaluate Video Generation

InternLM-XComposer-2.5: A Versatile Large Vision Language Model Supporting Long-Contextual Input and Output

Emote Portrait Alive: Generating Expressive Portrait Videos with Audio2Video Diffusion Model under Weak Conditions

Code for the paper "Query-Key Normalization for Transformers"

Code for the paper "Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer"

中文自然语言处理数据集，平时做做实验的材料。欢迎补充提交合并。

A curated list of foundation models for vision and language tasks

A cross-platform GUI automation Python module for human beings. Used to programmatically control the mouse & keyboard.

official implementation of VideoDirectorGPT: Consistent Multi-scene Video Generation via LLM-Guided Planning

transformer xl在中文文本生成上的尝试（可写小说、古诗）（transformer xl for text generation of chinese）

[EMNLP 2023 Demo] Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding

Stable Diffusion with Core ML on Apple Silicon

[CVPR 2024] 4D Gaussian Splatting for Real-Time Dynamic Scene Rendering

Swap face between two photos.

This is a list of awesome paper about optical flow and related work.

[CVPR'23] MM-Diffusion: Learning Multi-Modal Diffusion Models for Joint Audio and Video Generation

通过水印减除方法去掉视频中的水印，快速但不完美

Fine-Grained Open Domain Image Animation with Motion Guidance