🚀 PyTorch Implementation of "Progressive Distillation for Fast Sampling of Diffusion Models(v-diffusion)"

CLIP+MLP Aesthetic Score Predictor

This is a replicate of DeepSeek-R1-Zero and DeepSeek-R1 training on small models with limited data

Wan: Open and Advanced Large-Scale Video Generative Models

PyTorch implementation of InstructDiffusion, a unifying and generic framework for aligning computer vision tasks with human instructions.

The simplest, fastest repository for training/finetuning medium-sized GPTs.

Official Repo for Open-Reasoner-Zero

[CVPR 2024] Code for the paper "Using Human Feedback to Fine-tune Diffusion Models without Any Reward Model"

Improving Video Generation with Human Feedback

Implementation of the sparse attention pattern proposed by the Deepseek team in their "Native Sparse Attention" paper

A collection of awesome video generation studies.

A curated list of recent diffusion models for video generation, editing, and various other applications.

The official repo of Qwen (通义千问) chat & pretrained large language model proposed by Alibaba Cloud.

Let's finetune video generation models!

My implementation of "Patch n’ Pack: NaViT, a Vision Transformer for any Aspect Ratio and Resolution"

Tarsier -- a family of large-scale video-language models, which is designed to generate high-quality video descriptions , together with good capability of general video understanding.

Official repository for LightSeq: Sequence Level Parallelism for Distributed Training of Long Context Transformers

Video Generation Foundation Models: https://saiyan-world.github.io/goku/

每个人都能看懂的大模型知识分享，LLMs春/秋招大模型面试前必看，让你和面试官侃侃而谈

[ICLR 2025] Rectified Diffusion: Straightness Is Not Your Need

Janus-Series: Unified Multimodal Understanding and Generation Models

十大最佳接码平台

Investigating CoT Reasoning in Autoregressive Image Generation

ICLR2024 Spotlight: curation/training code, metadata, distribution and pre-trained models for MetaCLIP; CVPR 2024: MoDE: CLIP Data Experts via Clustering

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