Stars
MiniCPM3-4B: An edge-side LLM that surpasses GPT-3.5-Turbo.
[CVPR 2024] Code for the paper "Using Human Feedback to Fine-tune Diffusion Models without Any Reward Model"
Code for "Diffusion Model Alignment Using Direct Preference Optimization"
Implementation for "Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs"
Repo is required for the code of our research paper on micro-budget training of large scale diffusion model.
MiniCPM-V 2.6: A GPT-4V Level MLLM for Single Image, Multi Image and Video on Your Phone
Text-to-video generation: CogVideoX (2024) and CogVideo (ICLR 2023)
⚡ Fastest way to serve open source ML models to millions
Official inference repo for FLUX.1 models
Implementation of UltraPixel: Advancing Ultra-High-Resolution Image Synthesis to New Peaks
InstantID: Zero-shot Identity-Preserving Generation in Seconds 🔥
[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 …
Official implementation of Magic Clothing: Controllable Garment-Driven Image Synthesis
VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMs
VoCo-LLaMA: This repo is the official implementation of "VoCo-LLaMA: Towards Vision Compression with Large Language Models".
Open-Sora: Democratizing Efficient Video Production for All
A generative speech model for daily dialogue.
[ECCV 2024] HiDiffusion: Increases the resolution and speed of your diffusion model by only adding a single line of code!
MiniSora: A community aims to explore the implementation path and future development direction of Sora.
Hunyuan-DiT : A Powerful Multi-Resolution Diffusion Transformer with Fine-Grained Chinese Understanding
An Easy-to-use, Scalable and High-performance RLHF Framework (70B+ PPO Full Tuning & Iterative DPO & LoRA & Mixtral)
PyTorch implementation for Score-Based Generative Modeling through Stochastic Differential Equations (ICLR 2021, Oral)
A PyTorch implementation of the paper "ZigMa: A DiT-Style Mamba-based Diffusion Model" (ECCV 2024)
Mora: More like Sora for Generalist Video Generation