Awesome GitHub RepositoriesDiffusion Model Distillation

This project is a framework for training and sampling generative models designed to produce high-quality images in few steps. It provides implementations for image generation models that transform random noise into structured visual data through an optimized sampling process. The system specializes in accelerating image generation through consistency distillation and consistency training. It includes tools to transform pre-trained diffusion models into faster versions by distilling knowledge from a teacher model into a student model, as well as methods to train consistency models from scratch

This project is a framework for training consistency models and performing diffusion model distillation. It functions as a few-step text-to-image generator and an image-to-image transformation tool designed to produce high-resolution visuals from text prompts or existing images. The system focuses on converting pre-trained diffusion models into consistency models to reduce the number of required inference steps. It enables the training of lightweight model adaptors to inject specific visual styles into large models without requiring full network fine-tuning. The project covers broad capabili

LongCat-Video este o colecție de modele specializate pentru sinteza video, având o arhitectură bazată pe modele de limbaj mari (LLM) pentru crearea de videoclipuri de înaltă rezoluție din text, imagini sau secvențe existente. Include sisteme dedicate pentru generarea text-to-video, animația image-to-video și crearea de avatare vorbitoare. Proiectul oferă capabilități specifice pentru extinderea duratei clipurilor existente printr-un model de continuare video care prezice cadrele ulterioare. De asemenea, permite sincronizarea mișcărilor buzelor personajelor cu prompturi audio și text pentru a produce videoclipuri vorbite. Sistemul încorporează diverse tehnici de optimizare pentru a gestiona eficiența generării, inclusiv eșantionarea bazată pe distilare și cuantizarea pentru a reduce utilizarea memoriei și latența de inferență. Componentele structurale suplimentare acoperă compresia în spațiul latent și modelarea spațio-temporală pentru a menține consistența în timp și spațiu.

HunyuanDiT is a bilingual text-to-image generative model and diffusion transformer image generator. It uses a latent diffusion system to synthesize high-resolution images from text prompts, with a specific focus on understanding and generating content from both Chinese and English language descriptions. The project features a multi-resolution transformer architecture and a bilingual embedding space to map different scripts into a shared semantic area. It supports iterative multi-turn image refinement, which translates conversational dialogue into updated prompts to progressively modify visual

FastVideo is a comprehensive system for accelerated video generation, serving as a video generation inference engine, a video diffusion training framework, and a modular pipeline orchestrator. It provides a distributed transformer optimizer and a distillation toolkit designed to reduce denoising steps and model complexity to increase frame rates. The project distinguishes itself through specialized acceleration techniques, including joint distillation and sparse attention training. It implements low-step video generation and weight quantization to FP8 or FP4 precision to increase throughput a