diffusers

FastVideo

+111

A unified inference and post-training framework for accelerated video generation.

mflux

+22

Apple MLX native implementations of state-of-the-art generative image & video models

auto-round

+10

PTQ-Level Efficiency, QAT-Level Accuracy | 训练后量化的效率，量化感知训练的精度

inference

+10

Swap GPT for any LLM by changing a single line of code. Xinference lets you run open-source, speech, and multimodal models on cloud, on-prem, or your laptop — all through one unified, production-ready inference API.

PrunaAI/pruna

+7

Pruna is a model optimization framework built for developers, enabling you to deliver faster, more efficient models with minimal overhead.

fastsdcpu

+5

Fast stable diffusion on CPU and AI PC

SimpleTuner

+4

A general fine-tuning kit geared toward image/video/audio diffusion models.

sdnext

+3

SD.Next: All-in-one WebUI for AI generative image and video creation, captioning and processing

finetrainers

+2

Scalable and memory-optimized training of diffusion models