hunyuan-video

https://wavespeed.ai/ Context parallel attention that accelerates DiT model inference with dynamic caching

做企业 AI 视频项目逼出来的工具包 · 411 prompt · 15 模型 · 7 Claude Skill · 14 篇方法论

1000+ ComfyUI workflows for AI image & video generation — Flux, SDXL, Hunyuan, CogVideo, upscaling, ControlNet & more

LoRA Pilot is an ultimate docker image for all Stable Diffusion LoRA trainers. Includes kohya_ss, diffusion pipes and TensorBoard for trainings and ComfyUI and InvokeAI for validation. Features shared models, modules, custom integrations and automatization scripts.