目前该技术已支持 Flux、混元 video、Ltx-Video 等多个主流框架。 插件地址:https://github.com/facok/ComfyUI-TeaCacheHunyuanVideo 插件一共支持 Original(1*)Fast(1.6*)Faster(2.1*)三挡加速,这里推荐大家用1.6 倍以获得一个质量与速度的均衡 工作流也非常简单,把「自定义采样器(高级)」替换成「TeaCache ...
这是一个混元Video的TeaCache加速节点,支持原生节点工作流,无痛升级,选择你想加速的倍数,目前只开放3档。 加速会对质量有一定的影响,具体可以自己尝试。 视频演示 https://www.bilibili.com/video/BV1tVcJefEJE 安装方法 将文件下载后解压,重命名为teacachehunyuanvideo,放到ComfyUI安装目录的custom_nodes文件夹内...
感谢群里的fok大佬开发的新玩具人,让我们的混元视频模型更高效!项目地址:https://github.com/facok/ComfyUI-TeaCacheHunyuanVideoQQ讨论群:465158469, 视频播放量 2436、弹幕量 0、点赞数 66、投硬币枚数 31、收藏人数 69、转发人数 6, 视频作者 AIwood爱屋研究室, 作者
Saved searches Use saved searches to filter your results more quickly Cancel Create saved search Sign in Sign up Reseting focus {{ message }} welltop-cn / ComfyUI-TeaCache Public Notifications You must be signed in to change notification settings Fork 13 Star 353 ...
https://github.com/facok/ComfyUI-TeaCacheHunyuanVideo 主页 取消 保存更改 1 https://gitee.com/comfyui_custom_nodes/ComfyUI-TeaCacheHunyuanVideo.git git@gitee.com:comfyui_custom_nodes/ComfyUI-TeaCacheHunyuanVideo.git comfyui_custom_nodes ComfyUI-TeaCacheHunyuanVideo ComfyUI-TeaCacheHunyuanVid...
TeaCache4HunyuanVideo TeaCache4LTX-Video TeaCache4Lumina-T2X README.md teacache_lumina_next.py TeaCache4Mochi TeaCache4TangoFlux assets eval videosys .gitignore .isort.cfg .pre-commit-config.yaml CONTRIBUTING.md LICENSE README.md requirements.txt setup.pyBreadcrumbs TeaCache /TeaCache4Lumina-...
comfyui_custom_nodes/ComfyUI-TeaCacheHunyuanVideo 代码Issues0Pull Requests0Wiki统计流水线 服务 Gitee Pages 服务 一个支持Jekyll、Hugo、Hexo静态网站的服务使用帮助 因服务维护调整,Gitee Pages 暂停提供服务,给您带来不便深感抱歉,感谢对 Gitee Pages 服务的支持。
This is a TeaCache acceleration node for HunYuan Video, supporting the native node workflow for seamless upgrades. Simply choose the acceleration multiplier you want—currently, three levels are available. Acceleration may have some impact on quality, so feel free to experiment and see the results...
FLUXPuLID-FLUXHunyuanVideoLTX-Video rel_l1_thresh 0.4 0.4 0.15 0.06 speedup ~2x ~1.7x ~2x ~1.7x The demo workflows (teacache_flux, teacache_pulid_flux, teacache_hunyuanvideo, teacache_ltx_video) are placed in examples folder. Compile Model To use Compile Model node, simply add Compile...
理论2.最新缓存技术TeaCache原理的理论知识,图片和视频模型加速方法,支持FLUX,Hunyuanvideo,LTX-Video 295播放 最快的开源AI视频生成模型,LTX Video带你极速制作电影级别的AI视频短片,8G显卡可用 4551播放 【AI视频】Cosmos图生视频、视频生视频--英伟达世界模型ComfyUI工作流 3301播放 原声油脸盯～太美腻了 1.7万播...