[ComfyUI]腾讯混元视频:开源LORA生态来啦!视频人物一致性&运镜可控性里程碑,支持NSFW

科技   2024-12-14 18:02   浙江  

腾讯混元视频:开源LORA生态来啦!

🌹大家好!欢迎来到破狼公众号。感谢大家的支持与鼓励。在AIGC探索道路上,我将与你一路同行。喜欢就星标关注破狼公众号或文末扫码加入交流群 !

HunyuanVideo LORA简介

在之前文章已经多次介绍过当前最强的开源AI视频模型:腾讯混元视频模型。只从HunyuanVideo开源之后,就受到社区的广泛关注。如今,HunyuanVideo也已支持LORA的使用了,这也是混元视频模型逐步成熟的标志之一。这也意味着HunyuanVideo可以开始对模型微调,以适应特定的任务或风格的视频。另外,有了LORA训练,视频人物、衣服等一致性等问题就可以迎刃而解并且视频的生成则更加可控

HunyuanVideo LORA ComfyUI体验

在之前文章已经多次介绍过由 @kijai大佬开发的ComfyUI-HunyuanVideoWrapper插件,首先需要安装或更新该插件即可。

Flux文生图工作流

Flux文生图感兴趣的同学可参考LIBLIB在线运行工作流:FLUX[续篇]:12B参数23G最大开源文生图模型,Dev版直出惊艳美图欣赏
本文涉及ComfyUI工作流和模型均可在LIBLIBAI上下载或在线运行体验:

• F.1-绮梦流光-水湄凝香

https://www.liblib.art/modelinfo/134c6dd95aef48e98a22b24e003e026b

• 工作流-Flux文|图生图+LORA+提示反推一键切换工作流

https://www.liblib.art/modelinfo/782aacd70f604da39e83368c696a02a8


HunyuanVideo LORA工作流

HunyuanVideo LORA工作流已上传LIBLIB平台

https://www.liblib.art/modelinfo/433fbf0bd2a8484d8e32d9e32258f378?versionUuid=57810c42a2904b9a858a2716e2278d36

注意

  • • 加载LORA需要使用插件新增的HunyuanVideoLoraSelect节点。另外,有了LORA训练,视频人物、衣服等一致性问题就可以迎刃而解,并且更加可控。
  • • 以下案例使用的makima-hunyuan-character LORA模型体验,该模型还支持NSFW,读者需自行测试。该LORA模型只是作者的LORA训练代表模型,相信很快混元生态的LORA就会逐步成熟

01. 杂货铺

Kxsr, a lively Kxsr talking to the cashier at the grocery store about the product, the cinematic, animated aesthetic, the close-up of Kxsr, the camera gathered on the face, directly at the audience

02.沙滩散步

kxsr, , cinematic, anime aesthetic,full body shoot,  kxsr closeup, kxsr walks on the beach by the sea

03.演讲

kxsr, , cinematic, anime aesthetic,The camera is fixed in a carefully arranged study room, where kxsr is sitting at his desk facing the audience, wearing traditional Chinese medicine clothes and carrying on his back a bookshelf lined up with ancient books and medicine cabinets. His eyes reveal deep wisdom. Facing the camera, he tells the story of traditional Chinese medicine in a gentle and firm voice. The picture is presented in high quality, with calm colors and soft light and shadow, creating a solemn and warm atmosphere.

04.雪天

kxsr, cinematic, anime aesthetic,A young Chinese woman, wearing a white down jacket and a white scarf, looks directly at the audience as she walks down the street in Harbin, watching the snow fall around her

更多推荐文章:
• [ComfyUI]ZenID:面部融合神器!揭秘基因遗传,提前预测你和她的下一代基因
• ComfyUI原生精确多区域控制!官方最新LoRA和模型权重的遮罩和调度方法
• [ComfyUI]腾讯混元视频:v2v视频驱动,最强开源视频模型,影视级画质与导演级运镜
• [ComfyUI]Flux:国潮经典!敦煌古韵与现代极简国潮插画,敦煌风十二生肖和邮票集锦
• [ComfyUI]Flux:MJ艺术风!基于黑森林F1的Midjourney风,光效&写实&建模&演示&特写镜头
 [ComfyUI]AWPortraitCN:更真实质感细腻!专门针对国人外貌和审美优化F1模型
• 腾讯混元视频:视频写真换脸,请合理使用!工作流一键视频写真,最强导演级&虚拟与现实完美融合

    感兴趣加入[AGI技术交流群]+V

    如果觉得文章不错,就请在看转发三连

破狼
关注AIGC、LLM、绘图作品、软件工程、技术学习。交流+V:shunshizhiwu。
 最新文章