腾讯混元视频:ComfyUI官方原生支持!GGUF量化更低显存!
🌹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 GGUF简介
在之前文章已经介绍过腾讯最新开源的130亿参数的文生视频大模型:Hunyuan Video(混元视频)。是当前AI视频开源社区最具代表性先进视频模型之一,在很多方面能够足够媲美OpenAI最新开放的Sora视频模型。目前社区大佬也在发力改善腾讯混元视频生态,已有LORA微调生态支持、图片风格参考IP2V、FP8和GGUF量化模型支持等。特别在近日,混元视频也迎来了ComfyUI软件官方的原生支持,现在能够在ComfyUI中轻松实现混元视频生成的功能。
• ComfyUI官方文档:https://comfyanonymous.github.io/ComfyUI_examples/hunyuan_video/
• GGUF量化版本:https://huggingface.co/city96/HunyuanVideo-gguf/tree/main
• [ComfyUI]腾讯混元视频:虚实完美融合创意无极限!130亿大杯&影视级画质&导演级运镜&原生切镜&遵循物理运动&连续动作
HunyuanVideo GGUF ComfyUI体验
当前ComfyUI官方已原生支持HunyuanVideo的体验了,仅需更新ComfyUI软件本体到最新版本即可。下面所需模型均可文末网盘下载
• hunyuan_video_t2v_720p_bf16.safetensors :下载 hunyuan_video_t2v_720p_bf16.safetensors
文件,并将其放置在ComfyUI的models/unet
文件夹中。下载地址:https://huggingface.co/Comfy-Org/HunyuanVideo_repackaged/tree/main/split_files/diffusion_models• clip_l和llava_llama3_fp8_scaled:下载 clip_l.safetensors
和llava_llama3_fp8_scaled.safetensors
文件,并将其放置在ComfyUI的models/clip
目录中。下载地址:https://huggingface.co/Comfy-Org/HunyuanVideo_repackaged/tree/main/split_files/text_encoders• hunyuan_video_vae_bf16.safetensors:还需下载 hunyuan_video_vae_bf16.safetensors
文件,并将其放置在ComfyUI的models/vae
文件夹中。下载地址:https://huggingface.co/Comfy-Org/HunyuanVideo_repackaged/tree/main/split_files/vae• 如果使用GGUF量化版本可以配合ComfyUI-GGUF插件与ComfyUI原生工作流一起使用,能够显著降低显存要求。GGUF模型下载:https://huggingface.co/city96/HunyuanVideo-gguf/tree/main • 和之前ComfyUI-HunyuanVideoWrapper插件本次新增的模型为llava_llama3_fp8_scaled模型。
Flux文生图工作流
• 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 GGUF视频工作流
HunyuanVideo视频工作流已上传LIBLIB平台:
https://www.liblib.art/modelinfo/433fbf0bd2a8484d8e32d9e32258f378?versionUuid=aba77a6852f24c209fc1c5a4bf520505
注意:
• ComfyUI官方工作流仅需20步生成视频,无需原始的50步。同时GGUF视频质量保持很好。
• 可以仅需替换Unet加载为GGUF Unet加载器即可。对于显存使用GGUF量化模型12G显存可运行。24G显存2秒 720*480分辨率视频仅需约2分钟,5秒视频大约5分钟左右。
• 预测12G显存理论可体验混元大模型啦,更低8G显存需要待测试反馈。
01. 演讲
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.
02.动漫女孩
anime style anime girl with massive fennec ears and one big fluffy tail, she has blonde hair long hair blue eyes wearing a pink sweater and a long blue skirt walking in a beautiful outdoor scenery with snow mountains in the background
03.冬天
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
如果觉得文章不错,就请赞、在看与转发三连