用万相Wan2.1-Fun-1.3B-InP模型打造的【首尾帧生视频工作流】！
1、更省显存：直接用ComfyUI原生节点，8G显存也可以出720p视频。
2、速度更快：生成速度比Wan2.1_14b模型提升6倍。
3、附件中PNG图片隐藏了工作流信息。只要将它拖入Comfyui界面中即可。
V2版加入Wan2.1-Fun-Reward-LoRAs，HPS版人类偏好(单帧画面美观度)，MPS版动态偏好(帧间连贯性)
The [Start-End Frame Img2Vid Workflow] powered by the Wan2.1_fun_1.3b_InP model!
1、VRAM-Friendly：Use ComfyUI native nodes to generate 720p videos with just 8GB GPU memory.
2、6x Speed Boost：Render videos faster than Wan2.1_14b model.
Version 2 introduces Wan2.1-Fun-Reward-LoRAs, including the HPS (Human Preference Score) and MPS (Motion Preference Score) editions.
3、The workflow information is hidden in the PNG image attached. You just need to drag it into the ComfyUI interface.
Wan2.1-Fun-Reward-LoRAs:https://huggingface.co/alibaba-pai/Wan2.1-Fun-Reward-LoRAs
Wan2.1-Fun-1.3B-InP: https://huggingface.co/alibaba-pai
text_encoders+clip_vision+vae:https://blog.comfy.org/p/wan21-video-model-native-support
Description
FAQ
Comments (4)
good
mat1 and mat2 shapes cannot be multiplied (769x1279 and 1536x1536) with teacache.I tried any clips, different errors got. no workinng
doesn't work
SamplerCustom Error
mat1 and mat2 shapes cannot be multiplied (77x768 and 4096x1536)