WAN 14B T2V - Epoch 6 - trained 3/18/2025





In collaboration with @machinedelusions [https://civitai.com/user/machinedelusions]
KXSR Labs presents:
This LoRA enables the creation of cinematic sequences featuring subjects ascending staircases in imaginative environments. The typical view will be ??????????? the subject as they ascend a spiral staircase featured on the right side of the vertical aspect ratio generation. Can still create fun results at other aspect ratios/resolutions.
Use the trigger word "kxsr" to activate the model's specialized training.
kxsr, [person/thing] ascending a [adjective] staircase [describe the world around them]
kxsr, high quality nature video featuring a red panda ascending a bamboo staircase while a bird lands on it's head, on the background there is a waterfall
CFG: 5.5
Shift value: 4.5
LoRA strength: 1.0
~73 frames
720x1280 vertical aspect ratio
Base model: WAN 2.1 14B Text2Video
Training dataset: 80 clips
Resolution: 720x1280 (vertical format)
Frame count: 73 frames per clip
For optimal results, maintain these specifications during inference
This LoRA works best when you provide detailed descriptions of both the subject and the surrounding environment while following the prescribed format.
Screenshot shows my typical inference testing setup for lora evals:
WAN 14B T2V - Epoch 6 - trained 3/18/2025
1. 轉载模型僅供學習與交流分享,其版權及最終解释權归原作者。
2. 模型原作者如需認領模型,請通過官方渠道联系海藝AI工作人員進行認證。我們致力於保護每一位創作者的權益。 點擊去認領
