Wan2.2-T2V-A14B-4steps-lora-rank64-Seko-V1_low_noise_model
返回

Wan2.2-T2V-A14B-4steps-lora-rank64-Seko-V1_low_noise_model
0 0 5

其他

Wan2.2-T2V-A14B-4steps-lora-rank64-Seko-V1_low_noise_model

Wan2.2-Lightning

We are excited to release the distilled version of Wan2.2 video generation model family, which offers the following advantages:

  • Fast: Video generation now requires only 4 steps without the need of CFG trick, leading to x20 speed-up

  • High-quality: The distilled model delivers visuals on par with the base model in most scenarios, sometimes even better.

  • Complex Motion Generation: Despite the reduction to just 4 steps, the model retains excellent motion dynamics in the generated scenes.


Training details

High_noise_model and low_noise_model are distilled simultaneously. On 81x720x1280, 81x1280x720, 81x480x832, 81x832x480 size options.

Tips on usage

In the distillation process, euler scheduler is used, with time_shift = 5. Specifically, the timesetps should be [1000.0000, 937.5001, 833.3333, 625.0000] In inference, please set the scheduler accordingly. Besides, please set cfg = 1.0 so that NFE = 4 but not 8.

此模型源自站外搬运（搬运地址: https://huggingface.co/lightx2v/Wan2.2-Lightning ），若原作者对于本次搬运的结果存在异议，可点
申诉
我们会在 24 小时内，按照原作者的要求，对本模型展开编辑、删除或是转移给原作者等相关处理。由衷欢迎原作者入驻本站，共建 AI绘图的学习交流社区。

suoaao

suoaao

其他

模型信息

原创作者：
lightx2v
模型类型：
LoRA
基础模型：
WAN2.2
文件名称：
models/loras/Wan2.2-T2V-A14B-4steps-lora-rank64-Seko-V1_low_noise_model.safetensors

Wan2.2-Lightning

We are excited to release the distilled version of Wan2.2 video generation model family, which offers the following advantages:

  • Fast: Video generation now requires only 4 steps without the need of CFG trick, leading to x20 speed-up

  • High-quality: The distilled model delivers visuals on par with the base model in most scenarios, sometimes even better.

  • Complex Motion Generation: Despite the reduction to just 4 steps, the model retains excellent motion dynamics in the generated scenes.


Training details

High_noise_model and low_noise_model are distilled simultaneously. On 81x720x1280, 81x1280x720, 81x480x832, 81x832x480 size options.

Tips on usage

In the distillation process, euler scheduler is used, with time_shift = 5. Specifically, the timesetps should be [1000.0000, 937.5001, 833.3333, 625.0000] In inference, please set the scheduler accordingly. Besides, please set cfg = 1.0 so that NFE = 4 but not 8.

此模型源自站外搬运（搬运地址: https://huggingface.co/lightx2v/Wan2.2-Lightning ），若原作者对于本次搬运的结果存在异议，可点
申诉
我们会在 24 小时内，按照原作者的要求，对本模型展开编辑、删除或是转移给原作者等相关处理。由衷欢迎原作者入驻本站，共建 AI绘图的学习交流社区。