【老鸟进阶】deepfacelab合成参数详解

qiuxianbang

这个真的很有用，谢了楼主

shork74

这个模型怎么打开报错呢？辛苦给看一下吧




----------------------运行信息----------------------

                  设备编号: 0
                  设备名称: NVIDIA GeForce RTX 3080
                  显存大小: 7.25GB

================================================
猫之汉化
出售模型、商业换脸程序开发、商业换脸视频定制
QQ\微信:564646676
淘宝店地址：http://t.hk.uy/4ks
=============================================

启动中. 按回车键停止训练并保存进度。

保存时间|迭代次数|单次时间|SRC损失|DST损失
Error: 2 root error(s) found.
  (0) Resource exhausted: OOM when allocating tensor with shape[8,128,112,112] and type float on /job:localhost/replica:0/task:0/device:GPU:0 by allocator GPU_0_bfc
         [[node LeakyRelu_88 (defined at M:\YUN\2\DFL_maozhihanhua_RTX3000\_internal\DeepFaceLab\core\leras\models\PatchDiscriminator.py:178) ]]
Hint: If you want to see a list of allocated tensors when OOM happens, add report_tensor_allocations_upon_oom to RunOptions for current allocation info. This isn't available when running in Eager mode.

         [[concat_17/concat/_1335]]
Hint: If you want to see a list of allocated tensors when OOM happens, add report_tensor_allocations_upon_oom to RunOptions for current allocation info. This isn't available when running in Eager mode.

  (1) Resource exhausted: OOM when allocating tensor with shape[8,128,112,112] and type float on /job:localhost/replica:0/task:0/device:GPU:0 by allocator GPU_0_bfc
         [[node LeakyRelu_88 (defined at M:\YUN\2\DFL_maozhihanhua_RTX3000\_internal\DeepFaceLab\core\leras\models\PatchDiscriminator.py:178) ]]
Hint: If you want to see a list of allocated tensors when OOM happens, add report_tensor_allocations_upon_oom to RunOptions for current allocation info. This isn't available when running in Eager mode.

0 successful operations.
0 derived errors ignored.

Errors may have originated from an input operation.
Input Source operations connected to node LeakyRelu_88:
Add_157 (defined at M:\YUN\2\DFL_maozhihanhua_RTX3000\_internal\DeepFaceLab\core\leras\layers\Conv2D.py:107)

Input Source operations connected to node LeakyRelu_88:
Add_157 (defined at M:\YUN\2\DFL_maozhihanhua_RTX3000\_internal\DeepFaceLab\core\leras\layers\Conv2D.py:107)

mrji

真不错，很有用

xz999991111

老大問題是合成的時候系統都會說找不到合成的圖

gy1364gy

感謝说明

lion

看了几篇教程，都说要增大侵蚀，我感觉侵蚀要减少脸型才比较匹配，大概-60左右，稍稍盖住DST脸，不知道这样调对不对

deathlmx

学习 辛苦了大佬

pp6659659

后排观摩学习

pp6659659

需要大量的操作和思考，起码有了个方向

ydybezdzd

学习了学习了