古力娜娜直播模型带lab底丹
在其他论坛下载古力的颜色发绿,所以又重新训练了,liae-udt288分辨率使用 deepfacelab-MVE 训练的,模型复用请使用 deepfacelab-MVE
最终版本模型下边牙齿效果很好,清晰可见,src素材包含很多下牙素材,希望加精华
== resolution: 288 ==
== face_type: wf ==
== models_opt_on_gpu: True ==
== archi: liae-udt ==
== ae_dims: 480 ==
== e_dims: 72 ==
== d_dims: 64 ==
== d_mask_dims: 32 ==
== masked_training: True ==
== eyes_prio: False ==
== uniform_yaw: False ==
== lr_dropout: y ==
== random_warp: False ==
== gan_power: 0.1 ==
== true_face_power: 0.0 ==
== face_style_power: 0.0 ==
== bg_style_power: 0.0 ==
== ct_mode: rct ==
== clipgrad: False ==
== pretrain: False ==
== autobackup_hour: 0 ==
== write_preview_history: False ==
== target_iter: 0 ==
== random_flip: True ==
== batch_size: 16 ==
== use_fp16: False ==
== retraining_samples: False ==
== mouth_prio: False ==
== blur_out_mask: True ==
== adabelief: True ==
== loss_function: SSIM ==
== random_hsv_power: 0.01 ==
== random_downsample: True ==
== random_noise: False ==
== random_blur: False ==
== random_jpeg: False ==
== random_shadow: none ==
== background_power: 0.0 ==
== random_color: False ==
== cpu_cap: 8 ==
== preview_samples: 4 ==
== force_full_preview: True ==
== lr: 5e-05 ==
== session_name: ==
== maximum_n_backups: 24 ==
== random_src_flip: True ==
== random_dst_flip: True ==
== gan_patch_size: 36 ==
== gan_dims: 16 ==
== gan_smoothing: 0.0 ==
== gan_noise: 0.0 ==
== ==
古力娜娜直播模型老版本(2灵石相当于免费送):
***本内容需购买可见***
古力娜娜直播模型带lab底丹带素材最终版本:
***本内容需购买可见***
模型参数也贴下吧 ===================== 模型参数 ======================
模型名称: liae288_SAEHD
迭代数量: 523944
------------------- 模型选项 --------------------
resolution: 288
face_type: wf
models_opt_on_gpu: True
archi: liae-udt
ae_dims: 480
e_dims: 72
d_dims: 64
d_mask_dims: 32
masked_training: True
uniform_yaw: False
lr_dropout: y
random_warp: False
gan_power: 0.1
true_face_power: 0.0
face_style_power: 0.0
bg_style_power: 0.0
ct_mode: rct
clipgrad: False
pretrain: False
autobackup_hour: 0
write_preview_history: False
target_iter: 0
random_flip: True
batch_size: 8
use_fp16: False
retraining_samples: False
mouth_prio: False
blur_out_mask: True
adabelief: True
loss_function: SSIM
random_hsv_power: 0.01
random_downsample: False
random_noise: False
random_blur: False
random_jpeg: False
random_shadow: none
background_power: 0.0
random_color: False
cpu_cap: 8
preview_samples: 4
force_full_preview: True
lr: 5e-05
session_name:
maximum_n_backups: 24
random_src_flip: True
random_dst_flip: True
gan_patch_size: 36
gan_dims: 16
gan_smoothing: 0.0
gan_noise: 0.0
eyes_mouth_prio: False
啥也不是,不能直接复用 效果咋样 效果咋样 本帖最后由 随风漂流 于 2024-9-10 19:42 编辑
晓雷哥哥 发表于 2024-9-5 19:36
===================== 模型参数 ======================
模型名称: liae288_SAEHD
使用 deepfacelab-MVE 训练的
deepfacelab-MVE 软件下载: https://www.aibl.vip/forum.php?mod=viewthread&tid=597
页:
[1]