[MrDeepfakes pretrained models tutorial written by TMBDF from 08/04/2023]
Default/Pretrained Only Models (NEW MODELS - ADABELIEF ENABLED):
Full Face:
@twilight
DF-UD - res: 448, AB, dims: 390/96/96/32, 237200 iterations, Full Face (NSFW - Female Only (Groggy4 Training Dataset) - Pretrain - XSeg Masked)
https://mega.nz/folder/9BQ1zIAK#fmLvLUILlL5jW5NuG-xhUA
Whole Face:
@Groggy4
DF-UD - res: 384, AB, dims: 352/88/88/16, 142.000 iterations, Whole Face (NSFW - Female Only - Pretrain - XSeg Masked)
https://drive.google.com/drive/folders/12ea-NUs1QC9bYPUNuq1VwhNtuFzhTgo7
Trained Models (NEW MODELS - ADABELIEF ENABLED):
Full Face:
@Groggy4
DF-UD - res: 320, AB, dims: 360/90/90/22, 1.496.000 iterations, Full Face (NSFW DST - Female Only - Specific Celebrity Trained (Kate Upton) + 6-8 different celebs - XSeg Masked)
https://drive.google.com/drive/folders/1X3jJHnFStwsaznBIpqK5DmvCbVVruKlM
DF-UD - res: 320, AB, dims: 416/104/104/16, 1.347.000 iterations, Full Face (NSFW DST - Female Only - Specific Celebrity Trained (Kate Upton) + 6-8 different celebs - XSeg Masked)
https://drive.google.com/drive/folders/1LPiypZq05y7PR0GVImGcGMEYvEAaYReH
DF-UD - res: 384, AB, dims: 320/80/80/22, 399.000 iterations, Full Face (NSFW DST - Female Only - Specific Celebrity Trained (Margot Robbie) + 6-8 different celebs - XSeg Masked)
https://drive.google.com/drive/folders/1QKThzofqS25uVuoCjfxCsCNx8RQP1xio
(NEW MODEL) DF-UD - res: 384, AB, dims: 352/88/88/16, 1.255.000 iterations, Full Face (NSFW DST - Female Only - Pretrain + Specific Celeb Trained (Maddie Ziegler) + 3-4 different celebs - XSeg Masked)
https://drive.google.com/drive/folders/1w7_Qd5fTto43RaAINYWJV0IQVAlWxFlm?usp=sharing
Custom pretrain datasets:
Whole face:
@Groggy4
WF Custom Mix of: Female from FFHQ + Female Celebs + Adult performers (NSFW)
https://drive.google.com/drive/folders/1CEM379BEgkL6xVxsy0slF4sJdK6XKNz4
Default/Pretrained Only Models (OLD MODELS - NON ADABELIEF):
Full Face:
@Groggy4
DF-UD - res: 256, dims: 448/112/112/22, 251.000 iterations, Full Face (NSFW - Female Only - Pretrain)
https://drive.google.com/drive/folders/14kHRSvqOiMyZZIewtlFjtnyRTlOABQPq
@iperov
LIAE - res: 128, dims: 128/80/48/16, 1.000.000 iterations, Full face (SFW - old pretrain dataset)
https://github.com/iperov/DeepFaceLab/releases/download/pretrained/LIAE.f-128-80-48-16-1.000.000.zip
LIAE-UD - res: 192, dims: 256/64/64/22, 1.000.000 iterations, Full face (SFW - old pretrain dataset)
https://mega.nz/file/N45X3D4a#eCsaQOCJLRKSMekG4anjktf-PteEkJMUlC1fre_2IYM
@und3rd0g
DF-UD - res: 128, dims: 256/64/64/22, 500.000 iterations, Full face (SFW - FFHQ pretrain dataset)
https://mega.nz/file/1l92WajK#Lzw_y_xOZXVupf49qy__693kLAXfiWTxM87avBkOZFA
DF-UD - res: 160, dims: 256/64/64/22, 500.000 iterations, Full face (SFW - FFHQ pretrain dataset)
https://mega.nz/file/pk0GhQgL#wEqGKOdGoTLaj0KJTPejTAsXO7fjxrNDk7nBGAiC1mA
LIAE-UD - res: 192, dims: 256/64/64/22, 500.001 iterations, Full face (SFW - FFHQ pretrain dataset)
https://mega.nz/file/EhkXwZYC#JG-F6lak30qgHPbiFfbX4T_EG7wevEUfi8At5Oa8UkY
@VladShev
LIAE - res: 224, dims: 256/64/64/22, 322.144 iterations, Full face (SFW - old pretrain dataset)
https://mega.nz/#F!w0hlWZ6Z!Ol_KjRcGD8dDojFxl6m1zA
@rocket.svm
DF-UD - res: 224, dims: 256/64/64/16, 1.030.808 iterations, Full face (SFW - old pretrain dataset)
https://mega.nz/folder/HJB00AYb#1AN4ovkEBJJHcYENAGgDJw
@Thorganic
LIAE - res: 256, dims: 256/64/64/22, 1.000.001 iterations, Full face (SFW - old pretrain dataset)
https://mega.nz/folder/RuA2BIYK#ipOe_4zAd2BEah7rZm7Z2w
LIAE-UD - res: 256, dims: 256/64/64/22, 1.000.151 iterations, Full face (SFW - old pretrain dataset)
https://mega.nz/folder/tjJzEIob#8ftlsBBLN32EXNlQFy5vtg
@chervonij
LIAE-U - res: 224, dims: 256/80/80/22, 722.000 iterations, Whole face (SFW - old pretrain dataset)
https://mega.nz/file/pAJm1YpA#-Htt70rOyPvFy5GM5t2I5nFaf4n9qN4scCb0A1JwQUA
LIAE-UD - res: 224, dims: 256/64/64/16, 1.000.000 iterations, Whole face (SFW - old pretrain dataset)
https://mega.nz/file/5FxASABb#SIj-2ZMNTOICSLtk0pqdl64XxkBIdUiawWWLWrWFuUU
@BozoXXL
DF-U - res: 224, dims: 256/64/64/22, 412.000 iterations, Whole face (SFW - FFHQ pretrain dataset)
https://mega.nz/folder/bwwyAa4A#wmUpbPQWBHsIK0f0j7R8SQ
DF-UD - res: 384, dims: 256/64/64/22, 1.200.000 iterations, Whole face (SFW - FFHQ pretrain dataset)
https://mega.nz/folder/Xo5BXIAY#Ob6X5dOInMFbz9t-ZAq2HA
DF-UD - res: 320, dims: 320/96/96/32, 560.000 iterations, Whole face (SFW - FFHQ pretrain dataset)
https://mega.nz/folder/v8gzkSCL#_o9sCCaviIIIIFg_x8LTeA
@DarkAlchy
DF-UD - res: 224, dims: 320/96/96/22, 428.817 iterations, Whole face (SFW - FFHQ pretrain dataset)
https://mega.nz/file/LNM11SaA#tN8NaxFOPAJWOGkOK-lBfEsI1IKD-eVxGrZWlyL0LK4
DF-UD - res: 256, dims: 292/92/92/16, 750.000 iterations, Whole face (SFW - FFHQ pretrain dataset)
https://mega.nz/file/DBsXiLCB#INU9bKS7YuwFyn7p9ytSY4wqZugjCeUtCMAuYBl7CJA
@iperov
DF - res: 288, dims: 384/92/72/22, 1.000.000 iterations, Whole face (SFW - old pretrain dataset)
https://github.com/iperov/DeepFaceL...es.384.92.72.22/DF.wf.288res.384.92.72.22.zip
Last edited:
