How can acchive this result? Resolution advice

[Vittoria]

I saw this reels https://www.instagram.com/reel/C7gPO4iocgO/?igsh=YmEydTdsejdjdDNs.


Can i acchive this with this settings ?

train deepfake setting

6 core cpu, 16gb ram, GTX 1080ti 11gb
"

always use a pretrained model – you need > 600k pre-training before start you regular model training, so don´t start from scratch

go the the model secection use a 256 res model – try 256 DF-UDT F or WF ( face / whole face ) unsing default dims and start with random warp , batch 6 , remember to check using a downloaded model first time – set iter = 0 an pre training = N or the model will stay in pre training mode

look for something like this

==———————- Model Options ———————-==
== ==
== resolution: 256 ==
== face_type: f ==
== models_opt_on_gpu: True ==
== archi: df-udt ==
== ae_dims: 256 ==
== e_dims: 64 ==
== d_dims: 64 ==
== d_mask_dims: 22 ==
== masked_training: True ==
== eyes_mouth_prio: False ==
== uniform_yaw: False ==
== blur_out_mask: False ==
== adabelief: True ==
== lr_dropout: n ==
== random_warp: True ==
== random_hsv_power: 0.0 ==
== 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_src_flip: False ==
== random_dst_flip: True ==
== batch_size: 6 ==
== gan_power: 0.0 ==
== gan_patch_size: 32 ==
== gan_dims: 16 ==
== ==

 

[TMBDF]

I saw this reels https://www.instagram.com/reel/C7gPO4iocgO/?igsh=YmEydTdsejdjdDNs.


Can i acchive this with this settings ?

train deepfake setting

6 core cpu, 16gb ram, GTX 1080ti 11gb
"

always use a pretrained model – you need > 600k pre-training before start you regular model training, so don´t start from scratch

go the the model secection use a 256 res model – try 256 DF-UDT F or WF ( face / whole face ) unsing default dims and start with random warp , batch 6 , remember to check using a downloaded model first time – set iter = 0 an pre training = N or the model will stay in pre training mode

look for something like this

==———————- Model Options ———————-==
== ==
== resolution: 256 ==
== face_type: f ==
== models_opt_on_gpu: True ==
== archi: df-udt ==
== ae_dims: 256 ==
== e_dims: 64 ==
== d_dims: 64 ==
== d_mask_dims: 22 ==
== masked_training: True ==
== eyes_mouth_prio: False ==
== uniform_yaw: False ==
== blur_out_mask: False ==
== adabelief: True ==
== lr_dropout: n ==
== random_warp: True ==
== random_hsv_power: 0.0 ==
== 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_src_flip: False ==
== random_dst_flip: True ==
== batch_size: 6 ==
== gan_power: 0.0 ==
== gan_patch_size: 32 ==
== gan_dims: 16 ==
== ==

How many of you guys are there doing these? Jesus.

This is not done with DFL mind you, I did try to make these for few of your fellow friends in this business, this is most likely done with rope.

 

[cy2454]

How can you tell this is a deepfake? Is it even a deepfake? I can't tell... and looks like no one in the comments can either (if they aren't all bots)

 

[TMBDF]

How can you tell this is a deepfake? Is it even a deepfake? I can't tell... and looks like no one in the comments can either (if they aren't all bots)

It is a deepfake, anything that changes face is a deepfake. Comments might be bots to boost views and content engagment/increase a chance of algorithm suggesting it to other users.

Girl wears fake silicone boobs to make them appear huge, they make the face younger (jailbait), then point to onlyfans where they post nudes altered with AI (making the fake boobs look like real).

Horny 45 year old suggar daddies and simps won't notice, they are too busy giving these thots all their money, experts like me can tell it's all fake, nudes in most cases aren't even done well, lots of mistakes, it takes long time to make a perfect nude with no errors, little rendering "bugs" from stable diffusion and maintaining consistency between different nudifiying jobs done on each picture, but again, these horny loosers that pay for it won't notice it, until they do, then they expose these fake girls on forums