Best settings for photos to photos

Want to understand the training process better? Got tips for which model to use and when? This is the place for you


Forum rules

Read the FAQs and search the forum before posting a new topic.

This forum is for discussing tips and understanding the process involved with Training a Faceswap model.

If you have found a bug are having issues with the Training process not working, then you should post in the Training Support forum.

Please mark any answers that fixed your problems so others can find the solutions.

Locked
User avatar
Balmmaker
Posts: 15
Joined: Wed Nov 17, 2021 1:36 pm
Been thanked: 2 times

Best settings for photos to photos

Post by Balmmaker »

I am seeking better settings to try for swapping photo model A with photo model B. I have over 10k high quality, good lighting images for both.

Currently I am unable to get any sharp or at least not quite blurry and passable image swaps using 128x128 inputs, dfaker model, batch size of 40, 4000 faces for each set - went through each and every image to ensure the wire frame face matches the photo and it positioned correctly.

Reasably good hardware with an Rtx2080 and 32GB RAM.

Even with 500k iterations, the preview is noticably blurry. The improvement from 100k to 500k iterations was small but present. Previous attempts ran more than 1 million iterations while worse blurry previews than 100k with realface (used the original model and 16 batch size, 64x64 input)

What I am wondering is, what is the best training settings to try for large photos sets with good lighting? About how many iterations ballpark should I wait till I see reasonable sharpness or abandon to different settings? Is there anything else I can do to sharpen things up? Faceswap can do photos well and not just videos, right?

User avatar
bryanlyon
Site Admin
Posts: 793
Joined: Fri Jul 12, 2019 12:49 am
Answers: 44
Location: San Francisco
Has thanked: 4 times
Been thanked: 218 times
Contact:

Re: Best settings for photos to photos

Post by bryanlyon »

Yes Faceswap can handle images instead of videos.

Quality issues are almost always with data. Unfortunately it's impossible to guess what might be wrong without examining your data or results. If you can, please post a training preview so we can evaluate your data and results.

User avatar
Balmmaker
Posts: 15
Joined: Wed Nov 17, 2021 1:36 pm
Been thanked: 2 times

Re: Best settings for photos to photos

Post by Balmmaker »

Here is a typical level of blurriness -- this is after 650k iterations at the settings described above.

Image

And here is a typical level of quality of source material before extracting the faces

Image

I am not particularly attached to the models -- just grabbed easy to find, abundant photos for source material for trying out face swapping. But the process doesn't seem to be working so if the source material is a problem...what parameters should i look seek as better material? Personally, i thought, good lighting, clear photos, decent resolution, someone made packs of zip files, done. Lets start extracting and training.

I also haven't seen any screenshots of a completed training model preview to see what the level of detail would look like.

User avatar
torzdf
Posts: 2649
Joined: Fri Jul 12, 2019 12:53 am
Answers: 159
Has thanked: 128 times
Been thanked: 622 times

Re: Best settings for photos to photos

Post by torzdf »

Those previews should almost definitely look better than that at 650k on dfaker (assuming a reasonable batch size). As Bryan says, blurriness is almost almost down to data quality. Variety is key.

My word is final

User avatar
Balmmaker
Posts: 15
Joined: Wed Nov 17, 2021 1:36 pm
Been thanked: 2 times

Re: Best settings for photos to photos

Post by Balmmaker »

So a batch size of 40 is too low for dfaker? And for variety of images, is 8000 individual photos in both the swap and original sets, so 16000 photos total, you don't think there is enough variation in that?

I can try and add to these photo sets or create a separate group of data to train on. What is the process for changing the original and swap data, using the same people and continuing the training with what the model has learned already?

Locked