Faceswap Forum

cosmico

This question isn't me so much asking about practical advice, as much as it is about the philosophical contemplation post about the world we we will be living in, in the very near future. - ASSUMING I'm a unbelievably wealthy bad actor, maybe a dictator type, maybe dystopian government type with acc...

cosmico

Even though it's not written I've sortve been operating under this assumption. Do you guys have any interest in adding additional loss multipliers like to the cheeks, nose, and eyebrows?

cosmico

-There are a lot of things we can't control for when faceswapping (ignoring who we choose swap), for example: face shape, how much forehead they have, hair style, hair color, heck even their height and weight when the body matters. So to get a better understanding of what the community is thinking a...

cosmico

You don't have to have the perfect answer, I'm looking for any insight from the community here, The eye and mouth multiplier increase the speed at which the eye and mouth are trained, which is pretty useful as the eyes and mouth are usually easy ways to tell that the model hasn't trained enough. ......

cosmico

Interesting, thanks.

cosmico

Question 1 When Training for a long time, I've noticed on the overall summary statistic, it will just stop graphing any data or progress for a certain side. (Usually A). Like its will continue to keep graphing B, but just stop for A https://i.imgur.com/58tK8bK.png But when I click on this session's...

cosmico

I've been having similar issues but I can expand on the original post. Lets say I trained 50,000 iterations at 100eg/s then stop. Then I decide to train another 50,000 at 100eg/s again and then stop again. At the end of the second stop that second training session will be completely gone on the anal...

cosmico

I've always personally viewed it as villian>realface>unbalanced>dlight>dflsae>dflh128>dfaker>original>IAE>lightweight That being said, I never use villian or realface, dlight, because even though I think they are "more realistic" what ever realistic bonus is not worth on average taking on ...

cosmico

Thank you. So far it seems to be working for me now. Ive tried a multi-face jpeg collage deepfake and a VR deepfake and it seems to work. Check your DMs

cosmico

You will already know this because its sent to you, but just for everyone else to see. I have sent you 5 different before videos, alignment files, and afters videos(conversions). I would really like to have this issue solved, So I'm trying to send you the max amount of data possible. I don't know th...

cosmico

Thanks Djang anfd torzdf for the reply and follow up. I still have no solution to this issue. . Djang I did delete the entire faceswap file and re install it. And yeah, no real errors in training. Torzdf: If I understand what you are saying, you want me to convert a two faced video, but instead of c...

cosmico

https://media.proprofs.com/images/QM/user_images/2503852/1562928344.jpg I wonder If I need to uninstall and reinstall everything. Maybe the problem is somehow entirely on my end Edit: Update, I deleted faceswap and reinstalled it, and I also found that I had some nvidia game ready drivers that need...

cosmico

I replicated the scenario a third time, this attempt was to deepfake some pictures with a bunch of faces inside of them (of the same person) in each picture, and got the same results. Instead of every single face in that picture being converted, only one would randomly be converted. I'm surprised no...

cosmico

Reflections is a perfect example. It used to work in reflections for me too just like it used to work in VR, but now it doesn't. And I dont think this is alignment/extraction related because if my video is 10 seconds x 30 fps x 2 faces (cause VR), you would expect that I would have extracted 600 fac...

cosmico

Normally when converting VR videos, you convert both faces at the same time, the left angle of the face and the right angle as the VR clip is two videos side by side from slightly different angles. Since I've updated (it probably wasnt the most recent one, I usually only update once every couple wee...

cosmico

Ummmmmmmmmmmmm Also I have sessions 1, 4 ,and 6 two times. and those 2 session number 6's start at the same exact time but by looking at the eg's and iterations, they appear to be different sessions. Also One of them has a eg/s of 140 which is real nice, but I'm 10,000% sure the best my computer can...

cosmico

. . My training seems to be going pretty well but I couldn't help but notice this in the lower log: 09/26/2020 15:22:00 INFO [Saved models] - Average loss since last save: face_a: 0.12294, face_b: 0.18499 09/26/2020 15:24:16 INFO [Saved models] - Average loss since last save: face_a: 0.12187, face_b...

cosmico

Since you replied, I've thought about it a lot, I think I figured out why. The preview in app is relatively small, since you can't get the images to take up you entire monitor since you have all those task and tool bars and logs on your left and bottom. While the actual timelapse preview, when you o...

cosmico

. The questions are super simple, just let me give a little context. . So I've made a handful of deepfakes up to this point, and if seeing their individual sharp k-9 tooth, and seeing the shimmering of light in their pupil crystal clear can be considered 100% trained, usually I settle for 90% traine...

cosmico

This post has seriously helped me alot. I've got a DFLH128 model I'm super excited about now thats 93% perfect with in 50 hours of training.

When starting new models/projects, now I refer to those gifs I made of your videos all the time.

Faceswap Forum

Search found 95 matches

(Thought experiment) With enough power, are 10 second ultra realistic faceswaps possible?

Re: Does anyone know if the loss-function's eye & mouth multiplier come at the cost of slowing other facial features dow

How important are non-swappable bodily-features; like face shape and hair color to you in your finished faceswaps?

Does anyone know if the loss-function's eye & mouth multiplier come at the cost of slowing other facial features down?

Re: 3 small training abnormalities and questions.

3 small training abnormalities and questions.

Re: Log and graph weirdness

Re: The realface model

Re: Conversion error involving multiple faces per frame

Re: Conversion error involving multiple faces per frame

Re: Conversion error involving multiple faces per frame

Re: Conversion error involving multiple faces per frame

Re: Conversion error involving multiple faces per frame

Re: Conversion error involving multiple faces per frame

Conversion error involving multiple faces per frame

Re: " Average loss since last save: 282 octillion" or some times "nan" ???

" Average loss since last save: 282 octillion" or some times "nan" ???

Re: Does anyone else feel like the training "previews" always look better than the "timelapse" photos?

Simple question about lowering the learning rate near the end of training

Re: Comparing model types with examples