Faceswap Forum

CProdDigital

After extracting multiple sources to a folder, I have multiple alignments files, and I know theyre important, is it a good idea to extract that folder to unify the extraction settings/alignment file?

CProdDigital

Thank you so much for all your help dawg, I notice youre the one replying to everyone (Mine) posts and being so helpful I really appreciate it. The sad fact is this comes with experience. If your data doesn't look highly varied in terms of pose, expression, color, lighting etc. then it probably isn'...

CProdDigital

I tend to keep them around as they take up less space than a folder of faces wait can you use the alignment file INSTEAD of the folder of images? or do you mean After youve done all the training you want, you then delete the faces folder and keep the alignmnets, then if you want to train again you ...

CProdDigital

The swapped video has B face with a big toothy smile when A face is deadpan. Alot of the pictures for B Face are smiling, but there is reference of them with a straight face from multiple angles. How can I tell the AI no thats incorrect, this is the correct face?

CProdDigital

in my converted video I'm noticing 3 key issues 1- The face is shaky/jitters. I managed to fix this a little with the spatial alignments tool, but its still a very noticeable problem. Is this caused by too many of a similar reference in the training set? 2- The features blur during particular facial...

CProdDigital

The mask of actor B doesn't seem to extend down far enough on the face of actor A, so especially when they open their mouth wider, the chin and bottom of lip get lost/fade out.

How can I adjust the mask so B face extends farther down on the face?

CProdDigital

I have multiple alignments files for all the different pictures and videos Ive extracted for training, but just the one folder for the extracted faces to go in. Id like to clean up/change my training frames folder, do the alignments files matter? I know the alignment data is stored in the meta of th...

CProdDigital

After going to convert, It told me I had missing alignments for the video, and realized I hadn't extracted the source video. So I went back and did that and converted without issue, but read that its better for your A source alignments to be separate, so I extracted it to its own folder and found th...

CProdDigital

torzdf wrote: ↑Wed Nov 09, 2022 11:44 am
Yes, you want lots of variety on both sides.

Does having too much of the HMC footage clog up and confuse the training? still getting a blurry result when I use an expanded data set

CProdDigital

If I wanted to repeatedly use the same B face for new A videos, is there a way to reuse training/progress to speed up future uses?

CProdDigital

I've got thousands of frames of front on high res head mounted camera footage, as well as lots of other pictures and slightly lower res video from other angles for both actors. My goal was to put actor B onto HMC footage of actor A, which I thought would be easy since I have so much HMC footage of b...

CProdDigital

Ive got lots of facial capture footage I'm trying to put onto other facial capture footage, as in both actors are looking directly at the lens of a head mounted camera. For actor B (the face Id like to put on the clip od actor A) Ive got many frames of HMC footage as well as a smaller sample of vide...

CProdDigital

I cant make another post rn for some reason, but do you know how to reuse data from B source for a new A video, or vice versa? like a new B souce but keep data from the A vid training?

CProdDigital

I'm using footage from a head mounted facial capture camera to train a swap right now, so I have a LOT of dead on frontal frames that I'm training from, like 12,000. This seems like overkill considering its just them talking so there's probably alot of "redundant" frames, and I've got some...

Faceswap Forum

Search found 14 matches

Is it a good idea to extract from your faces folder to consolidate the alignments file?

Re: How can I asses and fix shortcomings in my training sets?

Re: What is the relationship between the extracted images and the associated alignments file?

Swap is smiling when A source video is straight faced

How can I asses and fix shortcomings in my training sets?

Mask cuts off toward bottom of face

What is the relationship between the extracted images and the associated alignments file?

Missing Alignments file?

Re: Output blurry even after 800,000 iterations?

How do you reuse training/data from B source face for a new A Video/face?

converted video bad even with many training frames and 800k iterations, how can I tell if there's an issue with training

Output blurry even after 800,000 iterations?

Re: How does FaceSwap handle changes in the B input library, or training model mid training?

How does FaceSwap handle changes in the B input library, or training model mid training?