Blurry result. Tips and help please on making a better quality video

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
gwyneth4320
Posts: 7
Joined: Sun Sep 27, 2020 8:13 pm
Has thanked: 5 times

Blurry result. Tips and help please on making a better quality video

Post by gwyneth4320 »

Blurry result even after having the followings:

  1. Used more than 11k images for both A and B face
  2. 1080p for B face, 720p for A face
  3. Used 3 x 1080p videos for B face
  4. Being very specific when clearing unwanted images after extraction stage
  5. iterations more than 200k
  6. used 'Original' model/trainer

Am i missing anything? Or should i be using another model/trainer?

Please advise.

Thanks in advance

Top
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:
Contact bryanlyon

Re: Blurry result. Tips and help please on making a better quality video

Post by bryanlyon »

We'd need to see some samples to know for sure, but a few points:

1: Original is a 64x64 model, that's pretty low res for any large videos. You may need to downscale your video or use a larger model.
2: Data curation is a bit of an art. It takes time to get down. Almost everyone's first video is a failure.
3: Using a single video for Face A might lead to overtraining the A side (especially if that's the video you're swapping as well)

Top
Locked

Return to “Training Discussion”