Result: Face Parts in Different Colors - How to fix that?

[AlonDan]

I've tested with JPG / PNG and a VIDEO and I get the same result:

• It shows parts of the face in different colors, like it's mapping the areas of nose, face, etc.. in different colors and it's not showing the actual clean final result
• It is very blurry (like the original Wav2Lip)
• The more the video progress the more blurry it gets
• As the video result progress sometimes mouth/teeth appears on random places many times = many mouths
• I've tested on short videos (few seconds 3 - 45 seconds long) I get the same results
• I used English Audio (tried different audios just in case) I get the same results
• I tried different resolutions, it doesn't matter I still get the same results

---

I followed all the instructions using Anaconda on Windows 10 machine, I created a dedicated 'Wav2Lip-HQ' environment, installed using the requirement file and downloaded all the needed models and placed them where needed, also did the 'wget' one, but still can't get a clean result.

Did I miss something?

Can somebody explain how can I fix that issue and make it works? Thanks ahead!

[harisreedhar]

@AlonDan Did you find any solution?

[tushar-31093]

Seconded. Any fix to this problem?

[AlonDan]

Unfortunately after many tries, it seems like it's just broken or not ready to use, unless there is a better Step-by-Step instruction or Video Tutorial I don't really have any clue how to make it work.

I must mention it looks great on the demo videos, but unfortunately it's not working as I explained above.

I hoped that by now someone from the community will either make a tutorial or Share: high-quality / higher resolution pre-trained model that works on the original Wav2Lip branch.

[codenamewei]

This issue is of the same manner with #6. That being said, more than one person has been facing this as I did too. Unless it's being fix, the results is not usable