Adding the ability to select the face to be swapped with in the video that contains more than one face #18

New Issue

2021-06-22T16:50:03+02:00

doaa831 commented

2021-06-22 16:50:03 +02:00

(Migrated from github.com)

No description provided.

NNNNAI commented

2021-06-23 03:41:01 +02:00

(Migrated from github.com)

We will consider adding this ability to the current project. Many thanks.

❤️ 5

AlonDan commented

2021-07-01 04:10:33 +02:00

(Migrated from github.com)

Question:
With the current version, how it's choosing automatically which face to swap? (based on 1 face video)
Is it the biggest / brightest one? is it most Left to Right or something combine?

Just wondering until we'll be able to choose faces, respectfully to your hard work if it will be a thing of course.

**Question**: With the current version, how it's choosing automatically which face to swap? (based on 1 face video) Is it the biggest / brightest one? is it most Left to Right or something combine? Just wondering until we'll be able to choose faces, respectfully to your hard work if it will be a thing of course.

NNNNAI commented

2021-07-01 05:15:23 +02:00

(Migrated from github.com)

Technically speaking, the subject of each face change is the person with the highest confidence in the face detector. In layman's terms, it is the most prominent face.

NNNNAI commented

2021-07-02 16:06:45 +02:00

(Migrated from github.com)

Thanks for your comments. The function of appointing a specific person to change face has been added, please go to Inference for image or video face swapping for details. If this rep helps you a lot, please star it! Many thanks~.

Thanks for your comments. The function of appointing a specific person to change face has been added, please go to [Inference for image or video face swapping](https://github.com/neuralchen/SimSwap/blob/main/docs/guidance/usage.md) for details. If this rep helps you a lot, please star it! Many thanks~.

❤️ 2 🎉 1

robbsaber commented

2021-07-02 20:34:33 +02:00

(Migrated from github.com)

Inference for image or video face swapping

Will this be added to the colab notebook?

> Inference for image or video face swapping Will this be added to the colab notebook?

AlonDan commented

2021-07-03 01:49:57 +02:00

(Migrated from github.com)

Thanks for adding this feature,, I just quick tested it and it's GREAT! you rocks❤

I just added an issue which is a suggestion to help in the project.
consider I'm not a programmer but I fall in love with this project already so I want to help using my skills if possible.

You can read about it here: #32

Thanks for adding this feature,, I just quick tested it and it's GREAT! you rocks❤ I just added an issue which is a suggestion to help in the project. consider I'm not a programmer but I fall in love with this project already so I want to help using my skills if possible. You can read about it here: #32

NNNNAI commented

2021-07-03 07:47:23 +02:00

(Migrated from github.com)

Inference for image or video face swapping

Will this be added to the colab notebook?

We will make colab demos of all the new features recently. Many thanks~.

> > Inference for image or video face swapping > > Will this be added to the colab notebook? We will make colab demos of all the new features recently. Many thanks~.

👍 2

NNNNAI commented

2021-07-04 16:46:29 +02:00

(Migrated from github.com)

@robbsaber the colab of "multi specific " has been released, please go to colab for details.

@robbsaber the colab of "multi specific " has been released, please go to [colab](https://colab.research.google.com/github/neuralchen/SimSwap/blob/main/MultiSpecific.ipynb) for details.

👍 1 🎉 1

Sign in to join this conversation.

1 Participants

Notifications

Due Date

No due date set.

Dependencies

No dependencies set.

Reference: CalvinBackup/neuralchen-SimSwap#18