Faceswap Forum

Is Faceswap have any update ? Last time I'm here It's V2.10.0 and now It's still the same. Faceswap is constantly updated. It is 'rolling release', so we don't really release final versions.. We push updates and bug fixes as and when they are implemented. The time when I do make a release is when t...

Thanks for this. Will be interested to see how it goes. Incidentally, you can insert a table with this notation (not in a code block): | Syntax | Description | | ----------- | ----------- | | Header | Title | | Paragraph | Text | will give you: | Syntax | Description | | ----------- | ----------- | ...

I'm sorry, without seeing a video I will not be able to help. The face jittering in the frame is not common, nor something I have seen. Without seeing what the actual issue is, I have no idea what a potential solution might be.

This happens because Conda-forge installs an unsupported version of ffmpeg. I have fixed this for fresh installs, but follow the instructions in this post to remedy the issue:
viewtopic.php?p=9716#p9716

I'm not sure such a tool exists. It could most likely be done with some kind of scripting using OpenCV. The issue is, and why I doubt such a tool exists, the search domain would be different for any particular use case. To use your example, how does the tool know that the "face" is an obje...

Help. I can't install the program. Mac Os Sonoma System. I paste the code into the terminal and nothing happens. How to solve a problem? Try downloading the file: https://github.com/deepfakes/faceswap/releases/latest/download/faceswap_setup_macos.sh Then open up Terminal in your Downloads folder an...

Honestly, that would be very helpful. Side by side comparisons are the only real way to understand the influence of each function. However, unfortunately they take a long time to create.

Discussions around loss functions are certainly tricky, because it takes so long to get results, and thoughts on what is happening can be entirely subjective.

If you haven't read this thread already, then I do recommend doing so:
viewtopic.php?t=2176

The issue is that Conda-Forge has updated its version of ffmpeg to a version that faceswap does not currently support. I am looking at a longer term solution, but in the meantime, the following should get Convert up and running: In Windows open up an Anaconda Prompt: Start > Anaconda Prompt Enter th...

Ok, I have now had several reports on this.

There hasn't been a code update in this area for a while, so it is likely to be an issue with one of the libraries we use. I will investigate and see if I can get a fix out.

Please provide the output of: `Help> Output Sytsem Information as per: app.php/rules#rule-4b

Please also press the "Generate" button rather than the "Convert" button and paste the output here.

I would probably need to see a video to understand the issue.

However, this may help you in the meantime: I've trained the model for ages, the previews look good, so why is the swapped face blurry?

Ok, this is a very confusing issue Convert getting stuck indicates a potential issue with the input video The preview tool (which uses much of the same code as convert) indicates that there are no faces in your alignments file The manual tool indicates that there are faces in your alignments file Us...

It is not, no. The sorting mechanism uses data that is stored in the PNG Header of the image, which is only generated by Faceswap's extract process.

Unfortunately not, no. You can't really combine GPUs in this way, and you definitely can't combine Nvidia and AMD GPUs.

Unfortunately, you cannot utilise system RAM for the GPU, no.

If you can get Dfaker running on your GPU, then that is likely to be the best model you can use.

Ok, there appears to be an issue with your alignments file (no faces have been stored)

Firstly load up the manual tool with that video/alignments file combination and see if you can identify the issue..

If you cannot, then I would need a copy of the video + alignments file to investigate further.

I have not linked 2 GPUs for training with NVLink (you'd need NVLink not SLI). However, without NVLink 2 GPUs would just let you run bigger batch sizes, they would not allow you to load larger model.s as a copy of the model needs to be loaded onto each GPU. You'd need to research NVLinking 2 GPUs to...

Unfortunately not, No. You'd need at least 8GB VRAM for that model.

With a 3GB card you will be very restricted to the lightweight model and, possibly, the Original model.

Does the preview tool work?

Faceswap Forum

Search found 2657 matches

Re: About Update

Re: Training Experiment

Re: I have a question，The face I finally synthesized was very shaken.

Re: convert crash

Re: Image sorting tool

Re: [Guide] macOS Install Guide: Installer Method

Re: INFO ABOUT LOSS FUNCTIONS AND TRAINING

Re: INFO ABOUT LOSS FUNCTIONS AND TRAINING

Re: Convert stalls

Re: Convert stalls

Re: Couldnt get ptxas version string

Re: I have a question，The face I finally synthesized was very shaken.

Re: Couldnt get ptxas version string

Re: Extract+Sort by face (full images, not just face)

Re: can my PC handel the Villain model

Re: can my PC handel the Villain model

Re: Couldnt get ptxas version string

Re: Hardware best practices

Re: can my PC handel the Villain model

Re: Couldnt get ptxas version string