sd-webui-roop VS FaceFusion

https://github.com/s0md3v/sd-webui-roop this link is for the original one and you can install another version of your choice if you want just by replacing the given link with your choice. (Just google it)

Adding Roop to the picture This is where Roop comes into play, to generate high quality content, we need to enable roop extension and use img2img to feed in a sample image we can use for the generation. click on "extension tab", then "install from url". enter github repo link of roop sd-webui-roop and click "Install".

Found it out here: https://github.com/s0md3v/sd-webui-roop/issues/227

I'm trying to install the roop extension (https://github.com/s0md3v/sd-webui-roop) on a rented runpod running sd a1111 and it's a no go when generating images. Steps I've taken:

Fuck that's a good idea... I have an inkling how you might do it, but it involves an extension I haven't needed yet - I'm gonna try it out quick and report back...

There is a undocumented usage example on the repo

The extension can be installed from "extensions -> Available." You can type the word "face" in the search bar to make it easier. You can read more about it here: https://github.com/s0md3v/sd-webui-roop.

Don't know if that helps, but here is what I do. First I generate an image sequence from the input video. Then, I start my StableDiffusion (with the sd-webui-roop extension installed of course : https://github.com/s0md3v/sd-webui-roop). In img2img, use the batch tab. Specify your input and output directory Set width and height to the correct ratio (same as your video). Turn down Denoising strength to 0 Enable roop of course. Fire up that generate button. When done, get all the images from the specified output directory, and merge them into a video with whatever tool you prefer.

There's no mitigation, the technology is out there for anyone to use:

https://github.com/facefusion/facefusion

Together with diffusion models we better get used to not take a video for proof that something happened. The way we already don't trust photos, because it's has been trivial to make convincing face swaps with Photoshop for a long time.

just download https://github.com/facefusion/facefusion . it very easy to use and results are amazing if face is not full screen. And with coqui_tts you can clone anyones voice form 10-20 second audio. Deepfakes got very dangerous already. Roop (Facefuiosn) also works real-time via webcam (rtx 3060 can easily handle it) Frankly it's kinda scary already. I gues in 12-20 months quality of that stuff will dramatically improve and even on 4k footage, it will be impossible to spot deepfake for 90% of population.