I dont know if you tried already but if you select the source file from the source selector inside of fusion you can select a whole faceset, for example you can get the source video into facelab, extract all the images into individual files and later extract the faceses so you can have your faceset, this faceset can be feed into the facefusion as individual files (png, jpg, etc) and improve the consistency of the results. The video is great man ;)
@alexvillabon
14 күн бұрын
Wow, im not sure I understand but it really sounds interesting. Could you elaborate?
@Glifan-official
14 күн бұрын
@@alexvillabon sure, my idea came from my former use of deepfacelab to create the videos, the idea is that in your target video you can get more consistency in the result, and make the AI imagine less and have more points of reference, if you instead of feed facefusion one image you feed facefusion with a lot, so instead of having one as reference it can have thousands to get ideas to create the faces, At least the process would be as follows, 1- lets say that you have two videos src(source) and dst(destiny). 2-You want the dace of src into the face of dst. 3-you take the src video and introduce it into the folder of workspace in deepfacelab 4- you click in extract images from video data_src.bat (this will separete every frame and turn it into an individual file) 5-later you can press in 4) data_src faceset extract.bat (this will extract a frame with the face detected in every file)that will contain the face in the size that you say once you start the process. 6-later from you can clean not good pictures or repeated to avoid redundant faces 7- later you can open facefusion and click into select the source file (or files) and it will allow you to feed him a lot of pictures from teh ones you extracted, idk exactly the limit but i tried with aprox 1800 and it works right of course wiht the downside of the time it takes to move all of the images. you can later select as you say the target video and do all what you did. at least i did notice an increase in the overall quality. Sorry if i didn't explain myself good enough, my language is the spanish
@alexvillabon
14 күн бұрын
Woah that is amazing! I had no idea I could import more than one image for the person's face! How does it decide what to use from each picture though. This is so interesting and helpful, thank you for sharing.
@behrampatel4872
13 күн бұрын
@@alexvillabon im "guessing" it works like a deep-fake . i.e tries to reach the output using all the inputs. In deepface lab we'd shoot the source face in various lighting conditions. Just a guess. Also would comfy allow us to run Expression Restorer before Face Enhancer ? cheers
@alexvillabon
13 күн бұрын
@@behrampatel4872 turns put the processes happen in the order you select them. As for the multi image input, i spoke with the developer and he let me know 5-6 images is the sweet spot. After that amount it doesnt really make a difference.
@VintageForYou
14 күн бұрын
I only got FaceFusion 3.0 a few days ago and your video explains how to use it. It's a great tutorial, and you have a new SUB.👍😁
@alexvillabon
14 күн бұрын
Happy to hear it helped! Thanks for the sub :)
@RS_0_7______
9 күн бұрын
I have run into a major issue, I have a RTX 3070ti but it doesn't show the CUDA option, only CPU, any fix for this?
@RDUBTutorial
Күн бұрын
Have you done any experiments swapping 2 faces in same shot or swap of same face over multiple shots (same face from different angles in same clip)?
@JavierCamacho
15 күн бұрын
Face fusion will stack up the process base on what you selected first and so on. For me, I deselect everything, the selected in this order... Face enhancer Face swapping This will make facefusion run one after the other.
@LoopnMix
15 күн бұрын
is the output better than what is shown?
@alexvillabon
14 күн бұрын
Oh! Thank you, I didnt think of trying that.
@visiblemaker
14 күн бұрын
Yes, the order of activating the processor defines which one is calculated first. More sense in my experience: 1. Face Swapper 2. Expression Restorer 3. Face-enhancer If you wanna use lipsyncer or agemodifier, put them after or before Expression Restorer, but before the Face-Enhancer. Definetly makes a difference on closeup shots, as well as using the 512x512 or even 1024x1024 FaceSwapper Pixel Boost.
@cornuArietis
15 күн бұрын
Really cool, thanks for creating and sharing!
@callyt09
15 күн бұрын
Modul not found error: no modul named ' numpy ' problem please solve it. One vedio for this topic plaese 🙏🙏🙏🙏
@WillFalcon-b7l
9 күн бұрын
Hi! Thanks for the video. I was facing a problem with side views and don''t know how to fix it. It is always flickering and trying to put front face into the side view. What can I do for it?
@alatteri
13 күн бұрын
Anyway to get this to render out at higher bit depths? Seems to do 8biit only.
@isrogan
12 күн бұрын
I just get errors when saving the frames during the process, any fix?
@EarmWermChannel
13 күн бұрын
Warning. Prerequisite for Pinokio is a ton of SDK files and dev tools, tons of tool scattered across your machine that you might not want.
@rajatsingh5723
9 күн бұрын
What does "Execution thread count" means under execution Provider and what is the best value we can select for 'Cuda'. Can anybody help?
@Mike-jj8nq
11 күн бұрын
is the pinnokio UI default still local? Or do I need to click on local URL
@alexvillabon
9 күн бұрын
Yes, still local.
@PelDaddy
14 күн бұрын
Difference key with some erode/dilate and blur should give you a reasonable matte to play with, not as good as the real thing, but at least a start. Thanks for making these. Interesting stuff.
@alexvillabon
14 күн бұрын
That is a way around it. I actually tested it but the reason why I didn't mention it was because the matte is barely usable because of the different compression artifacts.
@PelDaddy
14 күн бұрын
@@alexvillabon Ah, very good point, with compressed footage, which so few of us normally work with! You still couldn't choke out the artifacts or clip them with a black or white clip? Perhaps frame blending or noise removal first would help. But it looks like the developer is on to this given the earlier comment below. (That face exporter proof of concept video)
@alexvillabon
14 күн бұрын
Yeah I saw that! Having a face matte option would be amazing.
@M_a_r_e_k_B
15 күн бұрын
Another great video, thanks 👍
@dalecorne3869
6 күн бұрын
I've been running FaceFusion 3 in Pinokio for about a week now. I love it. The ONLY thing is I don't have the CUDA option at all. I have CPU and DIRECTML.
@alexvillabon
6 күн бұрын
That's strange. Might be a Pinokio thing. Consider installing the non pinokio version and see if that fixes it? Only thing I can think of.
@dalecorne3869
6 күн бұрын
@@alexvillabon I'm just going to leave it as is. It works for me, just takes awhile, but I'm retired and I have all the time in the world
@henryruhs
2 күн бұрын
@@dalecorne3869 Love to see that even older folks are using my software. 🙏
@Realdmighty
13 күн бұрын
How to use this on colab
@Mike-jj8nq
4 күн бұрын
Facefusion 3.0 is not very AMD Friendly....constantly crashes
@VesuviusAntaria
8 күн бұрын
For the Processors it is the order you check that determines the order. You can then decide for yourself in which order you want your method.
@alexvillabon
6 күн бұрын
Yes, thank you. I had no idea. I will do a followup video where I cover some new things I have learned.
@VesuviusAntaria
6 күн бұрын
@@alexvillabon I'm curious with Face_editor if that can animate like blinking eyes or moving head. Because if you set that then the head and expression only stays in that position.
@alexvillabon
6 күн бұрын
@@VesuviusAntaria im actively looking into that. Otherwise it seems like a feature for images only.
@VesuviusAntaria
6 күн бұрын
@@alexvillabon Maybe it works with the live webcam to express extra facial expression? Ideal for cgi animation for movies.
@callyt09
15 күн бұрын
Plaese do some some thing🙏🙏😢
@MMMMeeeeMMMM
15 күн бұрын
But, these tools really seem to be illegal.
@aintelligence-ef2yd
14 күн бұрын
😂 It’s like saying photoshop is illegal bc we can do the same thing (but with lot more time)
@aegisgfx
14 күн бұрын
Face fusion is heavily censored, so does not need to be regulated
@kalayan705
2 күн бұрын
onething i say its not better than roop unleash see the results nothing great anyway its ok for basic swap faces
@alexvillabon
2 күн бұрын
Good to know. Is roop compatible with video as well?
@kalayan705
2 күн бұрын
@@alexvillabon yes its compatiable borh pics and videos
@alexvillabon
2 күн бұрын
@@kalayan705 Nice. Ill check it out.
@aegisgfx
14 күн бұрын
Face fusion is heavily censored by the way
@alexvillabon
13 күн бұрын
@@aegisgfx in what way? Seems to have no issues with celebrity faces.
@aegisgfx
13 күн бұрын
@@alexvillabon any nudity even cleavage and it won't work at all
@aegisgfx
10 күн бұрын
@@alexvillabon try nudity
@roy5181
2 күн бұрын
You mean nsfw? You can change 1 line with the editor and its not cencored anymore. Trust me 😉
@aegisgfx
2 күн бұрын
@@roy5181 which line?
@henryruhs
15 күн бұрын
Creator of FF here... so you are asking for this? watch?v=qwDqm1wpEEs
@alexvillabon
14 күн бұрын
Hey Henry. Yes, that is exactly it! How do you manage to render the face by itself with an alpha channel?
@henryruhs
13 күн бұрын
Now in our buymeacoffee shop - free for members.
@callyt09
15 күн бұрын
Modul not found error: no modul named ' numpy ' problem please solve it. One vedio for this topic plaese 🙏🙏🙏🙏
@alexvillabon
14 күн бұрын
Not sure I can help. I'd refer you to the github page.
@bigpiipe3206
9 күн бұрын
Missing python input. I’d suggest manually downloading numpy into python and it should work
Пікірлер: 62