This is an archive of my vace flows, most are over a year old. It will take time for me to get them all in working order for release but this is where they will end up.
Archive Flow 1
simplified wan 2.1 vace
This workflow was designed to simplify video to video copies with wan 2.1 vace
This shows a few tricks many may not know
Archive Flow 2 (every single video i released for vace 2.1 used this flow to fix faces)
This can fix any faces, from any video, not just vace.
Face fixing and enhance flow
This was a tutorial flow i made long ago to show how to fix ai mush faces with vace.
Vace face fixing is not as hard as many think and can be done with 1.3b model and bbox masks. Its the best face fixing still to this day for videos. even with 1.3b.
there is one main trick in this flow you will find that enables near perfect face fixing that i dont know anyone else that uses.
This crops the face and does not process the whole video
This has extend abilities to do the vace flows batches or to break larger videos into batches to process.
I cleaned it up and replaced many nodes that were outdated
Notes should explain It was a tutorial flow.
Archive Flow 3 Full vace
Vace work flow.
This is the main flow i used for over a year. I cleaned it up A LOT. I delt with a mess here for a long time LOL. This can do any of the videos i have done. But you will need to learn it. I spent over a year learning and this flow is about as strait forward as i get when showing you how its done. I tried automating many things but each video i made needed me to adjust. It needed me to direct it. And it took a lot of time to do.
This is not my most advanced flow for vace as it does not include inpaint but i never used inpainting. I make new videos not change them. I used this more than any other flow.
I dont know if this is worth the time for many. LTX can do some crazy stuff very fast. This takes time. This can still do more than LTX when it comes to action and i think thats where people will get use of this. I cant replicate what i did here with LTX or any other local model, what i do with LTX is very different.
I will answer any questions in the comments if you have them. I probably dont explain things well enough.
If anything is wrong, errors. Post and i will see to fix them.
I am including a few copies i made of videos. I cant share real videos on civitai.
These copies are some of my best. They can be copied themselves.
Good luck everyone.
Description
simplified wan 2.1 vace
I took out many things most would not understand and confuse everyone... This can still do a lot. If enough people like this flow i can fix up the full ones that fixes many of the issues with this flow but it would take time and i dont know if its worth it with the pace of LTX taking over. LTX cant do some things like skipping, or flips but its really good at everything else.
This is not fast, its a slow, and difficult process to make this work for the things i show... I have done this a LONG time and know how to manipliate the flow to get results, I spent 8 hours to 4 days for each video... Multiple takes, multiple batches... On a 3060. This is why i never understood the hate i have recieved :P. I worked harder to make the ai copy than the people making the originals usually. I now use a 5060 and 2.1 vace still takes ages.
This flow was designed to be used with my face fix inpaint flow that fixes faces.
Faces in this output can be .... not great. Vace face inpaint is actually VERY good.
Going further than 4 batches you will notice a significant drift in contrast. This is worse with a static camera, anything static on the screen will drift and not look good after 6 batches. Moving cameras work well because it wont over contrast the areas remaining the same. PIDnet copies background movement.
That being said nothing copies like vace... yet.