thanks for this. Does IDM VTON work better than IP Adapter V2 for transferring the outfit or like IPA, it is just an approximation and not the exact replica of the outfit?
anyone know why my ksampler step would be extremely slow? I followed these directions to a T, twice and both times the process stalled at Ksampler and took 10-15mins for just 2-4 images. help!
Hi. U are using img2img+ Controlnet +IPAapter!. You know it's useless? Try bypassing the Controlnet and you see the same result ,and try putting another image input for IPAapter, same result. I think the best thing is to not do img2img ,but work with 2 Controlnet , like openpose and canny ,to keep the shape of the girl. Do you think it's good what iam saying? I tried like this, and could see the difference in the T-shirt, like changing its style to make it realistic. But I don't know how to have more control I think something is missing. Could you help, please? Appreciate
Great video! How can I add additional nods, like face adapter or an upscaler to this workflow, is it possible to include it in 1 generation or I need to add a second step in the workflow?
Iam in need for running comfyui with higher vram than mine. Does this methode have its own vram or will it use mine? How much vram does it have please. Tell me if its the best methode or if there is another way so that i seach. Please
Well done. I did the grid method on A1111 last week, and it was not this easily achievable. Though, you could say this workflow may seem daunting to someone not familiar with ComfyUI. Subbed!
Any idea about why my "ImageCompositeMasked" is missing the x y? I've been looking for different nodes that have it but can't find it... anyone could please give me a hand with this? Thanks!
when I try to open IDM VTON in Pinokio. I will get an error where it says: ENOENT: no such file or directory, stat '/Users/-----/pinokio/api/idm-vton2.git/{{input.event[0]}}' any help?
Something feels weird about a company that trained in millions on artists work without consent talk about their license and terms of use. - Don't get me wrong I'm not some sort of anti-ai warrior that writes "AI sucks" on every AI image. - But to see them try to enforce copyright on users when they themselves cared little about it is a bit funny. - I think at some point there will be a complete open source version of some of these models.
Also impressive work they did, but at the same time not. The newest discoveries in the field is thanks to AI scientists. The dataset is thanks to unappreciated artists. All they really did was just throw a ton of money and compute at it. Which basically anyone could do in theory. And all that compute will be a waste once a smarter architecture or training method is discovered.
the ceo's plan on supporting censorship and censoring the new models is really showing and its terrible we are going to need to fix these open source models our selves no matter what it will take!
thanks for this video! amazing! ..No matter what I try, I don't get the option of applying the Apply IPAdapter Node.. What do I miss? would be thankful for any help!
So i can see this used on amz and Levi's and nordstrom and wherever, BUT. It's a bunch of guys making this. Choosing the ideal model and fitting and bg. Coding this. Until a woman is doing this for women's clothing, the BIGGEST rev stream, this is just wasted genius. It'll work great for furniture, though. My point is NOT that a man made this. But the scalable selling will be when women, like me, can adopt it. Maybe show that so ppl not as immersed as me can see it better.