able2608

VAE seems to not be causing that much of an issue. I have compared the difference between original vs VAE processed and original vs VACE processed (albeit using ComfyUI and...

> I came across the same color issue. It's really easy to reproduce. > > Provide any image to VACE, and all black mask. The expected result is that all...

Judging from the network architecture, controlnet support seems to be possible. However, most controlnets come from the community, not from the original author. Perhaps we need to wait a while...

The provided checkpoint already contains both WAN 2.1 and the adapter, and you should be able to use it out of the box. That said, if you want to use...

You do not need to use the node `CogVideoXFunSampler`, replace that with `CogVideoXSampler` and that'll do the trick. You have already installed all the required nodes.

First and foremost, there is a tool call Unianimate. It is built with pose transfer in mind and ONLY does pose transfer. Although VACE supports pose transfer out of the...

> Not gonna work with 6gb of vram for sure In my experience 6GB is totally fine though. Been able to do more than 100 frames with 480p resolution. Perhaps...

I guess that most of the VRAM burden is on text encoding with those heavy t5 models (on my Comfy setup using the vanilla checkpoint without any memory optimization tricks...

Quite late to the party, but I found someone who did exactly what @lack is asking for: [NoteLLM](https://github.com/HorseSword/joplin-plugin-notellm). It supports streaming and is also able to hide the thinking process...

I don't think you need to train a lora for what you're trying to achieve. How to do it depends on scenarios though. 1. If you just want those flowers...