watching this intently for updates :D

#1
by gjnave - opened

Me every few minutes: refresh
is this going to require low noise as well?

QuantStack org

The high-noise models have already been uploaded. Thanks for your patience🙌🏼🙌🏼 … there are a lot of models 😅

The high-noise models have already been uploaded. Thanks for your patience🙌🏼🙌🏼 … there are a lot of models 😅

so no need to wait for low-noise models than right? :D So awesome btw.. you were ON it. haahah

Well… from what I see in the workflow, the flow is divided into two sections.

High noise would be for the first KSampler.

Low noise would be for the second KSampler.

You can run the first one and generate video, but the models do the following:

The high-noise expert focuses on generating overall layout and motion.

The low-noise expert refines textures and details.

Here you can see workflow and examples to use it on ComfyUI
https://docs.comfy.org/tutorials/video/wan/wan2_2

Well… from what I see in the workflow, the flow is divided into two sections.

High noise would be for the first KSampler.

Low noise would be for the second KSampler.

You can run the first one and generate video, but the models do the following:

The high-noise expert focuses on generating overall layout and motion.

The low-noise expert refines textures and details.

ok .. trying to wrap my caveman mind around this .. soo... then we ARE waiting for you to relase the low noise ... ?

QuantStack org

Well, here you can find information about what I mentioned:

https://docs.comfy.org/tutorials/video/wan/wan2_2

You can run the first stage, which is the one that uses the “high noise” model, and already see results of the generated video.

In the second stage, you use the “low noise” model to improve the quality of the video.

YarvixPA changed discussion status to closed

Sign up or log in to comment