Gyramuur
Gyramuur
> Can you throw a screen shot in here to see what you mean? We have a pull request in that allows previous actions to have images and to show...
> after activating the **conda env** , **cd** to the root directory of cloned project Try with the following command that resemble the sh file > > `python scripts\evaluation\inference.py --seed...
Yeah img2img transparency would really be a huge game-changer, especially for characters. Seems like the most important thing to do right now.
I've pushed a little further with this to see if I can find some sort of workaround. The first thing I tried was using OpenAI but with "lm-studio" as the...
I just ran into this tonight by starting a batch and then switching to another tab for a little while. When I came back, the Txt2Img previews were all the...
> I'm getting the same issue after the commit 7 hours ago -> it worked perfectly fine then after the node wanvideo add s2v embeds was changed from wanvideoaddaudioembeds, it...
> I tested the bigger push for half the day without any issues with the reference image, still can't reproduce any issues, so no idea what's going on in that...
> > > > Just tried the new model (16gb) and I am getting the same error -> video2audio is txt2vid (just following my prompt) > > > > Will...
> Honestly at this point only thing I can think of is that you have some other version of WanVideoWrapper installed alongside, and it overrides the sampler node so that...
Lol I came here to say this. I don't like the UI, and would much rather just run through console if possible.