LK / Aivanjo
LK / Aivanjo
The same issue. How can we make it work?
Ok, I found a solution: https://phoenixnap.com/kb/ffmpeg-windows I did this and it works for me.
> Even with Clean VRAM I can't get this workflow to run properly. I get to the SamplerStage with the Clean VRAM nodes but it seems to get stuck there....
> Please follow the instructions in the log message and retry the install without repair mode enabled. I tried to enable and disable repair mode, but it does not help....
Is there any other way to install Invoke AI now without using this installer?
> Try turn off the text encoder quantization to None. It works for me. I can confirm this worked for me too.
> yeah, what do you think wan 2.5 can come soon? open source can make that model better I don't know about Wan 2.5, but LTX 2 will be open-sourced...
> In difference with LTXV/Wan, it produces **scenes cuts** though a special block sparse attention mechanism. It's like Sora2, but with sound yet. See their examples https://holo-cine.github.io/ Yeah, I've been...
Agree, the model looks really good (t2v)! Can we get a distlled model/lora please (for pro and light versions)?