Maybe I misunderstand the project but I feel it'd make sense to support some local inference, i.e using arbitrary ComfyUI workflows?

I dont think i am understanding your reply

you can use LTX to generate the videos, this video took 15s on a 4090

https://vimeo.com/1152992073?share=copy&fl=sv&fe=ci

nice did you make this just for the comment? haha

yep haha

we live in an era of frictionless slop creation. yay.

I've been using this with nothing notable to mention besides there seems to be a common bug where you receive an empty text response.

https://discuss.ai.google.dev/t/gemini-2-5-pro-with-empty-re...