local video generation really usable yet

[mangopeak72]

Posting this in case it saves someone else a little time.

If you were starting from scratch today for this use case, what would you choose first and what would you ignore?

I'm especially interested in mistakes worth avoiding.

[turbogrid11]

Posting this in case it saves someone else a little time.

What worked for me was pretty simple. Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at NVFP4.

[cacheline]

Interesting, I hadn't tried that. I ended up in about the same place using TensorRT-LLM. I got better results once I stopped chasing one metric and just looked at whether the workflow felt usable.

[fastlab]

Not sure I agree there. The reported numbers can look compelling, but in ordinary usage I didn't see the same benefit. Worth testing the simpler explanation before adopting the more interesting one.

[phasetrack]

subscribed, curious where this lands.

[plainline]

Good point. The pattern around KV cache pressure has been pretty similar for me. The biggest change for me was simplifying the stack instead of adding one more optimization layer.