Biswaroop comments

Results 7 comments of


                                            Biswaroop

[binary] Stable Beluga 2 - process p2pd not killed

looks like this will be a bit tricky: So when normally swarm starts it also creates a p2pd process (which hivemind creates), and when any petals service starts (e.g Stable...

[binary] Stable Beluga 2 - process p2pd not killed

I'll check this 🙏🏻

state-of-open-source-ai/models/

@flaxsearch True, thanks for pointing out! hence we also [mentioned](https://book.premai.io/state-of-open-source-ai/models/#id54) - > All model variants under LLaMA-2 are released under [LLaMA-2 License](https://opensourceconnections.com/blog/2023/07/19/is-llama-2-open-source-no-and-perhaps-we-need-a-new-definition-of-open), permitting commercial usage unless it’s facing 700 million...

"Cannot find content_or_style in the current config/example/train_lora_flux_24gb.yaml. Has it been removed?"

it's not removed, works

The right way of using SD XL motion model to get good quality output

thanks a lot for sharing this @F0xbite, would love to use your hybrid workflow above if you could share 🔥

Add automatic kps detection

hi @mymusise thank you! this helped me a bit more on the observability 🙌🏻 kinda stuck with instantid face analysis, do you happen to know any workaround for [this](https://github.com/fofr/cog-consistent-character/issues/4#issue-2334446648)?

train_dreambooth_lora_flux with prodigy and train_text_encoder causes IndexError: list index out of range

I've added a fix, given that we don't tune the T5 text encoder in flux, so that line is unnecessary (possibly a typo). Let me know if that's not the...