ai_anchorite comments

Results 4 comments of


                                            ai_anchorite

[Feature Request]: Add a button to remove Lora

Project is looking very promising! A related issue that's likely been mentioned and probably already on your roadmap, but just in case: The LoRA loader needs a scrollbar, as only...

Hello. here is the error message at opening. using latest PINOKIO, win 11. latest update done, 256gig RAM, and 4 Gpu in the system Nvidia A5000

It's a problem between the installed Gradio version and fastapi or something. Just have to downgrade gradio to version 4.43.0 to "fix". In Windows, this has to done with **Anaconda...

Thanks! Works well on windows

That model loading behaviour and low vram during inference is consistent with CPU offload. Inference, including vae decode etc, consistently takes me 20 minutes. less than 64GB RAM may push...

> @ai-anchorite I just found out that for running on a 3090 you can disable CPU offloading (#pipe.enable_sequential_cpu_offload()) - leaving all other mem optimizations enabled. Then ~20GB VRAM are used,...