Spaces:

jasperai

/

flash-lora

like 155

Running on Zero

Hello, indeed this is a problem we are aware of, apart from paying for a dedicated GPU, I don't really know how to solve this (I did try loading the LoRAs on the CPU and then passing the new pipeline to the GPU for inference but it didn't complete properly, I'm not very proficient with ZeroGPUs. It works quite well locally though. Feel free to download the space and use it on your own machine. If you have a fix for the LoRA setup, I'll be happy to merge it !