more lora for anime

change lora heights

change lora heights

change realistic to DPM++ 2M SDE Karras

change lora heights

change lora heights

change lora heights

change lora weights

return status when starting inference, less muscles

hydra

forced lora

forced lora

remove load loara for tests

add gaussian blur on rpogress images

changed to DPM++ 2M Karras scheduler

restored handler to a supposed working version

Push to hf

New handler

set inference to false once finished

working endpoint with pwV5

PD model and funcitonnal endpoint inference + check progress'

added requirements memory speed xformers

remove memory speed xformers

Using PAth for imports

change path for imports

change path for imports

change path for imports

change path for imports

change path for imports

change path for imports

change lora path to root'

change lora path to root' & git push

try repo path for imports

add custom handler