HELP!! PLEASE!! Update: Problem solved! It's working perfectly now!

#5
by lucas-ai26 - opened

Guys, I need help, please. When I use this LoRa (any version), the execution freezes at 19% and doesn't progress. Several messages appear: "[WARNING] LoRa key not loaded". This happens with any node I use (Power Lora Loader rgthree or LoraLoaderModelOnly).

I'm using all the original templates (checkpoints, text encoders, VAE, workflow) posted by comfyui. Do I need to do something else that I don't know about? Could someone help me solve this problem? Thank you in advance.

Update: Problem solved!

I replaced the LoRa with this converted version to run on ComfyUI, and it worked incredibly well. Very fast generation and with excellent quality! ( https://huggingface.co/QrusherZA/H3_Turbo_ComfyUI/tree/main ). Use the node "Power LoRa Loader"..I'm using a 720 x 720 resolution, 4 or 6 steps, and Euler - beta. Another tip to speed things up even more is to use the "spectrum apply minimax h3" node; it's amazing, it almost halves the generation time and has very little quality loss! ;)

lucas-ai26 changed discussion title from HELP!! PLEASE!! to HELP!! PLEASE!! Update: Problem solved! It's working perfectly now!

Update: Problem solved!

I replaced the LoRa with this converted version to run on ComfyUI, and it worked incredibly well. Very fast generation and with excellent quality! ( https://huggingface.co/QrusherZA/H3_Turbo_ComfyUI/tree/main ). Use the node "Power LoRa Loader"..I'm using a 720 x 720 resolution, 4 or 6 steps, and Euler - beta. Another tip to speed things up even more is to use the "spectrum apply minimax h3" node; it's amazing, it almost halves the generation time and has very little quality loss! ;)

Where do you get that node "spectrum apply minimax h3" ?

Sign up or log in to comment