Working remote so this is taking longer than I'd like. Uploading four versions. Minimal testing done as I'm away for work. Bob = Made with Bob's upgraded node DMD = DMD lora merged in at 1.0 strength. Saves space and should speed up your generation speed. If you use the non DMD models you will need to load the DMD lora as you normally would at strength 1.0 Check 10Eros discord for sigmas. I used 1.2 sigmas and it was fine however. 10Eros v1.4 Bob INT8 Convrot.safetensors 10Eros v1.4 Bob DMD INT8 Convrot.safetensors < from testing this is the fastest for me on a 3090 and 64GB ram. Most people will want this one. 10Eros v1.4 int8 convrot.safetensors 10Eros v1.4 DMD int8 convrot.safetensors < this one was expected to be faster but not proving to be. Not sure why. Just testing it for fun. Resources: https://github.com/BobJohnson24/ComfyUI INT8 Fast/tree/main https://huggingface.co/tech77/int8 https://github.com/silveroxides/convert to quant
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy