Today we explore how to use the latent consistency LoRA in your workflow. This fantastic method can shorten your preliminary model inference to as little as 0.7 seconds and in only 4 steps using ComfyUI and SDXL. This will also make it a lot easier to run these models on older hardware and is just mind-blowing fast! Now, it isn't perfect, but it sure helps you find some base images quickly.
#comfy #stablediffusion #aiart #ipadapter

You can download the LCS LoRA models from hugging face here:
https://huggingface.co/latent-consist...

Interested in the finished graph and in supporting the channel as a sponsor? I will post this workflow (along with all of the previous graphs) over in the community area of YouTube. Come on over to the dark side! :-)

   / @sedetweiler