These files are Custom Workflows for ComfyUI
ComfyUI is a super powerful node-based, modular, interface for Stable Diffusion. I have a brief overview of what it is and does here. And full tutorial on my Patreon, updated frequently.
Please consider joining my Patreon! Advanced SD tutorials, settings explanations, adult-art, from a female content creator (me!) patreon.com/theally
Description
FAQ
Comments (6)
Nice to see you to update and working on comfyUI workflow and nodes
I will definitely try these out, but I have to mention a thing i figured out that can help you: did you know you can use a different text encoder (CLIP) for to generate images? This potentially means you can use prompts phrased in normal english and the model gets it better. If you use the OpenAI CLIP it seem to work pretty nicely.
Oh, interesting, with the CLIPLoader node?
@theally Exactly. I tried this with my models and it works pretty good.
How does this work? I tried downloading a .bin file from https://huggingface.co/laion/CLIP-ViT-bigG-14-laion2B-39B-b160k and the output is just a garbled screen. The .bin file is loaded with the CLIP Loader and connected to the text prompts instead of the checkpoint.
@gsgsdg Could you describe the process of using it in more detail or give me a link to read it? Thank you in advance.