Makes things more realistic looking, works better for text2image than text2video but works fine on both, just add it as a lora, no trigger words.
Description
FAQ
Comments (10)
Love it! Will post some images as soon as possible.
How can install this into runpod?
I've not used runpod, so you'll have to figure out how to get it from the console I guess?
download civicomfy from model manager watch a youtube tutorial
RTFM
https://docs.runpod.io/tutorials/pods/comfyui
Don’t forget to install any missing models using the model manager. If you need a model that isn’t available in the model manager, you can download it from the web to your local machine, then use the Runpod CLI to transfer the model files directly into your Pod’s /workspace/madapps/ComfyUI/models directory.
Disclaimer: I've never used runpod, I've never opened the website before today. I simply googled "runpod comfyui", the first results were the runpod documentation, which the above excerpt was obviously within.
Question: if you generated an image/video using this and then used that to do another I2V (like for continuing videos), would it make sense to add this lora to that I2V or should it be left off? I can't figure out if motion/new objects in the video would need this treatment to keep the realism or if it would kind of stack the graininess and make it too much.
You'd have to test, but I think the graininess would end up stacking and degrading it further.
at 0.8 H and .4 L works fine for me
@JustAnnaBortion Thanks!
thank you for this, appreciated a lot!