L8: Loras in ComfyUI - Comfy Academy

Let's learn how to use Loras in ComfyUi. Loras is a very effective way to create more styles and better images with the models you have. You can use Loras to create various styles, including specific clothing styles, actions, faces, and colors. You can even add more details to the image and get better skin details in your AI image.

#### Join and Support me ####

[damienmescudi]

Thank you so much Olivio, you've taught me more than all the teachers put together. Your pedagogy, your clarity and your commitment to the subject make it hyper accessible and I'm very happy to learn so much, and it's all thanks to you.

[Hexrun]

@Olivio I would love to see an academy series on model/lora/ti training please :)

[taucalm]

Whats the reason for using different VAE than the checkpoints gives?

[MikevomMars]

I wish usage information for every Lora would be saved within that file since it is quite tedious to re-visit each Lora's download page to look up the correct paramters used.

[TheRMartz]

Was there a lesson on embeddings and I missed it or will you create one? :D

[mat]

Hi, thanks for the video. Would you mind explaining what the CLIP Set Last Layer does?

[Atreyuwu]

Hey Olivio, thank you for the awesome tutorials!! I have used your lessons almost exclusively so far for ComfyUI - and I've learned so much from you.

I am curious though, why your 'Learn ComfyUI' playlist only goes up to video 8, when there are many more videos.
The funny thing is, I can't seem to find where the other videos reside on your channel, and when I search for Lesson 9, 10, etc. it brings up nothing - though if I watch to the end of one, I will get a link for the next one.

Just wanted to let you know, because if I hadn't watched this video all the way to the very last second, I wouldn't have discovered there were more in the series - so if your metrics show that lesson videos after lesson 8 are getting significantly less hits, that might be why.

Keep up the great work as always, cheers! :)

[maxdeniel]

Hi Olivio, very nice video, thanks for the tutorial, I have a question, how can I get the nodes "CR LoRA Stack" and the "'CR Apply LoRA Stack"?

I can download your workflow, but I think it is gonna pop up an error because I don't have those nodes installed.

Thanks in advance.

[MariushAI]

@OlivioSarikas Will you continue the series on Comfy Academy?

[goodieshoes]

it was never explained what clipskip is??

[---Nikita--]

thank you very much for the playlist with your helpfull videos

[Xavi-Tenis]

excellent tutorial, and the detail of the explanation
when part 9? hehe maybe animatediff? or IPa?
thanks a lot

[rokiplay]

Great video, thanks:) I have one question. Can I call the LoRa just through the prompt so it's not activated when the prompt is not asking for it?

[AI-Art-achitecture]

Hi, thank you for your shares, I have a question : how to to creat a image have same ration with controlnet image ?

[SameerMirza-scef]

Hey Olivio, I created a ComfyUI node called "Lora Info" that helps with trigger words and example prompts. might be useful in your workflows

[amrhesham]

Thank you so much for this, it was so helpful

[signsbystu]

I was hoping he would show how to choose the location of the LoRA. I have downloaded LoRAs and I use them for other setups with Auto111 and Forge. Comfy does not give me the option to change where I can load my LoRA from, I need to be able to choose a folder, ideally it would nice to save each node as a template for like SDXL lora node (specific folder) Flux Lora node (specific folder). Maybe I missed it, but can't seem to find it

[hongtian]

in this way to use Lora, do we need to put trigger words?

[CameronWills]

the series started out fine but then you quickly jumped over some important features without any explaination of what they do or why, such as embeddings in your negative prompts, clip skips etc.
Tutorials for beginners should explain what each thing does with examples, to help understand what's being done and why instead of just jumping to the end results or moving on to other topics

[Beauty.and.FashionPhotographer]

would an XY PLOT GRID be implemented between the LORA and the Prompt node, or somewhere else?..in order to get different Loras and different weights of these LORAS tested in a Grid Test Image ?