Trained on AnyLora
To get the best results, please read the description below:
Recommended weight: 0.6-0.8
Activation word: Hina
Use of " beautiful detailed eyes, ", "Detail Tweaker LoRA" is also recommended for good results
Upscale to 1.5
Using anime SD models is recommended, some semi-realistic checkpoints may also work
I would appreciate any reviews, positive or negative!
I would very much appreciate you sharing your results ^_^
If you have any suggestions on what LoRA i should do next, please share them in the comments
Enjoy :)
Description
Version 1 - trained on 44 images
FAQ
Comments (5)
I love it so much <3
Can you upload pictures that use just the Hina LoRa and not detail tweaker and eye enhancers? Showcase should be what the LoRa looks like, not what it looks like with enhancers.
I kind of disagree with the idea that showcase images shouldn't contain any enhancers, IMO using some enhancers should become the standard just like all the negative embeddings now are. I always work with them and don't really see any reasons to stop.
Those enhancers don't change the picture much, they only make it look a bit nicer - so it's not like the images don't objectively illustrate the quality of the LoRA when i use some enhancers. And I would rather present my LoRA with the best images i managed to generate, because by that I may as well be providing an already paved path or instruction for people who might want to use my LoRA's to get better results :)
@12user34kn276 That's fair it's your LoRa, just others publish their images without any enhancers, it makes it easier to see the base capabilities of their LoRa vs other similar LoRas. Like I want to see what is different between your LoRa and another Hina LoRa for instance. Maybe bad example since idk any other Hina LoRas but it would apply to your Nami/Robin/Yamato LoRas
@JoesephMother2030 That makes sense! I’ll try to do more of that in the future, but updating the showcases for already published LoRA’s would just take a lot of time, so i probably won’t be doing that:)
Details
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.