We used one of Meina's model to generate the images.
We don't provide exact prompts on the images, because we do post-processing on them so we lose the information, but we include tags how to summon her, which should be enough for you to use the model.
Tips to use:
Use LoRA weight between 0.6-0.8
If you want anime style make sure to use the tag "drawing"
To summon her use the following tags: tyrande whisperwind, night elf, 1girl, pointy ears, long hair, green hair, colored skin, jewelry, medium breasts or large breasts, looking at viewer, earring
You can also add purple skin, but it rarely works, usually she is white or really dark purple
The prompts above only describe the character, make sure to put clothes on her too
If you have any questions feel free to ask!
Hope you guys like it! ❤️
You can ask for character LoRAs on our patreon page. Consider supporting us. 😘
Description
FAQ
Comments (14)
No prompts? what a shame
Why do you need prompts?
@Pikkiwynn because your preview images are AWESOME and people learn a lot from exact prompts, like the model used, textual inversion, and keywords. When artists don't share the prompts it takes much longer time to make something similar, and in your case the images are truly unique.
@zx96 Thank you, but the thing is we are only using the LoRA with the tags written in the description. We add poses, angles and a bit of a background descriptions to it and that is it. We also enhance the images by adding a bit more color to it.
@Pikkiwynn I don't know if you, or the model really are just that bad. Not a great look to have a public tantrum. I don't know mate when or if I make model I'll put it up warts and all with screen shots of what I did. all I read was you photoshoped it or "borrowed" liberally or entirely advertising and stock assets from mmo under MS stewarship, though probably in for a reboot after umpteen years and umm "challenges" (like getting smacked like world boss on anti--just about everything) in hornyteenporn er umm dev culture. frankly if I had some say I'd consider not allowing models and pictures that don't include in PNGs and tiffs all the deets, plus the same in screenshots and text. The sight really needs a reproducibility standard. so I'm i'm just going to assume you stile game assets.
@Pikkiwynn and when I reed "enhanced and added color" all I hear is: My model is to janky to stand on it's own, so I photoshopped in colors you'll never get.
@bugsbe what?
@Pikkiwynn So not only did you post in game art as if its your own, your model is to week to stand on its own, photoshopped in color, but your to dull to read. Wow, why did you post anything then anyway? U haz no proof uz no stoly from game art, prompts or iz stolen concept or other type of media from a MMO ur model iz eet just that terrible?
@bugsbe There is no way we are going to start arguing with you when you can't even form a coherent sentence. You have absolutely no idea how LoRAs work. Therefore, you have no standing ground lecturing others.
But just to prove our point:
- We did not use in-game art. There is no point in that. The LoRA would look terrible. It would look like the in-game model, pixelated and 3D. If you would know what you are talking about, you would know this much.
- What is wrong with changing the saturation and hue a bit? You can check how others have used it. It works pretty well for them too.
So you can stop your pointless arguing. Nobody cares.
Goodbye!
Looks nice, but please consider to at least add the model which was used to generate the example images to the description, so we can get an idea what works best.
Also, this might be an "akshually" moment, but you have a typo in the title. Name is whisperwin ->d<-
It should work with any model, you don't need to use the one we used, but we used one of Meina's model. Just try it out with the one you usually use.
I was curious, because I tested it on 6+ different models before making the initial post. Used both nai and sd based mixes and the only one that didn't gave me messed up faces was darkSushiMix.
The model's base model version is always in the model details: SD 1.5. I just tested it with 7 different models: Anythingv4.5, AOM3A1, ChilloutMix, CMoon, MixProV3, OrionMix, PopcornMix. Simply followed the description with little background description. They turned out great. Keep in mind I only generated 1 image with each model: https://imgur.com/a/6LTEmf9
Details
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.