It's Tali'Zorah, you bosh'tet!
2/17/2025 Update:
Finally got around to updating this... This new noobaiEPSv11-based model has a completely new dataset, going from the previous 119 images to 305 images of Tali! With that totally redone set of images comes with MUCH better tagging, since I ripped them straight from e621 and gelbooru, which is the first time I've done that, so this model supports both e621 AND danbooru tag schemes (about 70% e621). When picking images, I had a major bias to any art that had fine details regarding her outfit, especially the swirly pattern that her purple clothing has, so her outfit is much more accurate now. ☝️
Notes:
A lot of images have her eyes 'pass through' the helmet. Personally I dislike that, so to prevent it, use "eyeless" in positive and "glowing eyes, looking at viewer" in negatives. (Or embrace it!)
Noob-based models inherently knows a good bit about Tali, so feel free to play with the weights of this lora. I mostly used 1.0-0.8 weights, but it could probably go lower.
Tali is the best romance option is Mass Effect.
Tali has 3 fingers. Using "(3 fingers:1.2), (2 fingers:1.1)" seemed to help with those results. Avoid using just 'fingers'.
I didn't know this, but loras trained on Epsilon v11 noob work great on the vpred version of the model. Most example images were on vpred. The more you know 🐛
Older Description
3/14/2024 Update:
I updated this model for use with PDXL. Please see the "About this version" section to the right for details. It's pretty much the same model, just trained on better tags, at a better resolution, and with a better optimizer. Hope you enjoy!
Older Description:
This is a lora trained on 119 hand picked images of Tali'Zorah from Mass Effect. It was trained mostly on digital art, but there are some 3d renders in there for variety. I know there is already another Tali'Zorah lora on this site... But I had already trained this before checking so... Here we are! I have not tested between the two, so it's up in the air which one is better. Feel free to test. It was trained on danbooru-style tags, so use those when trying to prompt - I've included the tags in a .txt file in the "Training Images" download below.
It works pretty well with most ckpts, but I recommend Anything 4.5 or AOM3A1B, I used them for the example images.
NOTES:
-It actually seems to understand her alien fingers (She only has 3). I did not do much testing on her feet, but it also seems to kind of get them, too.
-Her weird little skirt(?) thing on her outfit is a bit inconsistent, but otherwise it gets her suit quite well
-A number of images it was trained on had added "eyes" to her, from behind her helmet. If you add "glowing eyes, purple eyes" to the prompt, you can kind of get them, but they may need to be emphasized a good bit.
Example prompt: (See example images, all images should still have their metadata. Just drag the images onto the PNG info tab and import it.)
Description
FAQ
Comments (10)
just want 2 let u know ur a legend
Any chance you'd be willing to do more Mass Effect characters? Like Male Shep and Kaiden? Your work is just amazing!
I'll consider them, but in truth... I've never even played Mass Effect! In fact I haven't played half of the games that the characters from my loras are from. I'm a huge poser :P
ZoochMan... You were the guy who nailed what I like the most: Faceless... Thanks friend, you are a friend!
And if so, what are the chances of you doing something related to these characters? Since faceless and genderswap are a perfect combo:
- Hunk (Resident Evil)
- Ghost (Call of Duty)
- Marine Wetsuit (Fallout 4)
- Doomgirl (Doom)
- Guardians (Destiny 2)
- YoHRa (Nier Automata)
Love the lora, thank you but something is confusing me, is the lora named <lora:tali:1> or <lora:talizorahMassEffect_v1:1>? Its been driving me crazy, Im trying to organize my lora list
This one is simply named Tali, when I name my loras I try to name them as simply as possible.
@ZoochMan This is really strange, because I saw the lora named <lora:talizorahMassEffect_v1:1> in some of the work submissions here for YOUR lora, and I've been use that lora for a while. I was thinking maybe it was the the other lora you've linked in the description, but that one is called <lora:Talizorah1:1>, and looks way different. But the weird thing is that both your lora <lora:tali:1> and this mystery <lora:talizorahMassEffect_v1:1> have about the same exact size and I can't make heads or tails of that.
So yeah, not sure where did the third tali lora came from, or if it's simply your lora that somehow got renamed and I downloaded somewhere again.
@BladdyVaddy Civitai used to force rename files to an automated rename iirc. Could be you downloaded back then. Also, there is a setting (at least on vlamantic fork of auto1111) to choose whether a lora is prompted by filename or its alias from its metadata. That all being said, if you want to check if files are different, you can get a "MD5 & SHA Checksum Utility" from googling. It would allow you to verify whether a file is exactly the same or not.
Also, if you get the civitai helper extension (I recommend goldmojo's fork atm, since the main branch refuses to support lycoris), it can be made to automatically scan your files, and it will get most (civitai has some bugged hashes, and the bug report channel on discord is locked) of the files a preview pic downloaded for the thumbnail, and create an info file which can be viewed to see the page's information, including metadata on every pic. This extension can also be used to check for any files that have updates.
Can you specify the base model in the details please? Its currently set to 'Unknown' which means this LORA doesn't work with Stable Horde at all.
It was trained on the NAI anime model. It's intended to be used with Anything 4.5 or pretty much any anime model trained off the NAI model.
I don't use Stable Horde, so I have no idea what this has to do with anything, but I hope this helps.