Trained on NAI with 27 pictures.
Best result with weight between : 0.8-1.
Prompt activator : anissa
Other prompts : black hair, short hair, breasts, muscular, bodysuit, pelvic curtain, boots
Commissioned by aleoncenko3 on fiverr
Reviews are really appreciated, i love to see the community use my work, that's why I share it.
If you like my work, you can tip me here.
Got a specific request ? I'm open for commission on my kofi or fiverr gig *! If you provide enough data, OCs are accepted
*Any paid request will not be presented on this page, unless you give me permission to.
Description
FAQ
Comments (6)
Which model did you use to train this model?
First line in description.
NAI == > animefull-final-pruned
@KonanĀ Thanks! I read it but i didn't know what NAI means, so thank you so much.
Another thing i'd like to ask you is, how did you get such a clean lora?, if i go to Invincible comics, i just find Anissa images that are a little bit hard to use in order to get a good lora character, do you crop those images, do you use photoshop or any other tool?
Sorry for all those questions, i've been using SD 1.5 for a long time and the most hard part i'd say it's too get a wide and clean dataset to train my loras, so anything you can help me i'll appreciate it <3.
@parlonte1234279Ā i use everything. Upscaling, cleaning with Photoshop. A good dataset is 80% of the job to make a lora.
@KonanĀ Nice to know, but really.. how did you find the perfect dataset to make Anissa character, i mean, there're not many images about Anissa in the comics, do you use any special page or something to get them?
Could you upload this to tensor art please? Would be much appreciated šš¾
Details
Files
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.