[LoRA] Symbiote / She-Venom LoRA
模型介绍：LoRA for generating images with the "Symbiote / She Venom" Character
LoRA request queue on my discord: https://discord.gg/DAfjhRfyEM
This model was trained using the NAI model. A lot of them were NSFW, so there is a good chance you'll get those as a result. I made 2 models prior to this and merged them together to create this one since the first one was not good enough for me and the second one wasn't that accurate with the white pattern.
Works best by itself but with some inpainting you can get it to work with other character LoRA's.
I got the best results with a weight between 0.6 and 0.8.
Trigger word is symbiote, if you only use that you will get the symbiote face, but since it was trained on other faces aswell you can specify what else you want and it will show a normal face.
Example images were generated using Anything V4.5 on Euler A with 30 steps.
Note: This was made exclusively on anime images and on an anime checkpoint. Feel free to post images on realistic, semirealistic etc. checkpoints, but do not rate it on that! This was made to be used on anime checkpoints so keep reviews for that!
~~~~~~~~~~~~~~~~~~~~~~~o(*￣︶￣*)o~~~~~~~~~~~~~~~~~~~~~~~
示例提示词和参数：
Prompt: masterpiece, best quality, CG, wallpaper, HDR, high quality, high-definition, extremely detailed, symbiote,
Negative prompt: lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry,
Steps: 30, CFG scale: 7, Sampler: Euler a, Seed: 1597149735, Size: 512x768, Model hash: fbcf965a62, AddNet Enabled: True, AddNet Model 1: Symbiote_v3(ca033abe1c4b), AddNet Module 1: LoRA, AddNet Weight A 1: 0.8, AddNet Weight B 1: 0.8, Clip skip: 2
页:
[1]