This is my new Model! If you want your own style/person trained, just DM me with a dataset of ~20 imgs on discord Flonix#4022 and ill train it for you!
Lora made on drdarkwolf's SheVenom Dataset, set the weight lower than 1 to get it to follow your prompt more. Also remember to set CLIP skip to 2.
https://www.deviantart.com/drdarkwolf
USE WITH HIRES FIX LIKE THIS HERE & my MJ Model \/
example prompt:
purple, SheVenom, tongue out, tits, marvel
Steps: 20, Sampler: Euler a, CFG scale: 8, Seed: 1821601100, Size: 720x512, Model hash: 043e39185e, Denoising strength: 0.46, Clip skip: 2, ENSD: 31337, AddNet Enabled: True, AddNet Module 1: LoRA, AddNet Model 1: SheVenom Woman(69509d4016e2), AddNet Weight A 1: 1, AddNet Weight B 1: 1, Hires upscale: 2, Hires upscaler: SwinIR_4x
Keep in mind this is a LoRA, so you need to use it as such. It's not a standalone model and it's not a TI.
How to use LoRA's in auto1111:
Update webui (use
git pulllike here or redownload it)Copy the file to
stable-diffusion-webui/models/loraSelect your LoRA like in this video
Make sure to change the weight (by default it's
:1which is usually too high)
usage by @Lykon
Hide
Description
Bad version
FAQ
Comments (5)
Tried multiple models and settings but I'm struggling to make a quality image with this one.
well it works best with this model https://civitai.com/models/6488/flonix-mj-style
Can you add some prompt examples for the different looks?
purple, SheVenom, tits, marvel
these tags work great
Example Prompt:
SheVenom, tits, marvel
Steps: 20, Sampler: Euler a, CFG scale: 8, Seed: 2205360797, Size: 512x616, Model hash: 043e39185e, Denoising strength: 0.46, Clip skip: 2, ENSD: 31337, AddNet Enabled: True, AddNet Module 1: LoRA, AddNet Model 1: SheVenom Woman(69509d4016e2), AddNet Weight A 1: 1, AddNet Weight B 1: 1, Hires upscale: 2, Hires upscaler: 4x_foolhardy_Remacri
I want to ask if venom eyes are replaced by humans, what's the prompt?