This is a New Style Lora I have created, it is suitable for cartoon styles.
I will suggest using 0.6 to 0.8 weight for this Lora. Using weight above 0.8 can look more like the original art however this can cause the hands to go wonky and messy.
In the example images I used the same prompt and experiment with different Models.
This Lora is more stylized therefore the hand part may need additional fixes or extra care.
Model: Most known 2d models
Prompts: a girl wearing a white shirt and grey jacket, (hand well), (finger well), (long braided hair), (bangs), with in frame, ultra-detailed, 8k, masterpiece, beautiful detailed face, ((no texts)), no names, (volumetric lighting), beautiful detailed eyes, (ambient light), realistic shadows, (fullbody:1), (1girl), (cowboy shot), (shirts), pants, looking at viewer, perfect body, body well:1, leg well:1, arm well:1 , (GoodhandsV3)
Neg: (easynegative), (hands poor), (fingers poor:1), (badquality), (bad anatomy), (nsfw), (legs poor), (inaccurate limb:1), (bad-image-v2-39000), (2girls), bad composition, inaccurate eyes, (extra hands:1.2), (inaccurate limb:1.2), (extra arms:1.2), (bad quality), bad face, (bad eyes), deformed, ((deformed fingers:1.2)), ((extra fingers, extra limbs)), bad hands, bad fingers
Steps: 31, Sampler: Euler a, CFG scale: 9, Size: 512x768, Denoising strength: 0.34, Clip skip: 2
Description
Previous version did not uploaded correctly
FAQ
Comments (7)
oh wow, this looks great
i, myself, have a special lycoris prepared for next week of Motoko Kusanagi
I wonder what great things we could do when we mix our models together :-)
p.s. any chance you could put also prompts for the samples you've uploaded? i really love them
and I love the original Motoko (all the other ones are inferior to her, but that's only my humble opinion :P)
here are some samples of her: https://imgur.com/gallery/ONWF6bY
Maybe because im fairly new to this but I CANNOT generate anythjing that looks like it's in this style. Not sure what i'm doing wrong. I've loaded the Lora. Do i also need the yml?
I’m using the standard SD 1.5 base, should i be using something else?
@herpderpleton Yes I will suggest you try with some more popular 2d models people have recently published. For example Abyss, Camel, Dalcefo. Most of these models can be found on Civitai.
You do not need the yml for this.
When I download the file it shows up in .safetensors extension. How can I get the images?
Yes this Lora file is created as a safetensors model. You will need to put this model with in your stablediffusion lora file like this. (stable-diffusion-webui\models\Lora) There are plenty of videos on youtube teaching you how to do this.
Maybe I will create a video talking about how you can put this in your file and how to use it.
@EnthusiastAI Thank you so much 🫶