Hello CivitAI, this is my first Lora of a videogame character called ''Nasara'' from Crime Boss: Rockay City which is currently one of my favourite titles and I've decided that I should give one of my favourite characters a shot, thus it led me to create a Lora based on him and his appearance. It has been trained on a particularly large dataset of 201 images.
Activation Prompt: ``cbrc_nasara``
Recommended weight strength: Between 0.8 to 1
________________________________________________________________________________
Basic prompt: cbrc_nasara, 1boy, solo, flat chest, dark skin, dark green eyes, brown hair, dreadlocks, tattoo, dark-skinned male, silver rings, tattoos, (glasses, glasses with red lens, glasses with red tint, red glasses), facial hair, beard
________________________________________________________________________________
Full prompt with his outfit and accessories: cbrc_nasara, 1boy, solo, flat chest, dark skin, dark green eyes, brown hair, dreadlocks, dark gray jacket, dark gray vest, dark gray dress shirt, dark gray tie, dark gray pants, pants, tattoo, shirt, formal, suit, beard, dark-skinned male, jacket, long sleeves, black pants, black shoes, silver rings, tattoos, (glasses, glasses with red lens, glasses with red tint, red glasses), facial hair, formal, beard, watch
________________________________________________________________________________
Recommended Settings:
Sampling Method:
Euler A (40 steps), I found it to be the best sampler for this Lora.
DPM++ 2M Karras (45 steps),
DPM++ 3M SDE (63 Steps)
________________________________________________________________________________
HiRes Fix (I always use it after txt2image generation in most of my images):
Denoise values ranging from between 0.48 up to 0.51
Upscaler: 4x-UltraSharp
HiRes Steps: 45 should be fine, I use 63.
________________________________________________________________________________
CFG Scale: 5,5 - going below 5 will make the image look more real and may not stick to your prompting
________________________________________________________________________________
Recommended prompting as I usually go with my images:
high quality, intricate details, masterpiece, BREAK cbrc_nasara, 1boy, solo, flat chest, dark skin, dark green eyes, brown hair, dreadlocks, dark gray jacket, dark gray vest, dark gray dress shirt, dark gray tie, dark gray pants, pants, tattoo, shirt, formal, suit, beard, dark-skinned male, jacket, long sleeves, black pants, black shoes, silver rings, tattoos, (glasses, glasses with red lens, glasses with red tint, red glasses), facial hair, formal, beard, watch
And for negatives:
(bad quality, worst quality, back lighting:1.2), realism, realistic, lowres, bad anatomy, jpeg artifacts, suggestive, nsfw, (out of frame, frame, border:1.7), (watermark, text, signature)
If there is too much shine/glow type aura around the character, please use ``back lighting`` in negative prompts.
________________________________________________________________________________
- Notes from the author:
For my first lora I tried to make it as versatile as possible when it comes to adapting to styles to the best of my ability, feel free to give it a try. It works with anime styles and realism styles, it also works with concept loras. Personally I am happy with how it turned out plus I wanted to have a lora of a character I like. 😊
I have tested this particular Lora on three Illustrous based SDXL models, they're awesome:
________________________________________________________________________________
Quintillus - Illustrated "Reality" by nottheninja
https://civitai.com/models/1131256
Hassaku XL (Illustrious) - v1.3 - Style A by Ikena
https://civitai.com/models/140272
Hesperides [Illustrious-V1.0] by bloodsplash
https://civitai.com/models/1246248
________________________________________________________________________________
Thank you for checking out this model page. Have fun generating and have a great day!