, , (thick outlines, cinematic lighting_1.2), solo, 1girl, expressionless, closed mouth, dark blu.jpeg)
, , (thick outlines, cinematic lighting_1.2), solo, 1girl, expressionless, closed mouth, dark blu.jpeg)
, , (thick outlines, cinematic lighting_1.2), solo, 1girl, maid, facial mark, smile, looking at v.jpeg)
, , (thick outlines, cinematic lighting_1.2), solo, 1girl, maid, facial mark, smile, looking at v.jpeg)
, , (thick outlines_1.2), from side, solo, 1girl, expressionless, closed mouth, looking to the si.jpeg)
, , (thick outlines_1.2), from side, solo, 1girl, expressionless, closed mouth, looking to the si.jpeg)
, , (thick outlines, cinematic lighting_1.2), solo, 1girl, slight smile, closed mouth, blonde hai.jpeg)
, , (thick outlines_1.2), multiple views, reference sheet, solo, male focus, 1boy, facial hair, g.jpeg)
, , (thick outlines_1.2), multiple views, reference sheet, solo, male focus, 1boy, facial hair, g.jpeg)
Type | |
Stats | 757 |
Reviews | (8) |
Published | Apr 29, 2023 |
Base Model | |
Training | Steps: 3,920 Epochs: 20 |
Hash | AutoV2 FF3590B819 |
!! PLEASE READ !!
The original artist who made the concept art for S4 League and KIDO: Ride on Time has passed away 6 years ago, but you can still see their work here.
Install the LoCon extension here. Or use that extension that's displayed in the blue box.
Resource used: https://civitai.com/models/22530
This was requested through Google Forms
Weight: 1.0
Trigger: there's none
Can do concept arts well using multiple views and a reference sheet.
The resolution trained is at 768. This request was the most intriguing thing to wake up to. I have never heard of the artist nor the games themselves, but the art style looks distinct enough for me to get straight to training. I haven't an idea on what waters I'm treading on training a dead artist's work, but I'll take it down based on the responses of the community.
The results of your generations are dependent on the additional LoRAs, weights, and models you use, so it may not work or come out as consistent as my sample images. Other reasons may include me using xformers, token merging, and a modified DPM++ 2M Karras sampler.