Please check out my Ko-Fi page if you are interested in supporting me.
LoRA commissions open! -> Fiverr
No trigger words for V1.18! Just use the LoRA: <lora:legendOfKorrav118:0.7>
Note: trained on extracted frames from the entire series but I did not tag any characters in it. You might be able to generate specific characters if you prompt for them using booru tags.
Follow the steps in the Model Version notes to reproduce my images.
Sample images generated from Nothing.
All negative embeds should be easy to find. and Prompts should be included in the sample images! Click the little icon in the bottom right to see it.
It was trained on 558 512x512 images scraped from the internet and 18 epochs using animefull_final.
Danbooru tags generated by Waifu Diffusion 1.4 Tagger and fine tuned for specific tags.
描述:
Generate using a weight of 0.5-1 like this: <lora:legendOfKorrav118:0.7>
How I archived my generations:
-
txt2img: DPM++ SDE Karras with 20 steps,512x512(can go up to 768 for wide or tall), Restore faces on (using CodeFormer weight 1.0 in Settings), Hires-fix on, to 1024x1024 (double original size) with your preferred upscaler and Denoise 0.5, CFG 7. Then send to img2img!
-
img2img: DPM++ SED Karras with 20 steps, Restore faces on (CodeFormer weight 1), rescale to 1536x1536, CFG 7, Denoise between 0.3-0.7 (based on how much you want to improve the image), SAME PROMPT! Send to extras when happy with img2img/inpaint results.
-
extras: Scale to x3 (final will be 4608x4608, I suggest going lower, I did x3 just for the samples here) Upscaler 1 - FatalAnime 4x, Upscaler 2 - SwinIR 4x with 0.10 visibility, GFPGAN 0.10 visibility, CodeFormer 0.10 visibility.
训练词语:
名称: legendOfKorraStyle-000018.safetensors
大小 (KB): 29752
类型: Model
Pickle 扫描结果: Success
Pickle 扫描信息: No Pickle imports
病毒扫描结果: Success
