Type | |
Stats | 1,272 722 |
Reviews | (274) |
Published | Apr 30, 2023 |
Base Model | |
Trigger Words | nanoless |
Hash | AutoV2 CCF2FD1A8A |
This is a LoRa to recreate the style of Nanoless.
I suggest using this LoRA at 0.7-1.0 weight for best results.
This LoRA was trained on 500 sfw and nsfw pictures with NAI. All examples images were generated My Own Mix and Anything V3.
I suggest using this LoRA at 0.6-0.8 weight when using with other LoRAs or Characters. (Just play around with it.)
It works best on anime models or models trained on NAI.
I suggest generating at 512x512 then upscaling to a higher resolution.
Otherwise you can generate at 768x768 then upscale for finishing touches.
All pictures were upscaled using these settings:
Upscaler: Fatal-Anime 4x
Hires. Steps: 25
Denoising Strength: 0.5
Upscale by 1.5 (768x768)
Known Issues:
Watermarks show up way too often but you can negate this by adding (signature,watermark, patreon logo, patreon username:1.3) in negative.
Everything I'm making will always be free but if you want to show a little bit more support, you can buy me a coffee - https://ko-fi.com/ekune