version 3.0R (Lora, based on the version 7.6V model (it is not even on patreon yet), the most detailed and complete version of Lora, is much better than version 2.0R and with a greatly enlarged dataset)
P.S. new model ogipote (2.5D) and ogipote (2.5D)_v2.0 on Patreon
I made a video on how to achieve the same quality or just repeat my art
A small version comparison:
when I release version 1.3, versions 1.2 and 1.2R will be released to the public
Hands finally reached the style of the 90s. There were many difficulties, dozens of versions, but I found a golden mean, from which I will continue to build on future updates.
just use hires fix as much as your video card is capable of, so as not to give an error, with 8gb of video memory it is 512x768 with hires fix 2, upscaler Latent (nearest-exact), the picture will be much more detailed. If you want a style close to the original but with more detail, don't use Denoising strength above 0.55, but to avoid artifacts, do not use too low a value, optimally 0.5
LORA weight 0.6
CFG Scale - 7
Eta noise seed delta 31337
Use Abyssorangemix3aom3_aom3a3.safetensors With these negative prompts:
(worst quality, low quality, extra digits:1.4)
Trigger Words: First, depending on what you need, trigger words are not required at all, read:
1990s \(style\) - most often makes enlarged eyes and detailed pupils, as in anime Slayers or Sailor Moon for example.
1980s \(style\) - there are some 80s arts, when used together with 1990s \(style\) sometimes very interesting results are obtained
retro artstyle - additional optional trigger
Combined with my other LORA
How to use LoRA's in auto1111:
Update webui (use git pull
like here or redownload it)
Copy the file to stable-diffusion-webui/models/lora
Select your LoRA like in this video
Make sure to change the weight (by default it's :1
which is usually too high)
*Information taken from Lykon
Please post your work with or without comments, it will help me improve. Thanks!
If you like my work, click on the heart above, I will be pleased :3