Esthetic-80s-style

我要开发同款
匿名用户2024年07月31日
17阅读
所属分类aiPytorch、text-to-image、lora
开源地址https://modelscope.cn/models/sd_lora/Esthetic-80s-style
授权协议Apache License 2.0

作品详情

Lora of the 80s is completely based on the official art of those years, no

modern imitators, only the original, in the future I want to update this lora at least once and add characters that I loved as a child or just forgot to add. As well as improve the "understanding" of the characters of this lora. ( ͡> ᴗ ͡<)

I made avideoon how to achieve the same quality or just repeat my art

P.P.S. new model ogipote (2.5D) and ogipote (2.5D)_v2.0 on Boosty

P.P.S. If you want to support me, then you can subscribe to my Patreon and get builds earlier than they come out here (versions on patreon will always be newer by one than here) This will help me a lot in updating the video card over time to make models even better and faster (the main thing is better)

Eta noise seed delta 31337

LORA weight 0.5-0.6

Use Abyssorangemix3aom3_aom3a3.safetensors With these negative prompts:
(worst quality, low quality, extra digits:1.4) or (worst quality, low quality:1.4)

Trigger Words: 1980s \(style\)

Optional Trigger Words: retro artstyle

** 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 2-2.15, 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 0.6, but to avoid artifacts, do not use too low a value, optimally 0.5**

CFG Scale - 5.5-7 (for some reason hands are a little better at 6)

The training took place at a resolution of 512x768, so it makes no sense to use 512x512

** 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[

](https://huggingface.co/OneRing/TP3.7.safetensorsPlease)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

声明:本文仅代表作者观点,不代表本站立场。如果侵犯到您的合法权益,请联系我们删除侵权资源!如果遇到资源链接失效,请您通过评论或工单的方式通知管理员。未经允许,不得转载,本站所有资源文章禁止商业使用运营!
下载安装【程序员客栈】APP
实时对接需求、及时收发消息、丰富的开放项目需求、随时随地查看项目状态

评论