Text-to-Image
Diffusers
art

๊ณต์œ ๋งˆ๋‹น์— ์žˆ๋Š” ๋‹จ์› ๊น€ํ™๋„ ๊ทธ๋ฆผ์„ ํ•™์Šต์‹œํ‚จ hypernetworks ํŒŒ์ผ. ์ฒซ ์‹œ๋„์ด๋ฉฐ, ์ œ๋Œ€๋กœ ์ด๋ฏธ์ง€๋ฅผ ๋„ฃ์ง€ ์•Š์•˜๊ธฐ์— ๋ฏธํกํ•œ ๋ฉด์ด ๋งŽ์Šต๋‹ˆ๋‹ค. ๋“œ๋ฆผ๋ถ€์Šค๋กœ๋„ ์ œ์ž‘ ์ค‘์ž…๋‹ˆ๋‹ค. ์—ฌ๊ธฐ์„œ๋Š” ์ข€ ๋” ๋งŽ์€ ์ œ๋Œ€๋กœ ๋œ ์ด๋ฏธ์ง€๋กœ ํ•™์Šตํ•  ์˜ˆ์ •์ž…๋‹ˆ๋‹ค.

A hypernetworks file trained on the picture of Kim Hong-do in "https://gongu.copyright.or.kr/". This is my first attempt, and there are many shortcomings because I didn't put the image properly. It is also being produced as a Dream Booth. We are going to learn with more proper images here.

์Šคํ…Œ์ด๋ธ” ๋””ํ“จ์ „ 1.5๋ฒ„์ „์„ ์‚ฌ์šฉํ•˜๊ณ  ์žˆ์Šต๋‹ˆ๋‹ค. ๋‹ค๋ฅธ ๋ชจ๋ธ์—์„œ ์ž˜ ์ž‘๋™๋˜๋Š”์ง€ ์•Œ ์ˆ˜ ์—†์Šต๋‹ˆ๋‹ค. ๋˜ํ•œ ๊ฐ™์€ ๋ชจ๋ธ์„ ์“ด๋‹ค ํ•˜๋”๋ผ๋„ ์•„์ง์€ ์ œ๋Œ€๋กœ ์ž‘๋™ํ•˜์ง€ ์•Š๋Š” ๋ฉด์ด ์žˆ์Šต๋‹ˆ๋‹ค.

I am using Stable Diffusion version 1.5. Don't know if it works well on other models. Also, even if you use the same model, there are aspects that still don't work properly.

'img2img'์œผ๋กœ ์“ธ ์šฉ๋„๋ฅผ ๊ณ ๋ คํ•˜์—ฌ ๋งŒ๋“ค์–ด์กŒ์Šต๋‹ˆ๋‹ค.

It was created considering the use of 'img2img'.

-Translated through Google Translate.

์‚ฌ์šฉ ๋ฐฉ๋ฒ•

'stylekimhongdo' ๋ผ๋Š” ํ”„๋กฌํ”„ํŠธ๋ฅผ ๋„ฃ์œผ๋ฉด ์ž‘๋™ํ•ฉ๋‹ˆ๋‹ค.

If I put the 'stylekimhongdo' prompt, it works.

-Translated through Google Translate.

์ƒ˜ํ”Œ ์ด๋ฏธ์ง€ sample image

  1. https://www.instagram.com/p/CnlNGZmyrel/
  2. https://www.instagram.com/p/CngND0DSjRh/

๊ด€๋ จ ๊ธ€ Related article

  1. https://gagongjaryo.com/2023/01/14/์งญํ™๋„

jjabhongdo1

Downloads last month
0
Inference Providers NEW
This model is not currently available via any of the supported third-party Inference Providers, and the model is not deployed on the HF Inference API.