Any checkpoint can now be in the generator. Anything already loaded works for everyone; members load the new ones free for now, with a faster lane and Boost to jump the queue.

Any Model, Any Time: Load It Into the Generator Yourself

We rebuilt the trainer. Watch your run as it trains, generate with an epoch before it's done, and compare epochs side by side. It's in beta, and you switch it on yourself in your preferences.

Training Studio: Watch It Train, Generate As It Goes

A training and content contest with over 2 Million Buzz in prizes and 50% off H3 generation for the duration of the contest.

The Civitai H3 Contest: 2 Million Buzz Up For Grabs

t3sd ver3 (한국어 설명은 아래에 있습니다.)Now I'm not doing SDXL, I'm only doing PONY, FLUX, and SD1.5 models ^0^On the site below, I'm making pictures of the FLUX, PONY, and SD1.5 models that I'm making.You can just look at the pictures and go~<a target="_blank" rel="ugc" href="https://www.patreon.com/t3278">https://www.patreon.com/t3278</a>-★ Member-only models are made and shared with our sponsors.-★ If you upload at least one photo made using the t3sd Ver3 model uploaded by CIVITAI to the gallery, I would appreciate it~-Only SD1.5 models are released on CIVITAI~I had surgery for cancer and came back~It's impossible to stay up all night and make things like before, but I'm doing it moderately~The cfg value for this model is recommended to be 11~18. You can upload more ^^Most of the pictures drawn with the model I am making now on the site beloware released~-※ Caution ※For those who have strange pictures, I recommend that you refer to the settings and from in the EXIF ​​attached picture,and print it out and then evaluate the model.FLUX will come out well even if you roughly print it, but SD1.5 results vary greatly depending on the difference in from and settings.이제 SDXL은 안 하고 PONY, FLUX, SD1.5 모델만 하고 있네요 ^0^아래 사이트에서는 만들고 있는 FLUX, PONY, SD1.5 모델로 뽑는 그림을공개하고 있습니다~ 그림만 보시고 가셔도 되요~<a target="_blank" rel="ugc" href="https://www.patreon.com/t3278">https://www.patreon.com/t3278</a>- ★ 회원 전용 모델은 후원 회원분들과 함께 만들고 공유하고 있습니다.-★ CIVITAI 업로드한 t3sd Ver3 모델을 사용하여 만든 사진을 최소 1장 이상 갤러리에 업로드해 주시면 감사하겠습니다~- CIVITAI에는 SD1.5 모델만 공개합니다~제가 암에 걸려 수술하고 복귀했습니다~전 처럼 밤새고 만드는건 무리지만 적당히 하고 있습니다~이 모델에 cfg 값은 11~18을 권장합니다 더 올려도 됩니다 ^^아래 사이트에서 지금 만드는 모델로 뽑는 그림은 대부분공개하고 있습니다~-※ 주의사항 ※그림이 이상하게 나오는 분들은 첨부 그림에 EXIF에 있는 세팅 및 프롬을 참고하시고출력을 해보신 다음 모델을 평가해는 것을 추천드립니다.FLUX야 대충 뽑아도 잘 나오지만 SD1.5는 프롬, 세팅 차이에 따라 결과물이 크게 달라집니다.

t3sd ver3

t3xl ver01 (한국어 설명은 아래에 있습니다.)★ Please upload at least one photo created using the t3xl ver01 model uploaded to CIVITAI to the gallery.This model will produce a reasonably good picture even without upscaling.The cfg value is recommended to be 7~15.The maximum is thought to be 20.(The disadvantage is that the picture is a bit exaggerated.)The staff only tested it at 30.Most of the pictures drawn with the model currently being made on the site beloware open to the public~You can just look at the picture and go~<a target="_blank" rel="ugc" href="https://www.patreon.com/t3278">https://www.patreon.com/t3278</a>★ Member-only models are only open to sponsors.-------------------------------------------------------------------------------------★ CIVITAI에 업로드한 t3xl ver01 모델을 사용하여 만든 사진을 최소 1장 이상 갤러리에 업로드해 주세요.이 모델은 업스케일을 안해도 적당히 좋은 그림이 나올것 입니다.cfg 값은 7~15을 권장합니다. 최대는 20 까지로 생각됩니다. (단점은 좀 과한표현의 그림이 나옵니다.)스탭은 30 으로만 테스트 해봤습니다.아래 사이트 에서 지금 만드는 모델로 뽑는 그림은 대부분공개 하고 있습니다~ 그림만 보시고 가셔도 되요~<a target="_blank" rel="ugc" href="https://www.patreon.com/t3278">https://www.patreon.com/t3278</a>★ 회원 전용모델은 후원 회원분들께만 공개하고 있습니다.

t3xl ver01

t3xlpo(test3) version (한글 설명은 아래 있습니다.)t3xlpo(test3) version★ Please upload at least one photo you made using the t3xlpo(test3) model uploaded to CIVITAI to the gallery.This model is the third test model after the t3xl(test2) I made before.I recommend a cfg value of 9~13.The XL setting also comes out pretty well.(I tried up to 15, but the picture's tendency may come out strongly.)For reference, I didn't do the upscale or Laura test ^0^Most of the pictures drawn with the models I'm making on the site beloware public~★ Member-only models are only open to sponsors.Most of the pictures I'm making for member-only models are public.You don't have to sponsor to appreciate them.You can just look at the pictures~<a target="_blank" rel="ugc" href="https://www.patreon.com/t3278">https://www.patreon.com/t3278</a>-------------------------------------------------------------------------------------t3xlpo(test3) 버전★ CIVITAI에 올린 t3xlpo(test3) 모델을 사용해 만드신 사진을 1장 이상 갤러리에 올려주시면 감사하겠습니다.이번 모델은 예전에 만들었던 t3xl(test2)다음 세번째 테스트모델 입니다.cfg값을 최대 9~13 정도를 추천 드려봅니다.XL세팅도 어느정도 잘 나옵니다.(15까지는 해봤는데 그림의 성향이 강하게 나올 수 있습니다.)참고로 업스케일 이랑 로라 테스트는 안 해봤습니다 ^0^아래 사이트 에서 지금 만드는 모델로 뽑는 그림은 대부분공개 하고 있습니다~★ 회원 전용모델은 후원 회원분들께만 공개하고 있습니다.회원 전용모델 제작 중 그림은 대부분 공개 하고 있습니다.감상은 후원 안해도 됩니다.그림만 보시고 가셔도 되요~<a target="_blank" rel="ugc" href="https://www.patreon.com/t3278">https://www.patreon.com/t3278</a>-------------------------------------------------------------------------------------

t3xlpo(test3)

t3(2.5D-ver2) version (한글 설명은 아래 참고~)★ Please upload at least one photo you made using the t3(2.5D-ver2) model uploaded to CIVITAI to the gallery.This model is the second 2.5D style model I made before.I recommend a cfg value of up to 22? 13~22.(I tried up to 25, but the image may come out strong.)For reference, I didn't do a Laura test ^0^For those with slightly lower PC specifications, I'll go as far as sd1.5~The next model is the second PONY model. (I think it's not that good because it's the first time)Most of the pictures drawn from the models I'm making on the site beloware public~★ Member-only models are only open to sponsor members.Most pictures of the members-only models being made are public.You don't have to sponsor to view them.You can just look at the picture and go~<a target="_blank" rel="ugc" href="https://www.patreon.com/t3278">https://www.patreon.com/t3278</a>---------------------------------------------------------------------------------t3(2.5D-ver2) 버전★ CIVITAI에 올린 t3(2.5D-ver2) 모델을 사용해 만드신 사진을 1장 이상 갤러리에 올려주시면 감사하겠습니다.이번 모델은 예전에 만들었던 2.5D스타일 모델 두번째 입니다.cfg값을 최대 22? 13~22 정도를 추천 드려봅니다.(25까지는 해봤는데 그림이 강하게 나올 수 있습니다.)참고로 로라 테스트는 안 해봤습니다 ^0^pc사양이 살짝 낮은 분들을 위해 할 수 있는데 까지 sd1.5는 쭉~다음 모델은 PONY 두번째 모델 입니다. (전에는 처음 이라 별로인거 같아요)아래 사이트 에서 지금 만드는 모델로 뽑는 그림은 대부분공개 하고 있습니다~★ 회원 전용모델은 후원 회원분들께만 공개하고 있습니다.회원 전용모델 제작 중 그림은 대부분 공개 하고 있습니다.감상은 후원 안해도 됩니다.그림만 보시고 가셔도 되요~<a target="_blank" rel="ugc" href="https://www.patreon.com/t3278">https://www.patreon.com/t3278</a>-------------------------------------------------------------------------------------

t3(2.5D-ver2)

t3 ver-17 beta version (한글 설명은 아래 참고~)★ Please upload at least one photo made using the (civitai)t3 ver-17 beta model uploaded to CIVITAI to the gallery.This is my first upload after surgery ^^This model can use up to 30 cfg values,but I recommend 13~24.(30 may be a little strong.)It would be good to mix it with an appropriate roller.For reference, I haven't tested the roller ^0^For those with slightly low PC specifications, I'll do sd1.5 all the way~★ Member-only models are only available to sponsor members.Most of the pictures are being made during the production of the member-only models.You don't have to sponsor to appreciate them.You can just look at the pictures and leave~<a target="_blank" rel="ugc" href="https://www.patreon.com/t3278">https://www.patreon.com/t3278</a>--------------------------------------------------------------------------------------------t3 ver-17 beta 버전★ CIVITAI에 올린 (civitai)t3 ver-17 beta 모델을 사용해 만드신 사진을 1장 이상 갤러리에 올려주시면 감사하겠습니다.수술 끝나고 첫 업로드 입니다 ^^이번 모델은 cfg값을 최대 30까지 사용 가능하지만 13~24 정도를 추천 드려봅니다. (30은 살짝 강하게 나올 수 있습니다.)적당한 로라와 섞어서 쓰시면 좋을거 같습니다.참고로 로라 테스트는 안 해봤습니다 ^0^pc사양이 살짝 낮은 분들을 위해 할 수 있는데 까지 sd1.5는 쭉~★ 회원 전용모델은 후원 회원분들께만 공개하고 있습니다.회원 전용모델 제작 중 그림은 대부분 공개 하고 있습니다.감상은 후원 안해도 됩니다.그림만 보시고 가셔도 되요~<a target="_blank" rel="ugc" href="https://www.patreon.com/t3278">https://www.patreon.com/t3278</a>--------------------------------------------------------------------------------------------

(civitai)t3 ver-17 beta

t3xl test2 version (한글 설명은 아래~)★ Please upload at least one photo made using the t3xl test2 model uploaded to CIVITAI to the gallery.★ Member-only models are only available to sponsor members.Most of the pictures are being made public during the production of the member-only model.You don't have to support to appreciate it.You can just look at the pictures and leave~<a target="_blank" rel="ugc" href="https://www.patreon.com/t3278">https://www.patreon.com/t3278</a>----------------------------------------------------------------------------------------I uploaded a low-capacity sample image. I'm tired, so I'll upload it soon after setting it to high resolution.This is the second model. ^^I tested it with sd1.5 and sdxl settings, and it also works with pony settings.This version has strong color expression~----------------------------------------------------------------------------------------t3xl test2 버전★ CIVITAI에 올린 t3xl test2 모델을 사용해 만드신 사진을 1장 이상 갤러리에 올려주시면 감사하겠습니다.★ 회원 전용모델은 후원 회원분들께만 공개하고 있습니다.회원 전용모델 제작 중 그림은 대부분 공개 하고 있습니다.감상은 후원 안해도 됩니다.그림만 보시고 가셔도 되요~<a target="_blank" rel="ugc" href="https://www.patreon.com/t3278">https://www.patreon.com/t3278</a>---------------------------------------------------------------------------------------저용량 샘플 그림을 올렸습니다.피곤해서 조만간 고화질로 세팅해서 올려보겠습니다.두번째 모델 입니다. ^^역시 테스트는 sd1.5세팅과 sdxl세팅을 적용해 보았고 pony세팅도 먹습니다.이번 버젼은 색상 표현이 강한 버젼 입니다~

t3xl test2

t3 ver-16 version (한글 설명은 아래~)★ Please upload at least one photo made using the (civitai)t3 ver-16 model uploaded to CIVITAI to the gallery.★ Member-only models are only available to sponsor members.Most of the pictures are being made public during the production of the member-only model.You don't have to support to appreciate it.You can just look at the pictures and leave~<a target="_blank" rel="ugc" href="https://www.patreon.com/t3278">https://www.patreon.com/t3278</a>--------------------------------------------------------------------------------------------The upload model for CIVITAI is an appropriate model during the production of the member-only modeland uploaded as the official version of (civitai)t3 ver-16.I'm changing the graphic card guard to make it faster.In addition, I've started the sdxl model~ (Still a beginner ^^)I'm not feeling well, so I had surgery in August.I'll make a lot before the surgery and proceed slowly depending on my condition after the surgery.t3 ver-16 버전★ CIVITAI에 올린 (civitai)t3 ver-16 모델을 사용해 만드신 사진을 1장 이상 갤러리에 올려주시면 감사하겠습니다.★ 회원 전용모델은 후원 회원분들께만 공개하고 있습니다.회원 전용모델 제작 중 그림은 대부분 공개 하고 있습니다.감상은 후원 안해도 됩니다.그림만 보시고 가셔도 되요~<a target="_blank" rel="ugc" href="https://www.patreon.com/t3278">https://www.patreon.com/t3278</a>--------------------------------------------------------------------------------------------CIVITAI용 업로드 모델은 회원전용 모델 제작 중 적당한 모델을(civitai)t3 ver-16 정식버전 으로 업로드 합니다.그래픽 카드가드를 바꿔서 더 빠르게 만들고 있습니다.추가로 sdxl모델도 시작을 하였습니다~ (아직은 초보 ^^)제가 살짝 몸이 안좋아서 8월에 수술을 하게 되었습니다.수술 전에 많이 만들고 수술 후 컨디션에 따라 천천히 진행을할 예정입니다.--------------------------------------------------------------------------------------------

(civitai)t3 ver-16

t3 ver-15 version (한글 내용은 아래 확인)★ We would appreciate it if you could upload at least one photo made using the (civitai)t3 ver-15 model posted on CIVITAI to the gallery.(I will try to refer to the prom and setting.)-------------------------------------------------- ---------------------------The upload model for CIVITAI is an appropriate model created during member-only model production.Uploading as (civitai)t3 ver-15 official version.The graphics card is 1660, so it is very slow, but they also make an SDXL model.I'm watching. (It's so slow that I don't know if it will be completed.)-------------------------------------------------- ---------------------------★ The member-only model is only available to sponsoring members.Most of the pictures during the production of members-only models are made public.Sponsorship is not required for viewing.Please take a look at the picture~<a target="_blank" rel="ugc" href="https://www.patreon.com/t3278">https://www.patreon.com/t3278</a>t3 ver-15 버전★ CIVITAI에 올린 (civitai)t3 ver-15 모델을 사용해 만드신 사진을 1장 이상 갤러리에 올려주시면 감사하겠습니다.(프롬 및 세팅을 참고 하려고 합니다.)--------------------------------------------------------------------------------------------CIVITAI용 업로드 모델은 회원전용 모델 제작 중 적당한 모델을(civitai)t3 ver-15 정식버전 으로 업로드 합니다.그래픽 카드가 1660 이라 엄청 느리지만 sdxl모델도 만들어보고 있습니다. (너무 느려 완성이 될지는 모르겠습니다.) --------------------------------------------------------------------------------------------★ 회원 전용모델은 후원 회원분들께만 공개하고 있습니다.회원 전용모델 제작 중 그림은 대부분 공개 하고 있습니다.감상은 후원은 안해도 됩니다. 그림 구경 하시고 가세요~<a target="_blank" rel="ugc" href="https://www.patreon.com/t3278">https://www.patreon.com/t3278</a>

(civitai)t3 ver-15

t3 ver-15 beta version (한글 내용은 아래 확인)★ We would appreciate it if you could upload at least one photo made using the (civitai)t3 ver-15 beta model posted on CIVITAI to the gallery.(I will try to refer to the prom and setting.)-------------------------------------------------- ---------------------------Upload models for CIVITAI upload models that are eliminated during the production of members-only models.The other model is just better, it's not a bad model ^0^(civitai)t3 ver-15 The official version is expected to be released during the 4th production for members only.Also, I think I will have to focus on the members-only model for a while ^^-------------------------------------------------- ---------------------------★ The member-only model is only available to sponsoring members.Most of the pictures during the production of members-only models are made public.You don't have to donate to appreciate it, so please go and look at the paintings~<a target="_blank" rel="ugc" href="https://www.patreon.com/t3278">https://www.patreon.com/t3278</a>t3 ver-15 beta버전★ CIVITAI에 올린 (civitai)t3 ver-15 beta 모델을 사용해 만드신 사진을 1장 이상 갤러리에 올려주시면 감사하겠습니다.(프롬 및 세팅을 참고 하려고 합니다.)--------------------------------------------------------------------------------------------CIVITAI용 업로드 모델은 회원전용 모델 제작 중 탈락하는 모델을 업로드 하고 있습니다.다른 모델이 더 좋은거 뿐이지 안좋은 모델은 아니에요 ^0^(civitai)t3 ver-15 정식버전은 회원전용 4차 제작 중에 나올거 같습니다.또 한동안 회원전용 모델에 집중해야 겠네요 ^^--------------------------------------------------------------------------------------------★ 회원 전용모델은 후원 회원분들께만 공개하고 있습니다.회원 전용모델 제작 중 그림은 대부분 공개 하고 있습니다.감상은 후원 안해도 가능하니 그림 구경 하시고 가세요~<a target="_blank" rel="ugc" href="https://www.patreon.com/t3278">https://www.patreon.com/t3278</a>

(civitai)t3 ver-15 beta

This is the t3-14 version. (한글 내용은 아래 확인)For this model, we tried to make the skin feel and hand shape a little better than the previous model.Still, there's still a long way to go. I hope the next version comes out where you don't have to worry about things like your hands.While creating a member-only model, I am uploading one in the middle.It seems that working on models for CIVITAI will be difficult for the time being.We plan to focus on creating a membership model.※ The cfg value is okay below 13, and even up to 16 is reasonable.For reference, the picture comes out without any damage up to 18, but the expression is a bit excessive.I do it for you. I only use 30 sampling steps, but more than that.Testing is difficult due to poor PC specifications. ^^ insteadI would appreciate it if you could pull it out and attach the picture below.★ The member-only model is only available to sponsoring members.Most of the pictures during the production of members-only models are made public.You don't have to make a donation to appreciate the painting, so please go and look at the painting~<a target="_blank" rel="ugc" href="https://www.patreon.com/t3278">https://www.patreon.com/t3278</a>★ We would appreciate it if you could upload at least one photo made using the t3 ver14 model posted on CIVITAI to the gallery.(I will try to refer to the prom and setting.)이번 모델은 이전 모델에 피부 느낌과 손 모양이 조금 더 좋게나올 수 있도록 노력해 보았습니다.그래도 아직 멀었네요 손같은거 신경 안써도 되는 다음 버젼이 나왔으면 좋겠습니다~회원전용 모델을 제작하면서 중간에 한개 빼서 올려봅니다당분간 CIVITAI용 모델 작업은 힘들거 같습니다.회원모델을 집중해서 만들 예정 입니다.※ cfg값은 13아래가 무난하고 16까지도 적당히 나오네요참고로 18까지도 그림 깨짐 없이 나오는데 좀 과하게 표현을제가 해주네요 Sampling steps를 30만 사용하는데 그 이상테스트는 pc사양이 떨어져서 테스트가 힘듭니다. ^^ 대신뽑아서 그림을 아래 첨부 해주시면 감사하겠습니다.★ 회원 전용모델은 후원 회원분들께만 공개하고 있습니다.회원 전용모델 제작 중 그림은 대부분 공개 하고 있습니다.감상은 후원 안해도 가능하니 그림 구경 하시고 가세요~<a target="_blank" rel="ugc" href="https://www.patreon.com/t3278">https://www.patreon.com/t3278</a>★ CIVITAI에 올린 t3 ver14 모델을 사용해 만드신 사진을 1장 이상 갤러리에 올려주시면 감사하겠습니다.(프롬 및 세팅을 참고 하려고 합니다.)

t3 ver-14

This is the t3-14 beta-1 version.While producing the next version, we are opening an initial version.I plan to focus on being active in the member channel again for a while.★ The best-made model during production is only revealed to members who have sponsored through the sponsorship channel.Public paintings are available for viewing during production, so you can just look at the paintings before leaving.<a target="_blank" rel="ugc" href="https://www.patreon.com/t3278">https://www.patreon.com/t3278</a>★ We would appreciate it if you could upload at least one photo made using the t3 model posted on CIVITAI to the gallery.(I will try to refer to the prom and setting.)t3-14 베타-1 버전 입니다.다음버젼 제작 하면서 초기단계 버젼을 한개 오픈 합니다~다시 한동안은 집중해서 회원채널 에서 활동할 예정 입니다. ★ 제작 중 가장 잘 만들어진 모델은 후원 채널 에서 후원 해주신 회원분들께만 공개하고 있습니다.제작 중 공개 그림은 감상이 가능하니 그림만 구경 하시고 가셔도 됩니다.<a target="_blank" rel="ugc" href="https://www.patreon.com/t3278">https://www.patreon.com/t3278</a>★ CIVITAI에 올린 t3 공개한 모델을 사용해 만드신 사진을 1장 이상 갤러리에 올려주시면 감사하겠습니다.(프롬 및 세팅을 참고 하려고 합니다.)

t3 ver-14 beta-1

About this versionThis is t3-13 version.I plan to focus on being active in the member channel for a while. It's difficult to make it while going back and forth to both places. I'll stop by from time to time~★ The best-made model during production is only revealed to members who have sponsored through the sponsorship channel.Free members cannot receive the members-only model.Public paintings are available for viewing, so you can just look at them before leaving.(Free members cannot receive the members-only model.)<a target="_blank" rel="ugc" href="https://www.patreon.com/t3278">https://www.patreon.com/t3278</a>★ We would appreciate it if you could upload at least one photo made using the t3 model posted on CIVITAI to the gallery.(I will try to refer to the prom and setting.)~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~t3-13 버전입니다.한동안은 집중해서 회원채널 에서 활동할 예정 입니다. 2곳 다 왔다 갔다 하면서 만들기 에는 힘드네요 간간히 들리겠습니다~★ 제작 중 가장 잘 만들어진 모델은 후원 채널 에서 후원 해주신 회원분들께만 공개하고 있습니다.무료회원 분들은 회원전용 모델을 받으실 수 없습니다.공개 그림은 감상이 가능하니 그림만 구경 하시고 가셔도 됩니다.(무료회원 분들은 회원전용 모델을 받으실 수 없습니다.)<a target="_blank" rel="ugc" href="https://www.patreon.com/t3278">https://www.patreon.com/t3278</a>★ CIVITAI에 올린 t3 공개한 모델을 사용해 만드신 사진을 1장 이상 갤러리에 올려주시면 감사하겠습니다.(프롬 및 세팅을 참고 하려고 합니다.)

t3(ver-13)

This is t3-13 beta version.★ The best-made model during production is only revealed to members who have sponsored through the sponsorship channel.Free members cannot receive the members-only model.Public paintings are available for viewing, so you can just look at them before leaving.(Free members cannot receive the members-only model.)<a target="_blank" rel="ugc" href="https://www.patreon.com/t3278">https://www.patreon.com/t3278</a>★ We would appreciate it if you could upload at least one photo made using the t3 model posted on CIVITAI to the gallery.(I will try to refer to the prom and setting.)t3-13 베타 버전입니다.★ 제작 중 가장 잘 만들어진 모델은 후원 채널 에서 후원 해주신 회원분들께만 공개하고 있습니다. 무료회원 분들은 회원전용 모델을 받으실 수 없습니다.공개 그림은 감상이 가능하니 그림만 구경 하시고 가셔도 됩니다. (무료회원 분들은 회원전용 모델을 받으실 수 없습니다.)<a target="_blank" rel="ugc" href="https://www.patreon.com/t3278">https://www.patreon.com/t3278</a>★ CIVITAI에 올린 t3 공개한 모델을 사용해 만드신 사진을 1장 이상 갤러리에 올려주시면 감사하겠습니다.(프롬 및 세팅을 참고 하려고 합니다.)

t3(ver-13 beta)

About this version★ We are releasing undisclosed models in production and test pictures (including prom) for the next model to members. Thank you for your support~<a target="_blank" rel="ugc" href="https://www.patreon.com/t3278">https://www.patreon.com/t3278</a>★ We would appreciate it if you could upload at least one picture you created to the Gallery.If it was oriental before, is it western this time? It will have a completely different feel from the previous version.This model is a preparatory model for the next version.For the time being, I plan to release test pictures and test models to members only on my channel until the initial model for the next version is produced.It's free to view the test pictures, so please take a look and leave a comment ^0^The attached picture is a picture printed from Stable Diffusion 1.8.0.1. The characteristic is that picture deterioration rarely occurs when the cfg value is between 6 and 20.However, if it is high, certain parts may appear abnormal as the AI tries to make it more detailed.(The optimal threshold appears to be around 7 to 15. If you want to use a higher threshold, use Dynamic Thresholding. The setting method is in the description of the previous model.)2. Because my PC specifications are poor, I only tested Sampling steps 30. This model is in the preparation stage for the next version and has a unique feel, making it fun to draw. ^^3. I have not used Laura.Please test the use of Laura.Please make sure to draw a picture and attach it. If you upload various types of reference pictures, we can use them in the next model test, so I would appreciate it if you could upload the picture you made.4. Sampling method occasionally causes screen tearing in DPM++2M SDE.Other than that, I think a suitable picture comes out in all sampling methods.all sampling methods.

t3(ver-12-2)

★ We are releasing undisclosed beta models in production and test pictures (including prom) for the next model to members. Thank you for your support~<a target="_blank" rel="ugc" href="https://www.patreon.com/t3278">https://www.patreon.com/t3278</a>★ We would appreciate it if you could upload at least one picture you created to the Gallery.If it was oriental before, is it western this time? It will have a completely different feel from the previous version.1. This is the first version of t3 ver12.2. Please refer to the picture for settings3. We recommend using a cfg value of 13 or less.When using 13 or higher, use Dynamic Thresholding.If you use this article without reading it like some people do, the pictures will be overly expressive.It may come out.4. Personally recommended sampling:- DPM++ SDE Karras- Euler-Restart

t3(ver-12-1)

★ We are releasing undisclosed models in production and test pictures (including prom) for the next model to members. Thank you for your support~<a target="_blank" rel="ugc" href="https://www.patreon.com/t3278">https://www.patreon.com/t3278</a>★ We would appreciate it if you could upload at least one picture you created to the Gallery.If it was oriental before, is it western this time? It will have a completely different feel from the previous version.1. A Detailer is a sample picture drawn without adding anything.It pulls out well even without putting it in.2. Diet versions will not be added in the future. test results decreasedI feel like something is missing from the picture in this version compared to the full version.3. All settings are included as before.

t3(ver-11-2)

★ We are releasing undisclosed models in production and test pictures (including prom) for the next model to members. Thank you for your support~<a target="_blank" rel="ugc" href="https://www.patreon.com/t3278">https://www.patreon.com/t3278</a>★ We would appreciate it if you could upload at least one picture you created to the Gallery.If it was oriental before, is it western this time? It will have a completely different feel from the previous version.☆★☆★☆★☆★☆★☆★☆★☆★☆★☆★☆★☆★☆★☆★☆★While testing the next version, my PC suddenly became strange, so I checked and found that the graphics card was broken. It's so slow that I can't work.I don't think I can hold on as I keep pulling out tens of thousands of cards every day until dawn.I don't know when I will replace the graphics card.Maybe this version could be the last.Since I only watch YouTube on my PC, I made the model as a hobby, so I spent a lot of money on it.I don't think I will replace it.It's a shame something like this happened. It was really fun work.Stay healthy everyone~☆★☆★☆★☆★☆★☆★☆★☆★☆★☆★☆★☆★☆★☆★☆★There are two ver11 versions.I thought it was better than I thought so I divided it into two.The next t3 (ver-11-2) is also okay~ ^^ (I will post it after testing a little more.)First, try using t3 (ver-11-1)What I testedI think the cfg value is between 5 and 9.If you want to use 18~22, use Dynamic Thresholding.You know that you set it lower than the cfg value I applied, right?You can use ADetailer or not~ (Of course, it will look prettier if you use it, but it is slower~)The reference picture includes everything, so feel free to use it~

t3(ver-11-1)

The v11 official version is under testing and will be uploaded after more testing.This is the intermediate result of creating the official version.The v11 version comes out well even without using a detailer.More realistic now? Or is it less photo-realistic but has a lot of feel?Please be patient as we continue to test and create.Try the beta version first ^0^

t3(ver-11 beta)

While making t3 (ver11-beta), I felt like I used too much real-life, so I made a 2.5D version for the first time. I think 2.5D is more difficult than I thought because it's my first time making it, but it was fun. It is unclear whether the next version will be made. ^^

t3(2.5D-ver1)

happy new yearIt's a little late because I was editing various pictures.1. As a result of the test, this model produces reasonably good results.2. DPM++ SDE Karras was mainly used for sampling. (I would appreciate it if you could do something else and attach a picture.)3. We recommend a cfg value of 5 to 8.2. If you want to use it higher (15~23), use Dynamic Thresholding and you will get good results (try different settings ^^)4. In ADetailer, just adding a face is enough.5. Sampling steps from 10 to 30 are appropriate.

t3(ver-10)

t3(ver-10 beta)★☆★☆★☆★☆★☆★☆★☆★☆★☆★☆★☆★☆★☆★1. This version was designed to produce good pictures even at low sampling steps.2. Please refer to the reference picture (most of the reference pictures apply low Sampling steps. When using higher Sampling steps You will be able to create better pictures.)3. Useful pictures are created from sampling steps 5 or higher.CFG scale is recommended from 6 to 8.2. If the picture is broken above 9We recommend using Dynamic Thresholding. Set the value approximately “-1” lower than the sampling step you set. (Please make additional selections yourself ^o^)4. ADetailer produces a good picture with a face or hand. (I don't know because I haven't tested lora in use.)

t3(ver-10 beta)

t3(ver-09) final version1) Although the model has a large capacity, it can easily create good pictures.2) Please refer to the fromm and options in the sample picture and add a better fromm.Pick a lot of great pictures3) The next model has already been made in version 10, but I have made it a little moreI will draw a picture and reveal it later. (It will be much better)

t3(ver-09)

I haven't decided on a finished version yet, so I'll upload a test version first.▶▶ Stable Diffusion ver1.6 application settings ◀◀▶ These are the results of the actual picture test. After testing more than 10,000 pieces by changing the options below by 1, the best was selected. We will inform you after confirming the figure at which the picture will not be broken.▶ Sampling method recommendation ( ) is the CFG Scale application range. Euler(3~26), Euler a(3~22), DPM2 Karras(1~22), DPM++ 2M SDE Karras (3~25), DPM++ 3M SDE Karras (1~20) Heun(6~17), Restart(1~18), DPM++ 2S a Karras(1~17)▶ Hires. fix - Upscaler recommendation R-ESRGAN 4x+, ScuNET, ScuNET PSNR▶ Sampling steps: 20~40▶ Hires steps: 0~20 (no difference)▶ Upscale by: 1.5~2 (if your PC is good)▶ Denoising strength: 0.10~0.6 (no significant difference)▶ Use ADetailer unconditionally ▷ ADetailer model: No difference, use any one ▷ Only one face can be used for positive prom.▶ Two ways to set CFG Scale Method-1 ▷ Enable Dynamic Thresholding (x) ▷ CFG Scale: 4~7 (If you feel it's a bit strong, turn it down, if that's your style Turn on Enable Dynamic Thresholding and apply -1 above CFG Scale) Method-2 ▷ Enable Dynamic Thresholding (o) ▷ Mimic CFG Scale: -1 lower than CFG Scale ▷ Mimic Scale Scheduler: Cosine Up 1~3 ▷ CFG Scale Scheduler: Half Cosine Up 1~3 ▷ CFG Scale: 18~22▶ Set the rest as you wish. There may be cases where the picture appears strange due to changes in numerical values. So don't worry, instead, run a test and find out the setting range. Please note. Set the rest as you wish (Note: When using a detailer, around 0.1 to 0.5 is good. It doesn't matter if you don't use it.)

t3(ver-09 beta)

<ol><li>t3(ver-08)</li><li>Like a doll? Western style model</li><li>I will simply upgrade the version of the model name to be made in the future.</li></ol>

t3(ver-08)

<ol><li>t3xx3 (b09-ver3) 2nd model out of 9</li><li>t3 model integration + color correction 2nd (feels different from model 1)</li><li>Low-end PC models, high-end options available</li><li>Dynamic thresholds available</li><li>See prompts and setting values in some pictures.</li><li>test Using ddtailer</li></ol>

t3(b09-ver3-2)

<ol><li>t3xx3 (b09-ver3) 1st model out of 9 (3~4 to be released)</li><li>t3 model integration + color correction</li><li>Low-end PC models, high-end options available</li><li>Dynamic thresholds available (recommended 2-5)</li><li>See prompts and setting values in some pictures.</li></ol>

t3(b09-ver3-1)

<ol><li>t3xx3 (b09-ver3) prototype model</li><li>t3xx3 (b09-ver3) integrates only the parts I like from the models I have produced so far (it is unfinished, but one picture is uploaded and displayed at the top right of the picture)</li><li>Low-end PC models, high-end options available</li><li>Dynamic thresholds available</li><li>See prompts and setting values in some pictures.</li><li>The prom of the picture uses the prom left in the picture by other producers (lora X, Neger X)</li></ol>

t3xx3(b09-ver3) prototyp

<ol><li>Focus on expressing feelings in detail step 2 version</li><li>Low-spec PC models, high options available</li><li>Dynamic Thresholding available</li><li>See the prompts and setting values in some pictures.</li><li>5 models left for further testing</li><li>You can see the test process during production at the site below.( <a target="_blank" rel="ugc" href="https://arca.live/b/aimodelmaker">https://arca.live/b/aimodelmaker</a> )</li></ol>( This test picture is printed with the best option available in my house. )

t3xx3(b09-ver2)

<ol><li>Natural skin feel expression step 1 version</li><li>Low-spec PC models, high options available</li><li>See the prompts and setting values in some pictures.</li><li>1 in 8 models (of 7 tested)</li></ol>

t3xx3(b09-ver1)

t3(c1sz0.2)-1

<ol><li>Slightly dark color model</li><li>low spec pc model, rola ( x ), High quality not tested. (Please test and upload)</li><li>Refer to the prompt and setting value in the picture</li><li>Enable Dynamic Thresholding (CFG Scale Fix) Disabled Recommended(Need to adjust the number when using)</li></ol> 5. 1 out of 6 models

t3xx3(d09-pa0.2)

<ol><li>skin tone upgrade</li><li>Enable Dynamic Thresholding (CFG Scale Fix) Disabled Recommended(Need to adjust the number when using)</li><li>1 out of 8 models</li></ol>

t3(xx-v3-a0.12)

<ol><li>low spec pc model</li><li>rola ( x )</li><li>Refer to the prompt and setting value in the picture</li></ol>

t3xx3(b09)

Numerical correction for each part of the t3 model

t3(x3)

basic modelrora : koreandolllikenessV20_v20:0.4, pureerosface_v1:0.2