Sign In

Pony No Score v7 Update on October 16, 2024

Pony No Score v7 Update on October 16, 2024

The first thing I want to say is thank you for everyone's support of my open-source projects so far. Without your help, it would have been hard for me to continue working on these open-source projects. Honestly, during the process of making this model, I came close to bankruptcy many times. Just creating captions and training took an entire month, not to mention the time spent gathering data. I practically forgot to eat or sleep, from morning to night, just glued to my PC screen. Civitai’s withdrawal issues have left me with no income for almost three months now, one of my main sources of revenue, which left me with only $200 in early October. Fortunately, Astraliteheart supported me with an additional $200, allowing me to keep going and complete this model.

There were many times when I wondered if I should make this model exclusive. My only job is training open-source models for the community, and right now, I’m running out of energy to keep this fire burning. But in the end, I felt that I could still push forward, so I decided not to do that. I want my brainchild to reach more people, and besides, Civitai’s early access feature will help cover some of the costs of training the model. But I still have a Ko-fi link. If anyone feels that my work deserves support, don’t hesitate to throw money my way. I would be incredibly grateful for that LOL, it would enable me to continue future open-source projects.

https://ko-fi.com/duchaiten

Back to the main topic:

Once again, for those who haven't read what I posted when releasing Pony No Score V7:

https://civitai.com/models/376450

Pony No Score v7 is a groundbreaking version that unlocks enormous potential for Pony, marking the largest update to date. V7 integrates 55 styles into one model, each with separate trigger keywords, similar to how Pony previously added scores to the model. The goal is to create a model capable of producing a wide variety of artistic styles, rather than being limited to just a few that are difficult to control. Users can apply individual styles or combine different styles to create their own completely unique artistic vision. Once you hide your prompt and data, no one will know which style keywords you combined to craft such a distinct look—it will be uniquely yours.

Using the model is very simple, like the scores, but also not like the scores. The idea behind it is training based on various artistic styles of different artists and some unique AI models, arranging them into separate keywords (perhaps I should have made them numerical codes like score_1234 in Pony base, such as style_123—maybe next time I’ll do that). Each keyword corresponds to a different style, representing an artist or a uniquely special AI style. Users can call up just one keyword to bring out that style, but that’s not the main intention. What I aim for are unique style combinations. You can call up multiple styles at once, for example: A, B, C, or B, C, A, or C, A, B.

Any change in the keywords or the order of the keywords will result in different outcomes. You can even use parentheses like (A) or (A:1.2) to increase or decrease the weight of a keyword. This combination and arrangement will turn the initial 55 styles into hundreds or thousands of different styles, and as long as you don’t reveal your style combinations and keywords, it will be a one-of-a-kind creation unique to you. That was my original intention when creating this project.

Honestly, after completing this model, I still see several mistakes and feel not fully satisfied with the results. I believe that if I started over again, I could achieve an even better outcome. But redoing everything would take too much time, and I don’t have enough money to continue wasting resources. Perhaps I’ll have to wait for the next version, where I’ll expand from 55 styles to 100 styles.

OK, here is the complete list of 55 styles:

Arcane

ttguweiz

carmesjocelin

fiz-rot

anninosj

samdoesarts

elliemaplefox

sei5osuzuki

BM94199

yaoyao794

sea_Pall

Vergilhoo

hamukukka

omao_51061954

letsfinalanswer

106858

sungmoomoo

hakwansoo36

wonbin_lee

hex_jjung

Ghibli

niji3d

Hoovesart

cutesexyrobutts

afrobull

unfairr

Khyle

shexyo

Sinozick

ironlilyart

mossacannibalis

gabrielpicolo

Rossdraws

Kuvshinov_Ilya

RDJlock

wlopwangling

beitemian

strauzek

RyanReos

hdfurrybabes

Apone3D

wildeerstudio

AkiyamaRyo

fugtrup

crazytown

748cm

ArawAraw

stevencarson

rescraft

aromasensei

ponyvid

ponycos

ghost236
7200ss
lizchiefffff

Sorry, I’ll keep a bit of a secret about what styles these keywords represent and how to combine them. I want users to experiment and discover their own methods—that’s how you create a sense of fun and achievement, right?

44

Comments