license: creativeml-openrail-m
datasets:
- Phantom-Artist/phantom-diffusion-s2-dataset
language:
- en
- ja
tags:
- art
Another 20 models that are trained over hakurei's Waifu Diffusion.
Each model was trained on a notable Japanese AI artist's works using dreambooth, with 30 of their works gained mainly from twitter (except for aibanousagi, which I could find only 23).
It tooks 1000 steps to train each model, at a learning rate of 5-e6. I have shared the notebook here in case you want to try out additional training.
Some are good at backgrounds, while others can generate a semi-realistic style as seen in many SD 1.5 anime/waifu models (and some might be a bit overfitted).
This time, some of them are also quite good at generating a certain style (just as the swingwings_style in the first 20).
The dataset is published here.
For those who are against generative AIs
You can see that now they are the target. Take our tool. Now is the time for pay back. Generate the images in their styles, and bring back the power you had to yourself.
For those who support the development of generative AIs
Some of the AI artists, even though they take advantage of the open strategy of Stable Diffusion, now tend to hide their prompts, trying to monopolize their style (I'm not saying the AI artists I trained are as such, to be sure).
To continue protecting our values and beliefs on the open community and fight against them trying to create another pre-modern style guilds, I will show you a new way.
You no longer need their prompts; just train their images by yourself to protect the open community. It's not only legal but also ethical, as they have been taking advantages of others' trained dataset.
For those who call themselves "phantom 20"
Note that these artists are IMO as interesting as you are.
Some of them were in the second because I had limited time before disclosing the first series, some are recommendation through a feedback, and others are those who I found out to be interesting enough to be on the list after having communication on the discord server.
ALL of them, however, are as interesting, with their specific styles, and I recommend you that you call yourselves "phantom 40."
Will I add more models?
No, at least, not with the speed I did in the first and the second series.
I think I have covered 90% of those who are notable and interesting, and I'm kind of tired to see people trying to be or pushing someone to be in the waiting list of the phantom series.
You can simply do it yourself. That's why I have that notebook left open.
trained artist list
- ALyo
- cfromi_icwit
- Defpoint
- getkomusen
- hemlok_ai
- Inakamono_AI
- kaideen_bird
- recommended additional neg: bird
- kenzenna_ifuru
- kuyoh
- kyo_do4
- recommended to remove neg: nsfw
- littoch
- recommended additional pos: crying/beautiful tears
- moto_ourt
- nakamurashippo
- recommended additional neg: wrong perspective, distorted buildings
- sai81685361
- recommended additional pos: loli, big round eyes, flat chest
- ShunkaCule
- The_Pioneer
- possible additional pos: CG
- waterman
- yamaneko_catfox
- possible additional pos: cat ears
- Yoshi_kake0712
- SA1P
samples
The basic prompt is as follows.
However, to present you the potential of these models as much as possible, many of them have additional postive tags (such as "in the style of") to get the result below (yes, use aitop (ARTIST)_style to gain the finetuned result).
Many works better with the additional prompt beautiful face. Generally speaking, prompting words close to the trained dataset will give you a better result.
POS: masterpiece, best quality, 1girl, aitop (ARTIST)_style
NEG: nsfw, worst quality, low quality, medium quality, deleted, lowres, bad anatomy, bad hands, text, error, missing fingers, extra digits, fewer digits, cropped, jpeg artifacts, signature, watermark, username, blurry, simple background
TO BE ADDED