I pick up some environment art from Pangya fantasy golf and use AI to change them into a different look.
Original
Retro Futurism
Saturated Space
Wasteland
Wind Hill
Original
Retro Futurism
Saturated Space
Wasteland
Deep Inferno
Original
Retro Futurism
Saturated Space
Wasteland
All of these were made in playgroundai.com
The use of AI might soon become useful for creating new art to be used by the private servers, e.g. in the launcher or main menu banners. There’s of course still a lot of development to be done until it will be possible to generate faithful reproductions of all the characters or courses, but what we have now is already promising. I’d love to see an AI art generator trained on Seedark’s art style, for example.
I have done some attempts at rendering some of Pangya’s characters using Nemusona’s Waifu generator, which has been suggested to me by an user on Debug Pangya’s Discord channel: https://waifus.nemusona.com/ Among all the characters I have tried to render, I have managed to get decent results only with Kooh, for all the others I believe a very precise physical description will be required to be used in the prompts. All the models I have used have troubles correctly rendering a golf club, it was always drawn as bent, too short or strange looking, so at some point I gave up. This is the best result I got after ~50 tries:
If anyone is curious to try it by himself, here are the prompts I have used:
Positive prompts: (golf course), (flat chested), (long black hair), (petite), (twintails), (red eyes), (tight all black leather jacket), (tight all black leather trousers)
Negative prompts: hat
Model: Anything V4.5
CFG scale: default (10)
Denoise strength: default (.5)
I recommend to use it on morning time (UTC) during the week before 12.30, when it’s much less crowded.
Varthall
I love the Kooh artwork that came out. Though her right index finger looks like it was glued in.
I guess the model was attempting to render her hand holding a club, judging also by the position of her arm. Her left ponytail also looks like it’s midways shifted towards her left elbow. Unfortunately there were always errors like this on every render, though I have stumbled upon some prompts that might help fixing this. I’ll try adding them from now on, although I’m not sure if they have any impact:
Positive prompts: high detail, highly detailed, hyper realistic, intricate, intricate sharp details.
Negative prompts: lowres, bad hands, error, missing fingers, extra digit, fewer digits, cropped, low quality
EDIT: unfortunately they don’t, plus the “golf course” tag seems to be left out most of the times. Better to use fewer prompts I guess.
Varthall
Looks like someone is trying to generate new images using AI trained on SeeDark’s style… still needs some tweaking, but it’s a starting point.
Varthall
Oh my god, I don’t believe it with my own eyes! This is incredible!
I was thinking I might try to train LoRAs for StableDiffusion based on Kooh, Hana, Spika etc and try to generate new art of them. I like combining AI with my own moderate artistic talent to create stuff.
I guess I’ll try making some LoRAs this week and then see if they play well with the SeeDark LoRA.
I’m really looking forward for your creations, please post them here once they’ll be ready. Unfortunately I don’t have neither a powerful HW nor artistic talent, but I have uploaded the model on SeaArt (https://www.seaart.ai), as soon as it will be reviewed I’ll start making experiments with it.
Varthall
So far I’ve worked on a Kooh LoRA. It gets her overall look (twintails, red eyes, tends to be black hair) right, but it’s not quite right on the overall feel - and it easily blows out the style and looks funky. I’ll need to work on the dataset and training settings more. I foresee Hana and Spika and Lucia posing a greater challenge as there’s less to work with…
Keep it up man. I hope to see more Pangya character LoRAs in the future. Hopefully we can see them in different art styles.
Nice, keep up the good work! I’m wondering if the model includes tags for each character, so that you can use their name in the prompts without the need to describe them. Also, I’m afraid the model hasn’t been trained on Spika, since she was introduced 3 years after SeeD’s passing. Still no news from SeaArt, the model is still under review, no idea when it will be ready for use. For us without a powerful HW setup, SeaArt unfortunately seems to be the only free service which offers the option to upload new models.
Varthall
A new LoRA has been published on Civitai, featuring Arin:
Some of the example images are really gorgeous!
Hopefully more characters will be available in the future, though unfortunately it seems there won’t be for Lucia, Hana or the newer Erika because of lack of source images 
Varthall
This is really cool.
A different Arin model, somewhat more realistic, which was released some months ago but for some reason it has slipped under my radar:
So far my favourite still remains the newer model by Hoseki.
Varthall
In the meanwhile, Obliqeray has updated his SeeDark LoRA, now at v11, this time trained with NAI with better results:
Here are some examples, using CalicoMix’ checkpoints. Unfortunately there are still issue properly rendering a golf ball and club, but still it looks great.
Varthall
User Markwar has used Featureless Mix, I’m still undecided if this style or CalicoMix’ one is closer to SeeDark’s one, probably they are on par.
The best news is that Civitai now has included a free AI generator on its site, making it possible to generate new artwork directly form the website! I’ll see if I’ll manage to make some decent images out of it. For some reason, Civitai seems to only allow CalicoMix as model, not Featureless Mix. I recommend to generate 10 images at ones, since a lot of cherry picking among the results will be required.
Varthall
