|
|||
 Man the lighting for this one wound up being really tricky for some reason. I'm sure I've messed up with the shading and lighting but overall I like where it ended up.
Little Sister excitedly grabs the collar waiting for Big Sister to finish changing. She has a few bullies down in the village she'd like to introduce to her Big Sister. The High Res files are up for Copper Tier Patrons and above as well as the original .PSD for Gold Tier Members!
0 Comments
 Progress with this has been slower than I'd like... like usual. X0
Been experimenting with a new AI art generator I recently discovered called Promptchan. Its a paid for service where the niche they chose to focus on is that its... 1- A much more simplified Stable Diffusion tool set that's easy to pick up and start using. 2- Is mostly uncensored. Save for content that's illegal in most places around the world. It's using an in house compiled model that is much better than the typical service like these I've seen pop up with much more reasonable prices. Now mind you its by a very small team of 3 devs, So updates are a bit on the slow side, but they've been very open about utilizing the feedback from customers in their discord server. It has plenty of growing pains yes, but thanks to the way they've set things up its far easier to get a decent image generated even if it ends up not being very close to the mark of what you wanted. I experimented with Automatic 1111 for a good while and wasn't ever able to ever get it to produce anything even half as good as Midjourney's worst. Here I'm able to get right decent results though I find its model while great at doing pinups, struggles a bit more with more out there concepts... such as those I've been trying to get it to do... mainly female werewolves. XD They've been making steady progress though for how small their team is, and with SD having recently released some very powerful next gen tools available to the public for free I have high hopes that they will be able to continue to advance their service and make something that can eventually rival even MJ. Even while using the equivalent of older tech AI wise they've already put together something that easily fills in the gaps that MJ has purposely ignored the needs of from their customer base. I used it in this drawing tho not quite in the way you would think. Nothing in this image so far is directly made by an AI, but I did feed in progress I made along the way to see how well it could recognize the subject material and how it could be enhanced. That lead me to being able to identify several major anatomical mistakes that I was able to work back in to the ongoing work and making it far more appealing than it would have otherwise. I'm sure it will be able to help guide my process with the shading too. I'll post an example in a bit of ways it can be used by aspiring artists outside of letting the AI do all the work.  Inks are coming along nicely. I might change up the girl in the background again, Still not quite feeling her yet. The chest on the big shewolf is still an item of concern at the moment.
Still gotta decide if this is her sister or mom.  Not quite sure about the girls pose just yet.
Face feels off still and not sure if she shouldn't be more in that exterior hall. Will have that space be were the main light source is coming from casting long shadows. Wanted the shewolf to take up more of the space but then I'd have to crop large parts of her body off and there would be nowhere to put the girl were she would look right. Mebbe I'll zoom it all in a bit closer before inking tho not sure yet. I could scrap the scared girl aspect and have her just be all creepy about it. Oh yeah mebe shes holding a spiked collar and a chain leash. Like she's bout to take her sister out to get back at some people. That would read more interesting I think story telling wise. What do you think though?  Not sure if I'll take this to full illustration just yet, but just felt like doing another mid transformation shewolf.
Always love the first 15% and final 70% of the process most.  This piece was inspired by some AI results.
I'd thought up this simple moment of Orphan getting licked by one of the Daughters of the Fangs Brides. But it wound up helping to add a lot of connective tissue to various small moments and scenes I had in mind that will greatly help in fleshing out some powerful moments deeper into the series. I'd thought it would be fun if the girl licking Orphan winds up going Bleeck! She tastes like soap. ~ o~ Which would call back to a funny moment I wanted to do where RRH Standard gets sick of the smell of wet dog, and dunks Orphan into a pond and scrubs her down with a bar of soap leaving her comedically traumatized. With this new moment though I thought it could be really cool if the trio ends up going looking for Orphan later tracking her down by her scent. only to stumble upon Standard and Prisoner instead and freak out fleeing. Leading to the realization that the Fang hunters have been tracking the trio down via the scent of Standards Soap. Leading to them being able to turn the table on a major trap set for them taking out their pursuers. This will also be a moment that leads to one of the trio mentioning how Orphan looks just like the goddess they pray to of Queen Lupina the first of the werewolves in their world. This will lead to even more crazy revelations deeper into the story. It was such a small moment but its helped to pay off so many unique moments and set up others. I'm quite happy with it. ^o ^ The Super High Res file is available for Copper Tier Patrons with the original .PSD available to Gold Tier Members. (For learning purposes only please) :p  The journey to learning how to create the ideal Female Werewolf with A.I. has been a pretty chaotic one. Stable Diffusion has proven to overall be a wash for me, with how unintuitive its systems are. At some point I'd like to attempt to train a model for werewolves on it with my better results elsewhere but for now I feel I'm starting to get close with Midjourney... and I'd likely have succeeded already if not for the dam censorship. Either way I'm starting to find some fun poses that react well to some of the better models I've created so far as inputs. Which as been no easy task with most of my input attempts being blocked for censorship. Decided to draw over one I liked the energy of below adding my own unique style to it. Cant ever just use the base 1 for 1 due to how inaccurate the anatomy often is, but is pretty good as a general guideline to follow. I'll be posting the better of my results to a new page under the concept art section. Some of them make for very nice inputs tho most are blocked by the system. ;0 Not sure if i'll take this pic to completion yet but so far its a fun pose. Tell me what you think. ^_ ^
|
|
RSS Feed
