A tool to speed up your concept workflow, not to replace it. Added an SDXL UPDATE. As someone with a design degree, I'm constantly trying to think of things on fly and I can't - I just can't, and clearly these won't REPLACE the process - and while a LOT OF MODELS CAN DO THIS without it - I figured adding a LORA wouldn't hurt.
SHOP FOR BADGES HERE!
Designed by Ktiseos Nyx.
We've been at this since January of 2023! If you're interested in supporting us in our long standing AI journey please scroll down for ways to connect & sponsor us! Currently if you're interested in having it on the generator please feel free to donate towards auction costs!
✨ Recommended Settings
To get the best out of ANY of our models, try these settings:
Samplers: Euler or Euler Ancestral *(SDXL) - Or your preferred DPM style for SD 1.5 - We don't have settings for Flux as we don't gen flux off Civitai just yet!
Scheduler: Karras
Negative Prompt: Generally not needed! The model is designed to perform well without one, but feel free to experiment based on your preferences.
HiRes Fix:
Steps: 15
Denoise: 0.3
Upscale: 2x
Upscalers: Rex, 4x_Remacri, Lollypop or your personal favorite.
ADetailer: Use sparingly. Due to potential VAE differences, it might occasionally produce grey squares.
Embeddings: We've used some of our own custom embeddings to showcase character types in our examples, but no stylistic embeddings were necessary to achieve the core look.
Checkpoint Compatibility: Depends, not everything will behave.
🛠️ Training Details
If you're curious about what's the training details in full make sure to use this tool: https://xypher7.github.io/lora-metadata-viewer/
🙏 Acknowledgements
A huge thank you to the incredible community members whose work and inspiration contribute so much. Special mentions to:
Arthemy, Wai, Holostrawberry, FallenIncursio, RichyRich, JustTNP, Hoseki, CitronLegacy, Samael1976, Kairen92, ShadowxArt, Flyx3, YeiYeiart, LazyVisionary, and so many more! We try to train as much as we can ourselves, but the community's creativity is a constant source of inspiration.
🌟 About Ktiseos Nyx & Connect With Us!
Ktiseos Nyx is available for commissions! Find us and more of our creations here:
Discord: https://discord.gg/HhBSvM9gBY
Our Other Socials: https://beacons.ai/duskfallcrew
Sponsor Models & Commissions: https://ko-fi.com/duskfallcrew/commissions
TensorArt Space: https://tensor.art/u/611011406535381539
Dataset Tools: https://github.com/Ktiseos-Nyx/Dataset-Tools
💵 Training Costs Money!
While Civitai style trains usually cost buzz, testing and infrastructure to create better quality content to service our customers long term does cost money.
We're not looking to be the next Civitai at all, but AI has been a format of income outside of the inability to find regular work.
Donations, Commissions and Sponsorships are the backbone of our work!
Buzz donations work to keep our models on the generator that YOU the user choose! (This was originally a rarity, buy recently you've all chosen and we're all proud!)
Lora training can take time and effort, and while we do have cost layouts - if you're wanting a simple character lora you can use the Ko-Fi link shown in our link In Bio Above!
✨ Commission Details
If you're wondering why you're seeing a style lora or other loras ahead of your queue'd training or commission please see these FAQ lines:
Style Loras are usually developed independent of our normal training queues at the moment, as we use Civitai's platform to train them for use with our normal model making schedule during the month.
Character loras normally are trained as they come in, these semi depend on our own training service we've developed. Right now the NextJS system is almost complete for testing, and we will be resuming PAID and Free queues ASAP.
Concepts that are CLOSE to "STYLES" are again created using Civitai, at least on the short term. Once our main service has been completed we will amp up our schedule.
Description
FAQ
Comments (17)
Interesting idea! I like it. I have no use for it... but as someone who once had a use for something like it, it's something I definitely would have liked to have.
Considering that I graduated in 2019 and if allowed this would have made concepting shit so much easier, especially when yo uwant to concept your OWN ideas rather than print somene else's shit lo.
@duskfallcrew Yeah, no question. The benefits are immediately apparent, and those who would refuse to recognize that are, simply, unreasonable. And afaik, there's nothing else out there that could replace this. Humans get creative blocks and can't keep churning out one idea after another like—well, like an AI.
@dita Designers are more fluid about AI than artists are lmao. Designers are the trolls of the artworld, and we tend to distaste art activists UNLESS they have a decent reason (P*SSY Riot etc -- like Stuart Semple is just barf to me )
@duskfallcrew Makes sense. More pragmatic. That sort of goes along with design being an applied art, and fine art being art qua art.
I am ui/ux designer, I hope the perfect AI will be coming soon, your cover images could see brief functions/layout, although it can not be used for prototypes...
It's probably beacuse i'm VERY ADHD with my data, and A lot of it literally is that I'm used to making anime;comic stuff XD - I may re do this in future!
@duskfallcrew I think it is soon to see the perfect one.
BTW, from your cover images, I think your dataset is great, but need to classfication for different components, because each components have independent commons. and tags maybe need clarify details : filleted corner, device types, icon，even components.
@Cecily_cc Yea, I just sort of threw it in and forgot that like Anime it needs more detail, more description :)
It's great to see such a model, although it can't be applied very well at the moment, it can still provide some inspiration
Well here's to me learning to do better then! I've never been great at UI/UX outside of old school websites - so I sort of liken this to my journey of giving back to the design community for allowing me to graduate XD
Interesting tool to explore ui interaction with other themed loras.
It's not a perfect train, 😔 it's just the 1.5 data I had, but it works much better on Sdxl
anyone have an idea what was good negative prompt of this model
Nope, it's quite random xD I'm not sure i'll update it until SD3 comes around and i can focus the dataset
I gotta say...this lora is shockingly fun to play with.
Really love the concept, it was an awesome idea.
Lowkey cool tbhh
Details
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.