💡 Version 1 - first version of this series
Model Series: (zca series)
Version: v1 (zca1.4.0)
Created on: ~December/17/24ℹ Notice - Do not reprint this model. This model can be merged and shared, however derivatives cannot be used for commercial purposes (generative services, commissioned models, SeaArt, PixAI, etc.)
Info
A blind-merged model (not tested in-between merges) based on existing Illustrious/Noobai merges. A more dynamic or creative model in some regards in comparison to Auronami. As well as a sharper/cleaner semi-realistic styling in some cases. I've enjoyed the more dynamic images, especially with horizontal landscape orientations.
view more on Hugging Face
Recommended Use
See example images.
Euler, Euler a, or DDPM, etc. ~2-6 cfg, ~28 steps
This model is very flexible in these ranges, prompt depending of course. Use the parameters you find best for your prompt and application.
Hires fix/passes may nerf some shadows/lighting/details depending, or add ones that aren't wanted - but can shape things up further. This is optional of course, and I recommend adjusting any use to your context and application. The example images utilize this both on and off.
Disclaimer
This model(s) may output NSFW content unintentionally depending on parameters used. Make sure you tailor your prompts accordingly. For example "nsfw" in the negative prompt.
The purpose of sharing this model is not to showcase obscene material in a public forum. The use of this learning model is entirely at the discretion of the user, and they have the freedom to choose whether or not to create SFW or NSFW content. The decision of whether to engage with SFW or NSFW content lies with the user and their own personal preferences. The AI model(s) do not contain explicit visual content that can be accessed easily.Resources
This model used the following resources - all of these are great themselves, props to each creator.
v1
LIO1.2.0
ZukiCuteIllustrious_v2 (via ZU_KI)
NTRMix_v777 (via tkio)
naiXLmmmMix_v3 (via xiaofan941297)
NovaUnrealXL_v2 (via Crody)
AI Styles Dump (low weight, via bakariso)
License & Use
SDXL - CreativeML Open RAIL++-M
Illustrious - https://freedevproject.org/faipl-1.0-sd/
NoobAI-XL - https://civarchive.com/models/license/1140829
Terms of use
- You are solely responsible for any legal liability resulting from unethical use of this model(s)
- If you use any of these models for merging, please state what steps you took to do so and clearly indicate where modifications have been made.Note
If you see any conflicts or corrections to be made, please let me know.Description
Sierunami v1
FAQ
Comments (4)
Definitely creative. I uploaded a new image with a more dynamic pose but some sliiiight mistakes (ribbon appearing over the sword). For T2I it's a very good starting point and it's inpaintable anyway.
Neat image, hires fix/upscaling or like you said inpainting or simple manual fix would remedy that yeah.
I've typically ran a hires fix pass through an image, see which I prefer and/or modify the noise values. Then do any manual touch ups I might want to do etc. and then finally do an upscaling with sd upscale at low values as long as there isn't too drastic of detail/texture loss. Sometimes I'll modify the prompt or use a different model for upscaling too. I also at times do multiple upscales and merge the images.
Mind you though, none of the images on these models were edited or upscaled. A few of them use hires variants however, thus the different image sizes.
@Ocean3Â Oh wow the Img2img 50% upscale looks so much sharper and fixes the issue
Really like the soft style of this model, as well as how good it can interpret prompts. Thank you so much!
Details
Available On (2 platforms)
Same model published on other platforms. May have additional downloads or version variants.