💡 Version 1 - first version of this series

Model Series: (LIO series)
Version: v1 (LIO4.0.0)
Created on: ~December/13/24

ℹ 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

An illustrious/noobaixl based series that has been merged and tested on and off over the course of a few months. Results aren't quite the same as before lora were merged (vs model + lora), however are fairly adequate for now. The model should retain decent relevance to artist/character recognition from any of the merge parts.

view more on Hugging Face

Recommended Use

See example images.

Euler or Euler a, ~3-6 cfg, ~28 steps

Euler, 5 cfg, 28 steps is a good starting point

'Euler a' may do characters better. Depending on prompt/prompt values (etc.) you may find blank image issues with 'Euler' at lower cfg scales.

Hires fix/passes may nerf some shadows/lighting depending, and possibly details - 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. In the past, I typically stayed away from artist specific loras/models as to not mimic any particular style/artist. I've incorporated some into this mix at low weight values (similar to other loras). This is due to just what was on hand/new list and what I was playing around with at the time. I appreciate all and any artists' works involved in the creation of these models.

v1

• LIO1.2.0 (detailed recipe may go up on a Hugging Face page in the future)

• AI Styles Dump (low weight, via bakariso)

• Konya Karasue (correct one iirc, low weight, via Y_X)

• Lamentable (med weight, via DunkingOnSoul)

• 748cm (low weight, via AkioAI)

• ATNR Style (low weight, via RIM0)

• USNR Style (low weight, via RIM0)

• Chooine Style (low weight, removed)

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.