Tensor.Art
Create

not HL's AI slop styles [experimental garbage] - PSAIX

not HL's AI slop styles [experimental garbage]

LORA
Reprint

Updated:

ΣΙΗ Merge
PSAIX
ΣML [ARCHIEVED]
not HL's AI slop styles [experimental garbage] by EDICT on Tensor.Art
not HL's AI slop styles [experimental garbage] by EDICT on Tensor.Art
not HL's AI slop styles [experimental garbage] by EDICT on Tensor.Art
not HL's AI slop styles [experimental garbage] by EDICT on Tensor.Art
not HL's AI slop styles [experimental garbage] by EDICT on Tensor.Art

About this version

DISCLAIMER: This isn’t a trained LoRA - it’s a Schizo-Merge made from my own LoRAs and the sum of differences between ΣΙΗ and NAI VPRED.

After another fail, I think I finally managed to make this LoRA stable enough for use. Unlike the previous version, this time I didn’t make it for ΣΙΗ-2048b but for ΣΙΗ-1.5, fixed the “poisoned” iteration, and tweaked the weights a bit. Everything should be working fine now. I hope. Please. Help.

I tested it on: ΣΙΗ, ΣΙΗ-1.5, ΣΙΗ-2048b, and NoobAI Vpred. It should work fine on these models. However, it doesn’t perform perfect on ΣΙΗ-2048 as I’d like. Maybe I’ll release a separate version for that model later if needed.

And yes, I created this style mostly for myself and my own workflow, so I can’t guarantee it’ll be stable for you. Test it out, hehe.

Anyway, the recommendations are still the same:

  1. Weight between 0.5 and 1. I suggest starting at 0.85-0.9 and adjusting up or down. Unlike the previous version, at 0.8-0.9, characters shouldn’t lose their details, but who knows. Test and see.

  2. No trigger words needed - just load the LoRA and that’s it.

  3. Artist tags are a must. The default style isn’t that strong, so I’m not sure it can stand alone as its own style. It’s more of a direction for a style rather than a style itself.

  4. I’ve barely tested compatibility with other LoRAs, so I can’t guarantee stability. Need to test.

  5. I made a few comparisons - you can check them here: ΣΙΗ-1.5/ΣΙΗ-2048b and NAI VPRED and ΣΙΗ-2048b

  6. Well, Someone told me that this merge doesn’t work on Forge (I’m guessing because of the method I use to mix the LoRAs).

    I tested it on ReForge and ComfyUI, and it should work fine there. I don’t have any other UIs to try it on.

Version Detail

Illustrious
This version is super experimental, since I didn’t train it from scratch but merged A LOT of my own LoRAs together. Some of them I’ve published before, and some I never shared publicly. These models were pretty unstable, so I can’t fully guarantee how this LoRA will behave lol. But! I had so much fun working on this LoRA. The style combos turn out quite interesting, so I’m publishing it anyway. Maybe someone else will like it too. (AND I SPENT FIVE HOURS TRYING TO MAKE IT, ARGH)… yeah, I did enjoy the process… T_T Sometimes there might be minor issues with eyes or hands, but it’s usually easy to fix with inpainting or Adetailer or just by using a different seed. RECOMMENDATIONS: Weight from 0.5 to 1. I’d suggest starting around 0.85 and then adjusting up or down depending on the effect you want. Feel free to combine it with other LoRAs and artist tags for cool combinations. But it also works quite well as a standalone style. There’s no specific trigger word, but you can try tags like: “textured painterly sketch” “realistic” “messy rough sketch” “abstract, abstract background” You don’t have to use all of them at once. This LoRA inherited a gritty vibe from some of my other LoRAs, so if you see too much noise, try putting “film grain” in the negative prompt. That helps me. Originally, I made it for WAI, but it also works (though a bit differently) on NoobAI merges. I tested it on WAI 14/12, ΣΙΗ, and VPRED version of NoobAI, so it should be fine. Check how it performs on other merges too, and share your results I’d love to see the differences from merge to merge :D

Project Permissions

Model reprinted from : https://civitai.com/models/1721929/not-hls-ai-slop-styles-experimental-garbage

Reprinted models are for communication and learning purposes only, not for commercial use. Original authors can contact us to transfer the models through our Discord channel --- #claim-models.

Related Posts