Side quest with some AI-SLOP styles I’ve trained.Don’t expect quality or stability, this is super experimental and meant more as a support LoRA for mixing and using with artist tags. <s>as always i just bad at training, lol</s>You can check out my other styles <a target="_blank" rel="ugc" href="https://civarchive.com/models/1354064/not-hls-styles-wainoobai-experimental-garbage">here </a><s>Continuation of HL's AI styles series</s>

not HL's AI slop styles [experimental garbage]

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 <a target="_blank" rel="ugc" href="https://civitai.com/models/1721929?modelVersionId=1993766">previous version,</a> this time I didn’t make it for <a target="_blank" rel="ugc" href="https://civitai.com/models/1217645?modelVersionId=1980567">ΣΙΗ-2048b</a> but for <a target="_blank" rel="ugc" href="https://civitai.com/models/1217645?modelVersionId=1976509">ΣΙΗ-1.5</a>, fixed the “poisoned” iteration, and tweaked the weights a bit. Everything should be working fine now. I hope. Please. Help.I tested it on: <a target="_blank" rel="ugc" href="https://civitai.com/models/1217645?modelVersionId=1371790">ΣΙΗ</a>, <a target="_blank" rel="ugc" href="https://civitai.com/models/1217645?modelVersionId=1976509">ΣΙΗ-1.5</a>, <a target="_blank" rel="ugc" href="https://civitai.com/models/1217645?modelVersionId=1980567">ΣΙΗ-2048b</a>, and <a target="_blank" rel="ugc" href="https://civitai.com/models/833294/noobai-xl-nai-xl">NoobAI Vpred</a>. 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:<ol><li>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.</li><li>No trigger words needed - just load the LoRA and that’s it.</li><li>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.</li><li>I’ve barely tested compatibility with other LoRAs, so I can’t guarantee stability. Need to test.</li><li>I made a few comparisons - you can check them here: <a target="_blank" rel="ugc" href="https://civitai.com/posts/19416077">ΣΙΗ-1.5/ΣΙΗ-2048b</a> and <a target="_blank" rel="ugc" href="https://civitai.com/posts/19417365">NAI VPRED</a> and <a target="_blank" rel="ugc" href="https://civitai.com/posts/19439949">ΣΙΗ-2048b</a></li><li>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.</li><li><s>And yeah, good luck using this shit!</s></li></ol>&lt;3

SihMerge.safetensors

ΣML - ΣΙΗ Merge Lora

ΣML [ARCHIVED]

PSAIX

TMAIX

About this versionDISCLAIMER: 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 <a target="_blank" rel="ugc" href="https://civitai.com/models/1721929?modelVersionId=1993766">previous version,</a> this time I didn’t make it for <a target="_blank" rel="ugc" href="https://civitai.com/models/1217645?modelVersionId=1980567">ΣΙΗ-2048b</a> but for <a target="_blank" rel="ugc" href="https://civitai.com/models/1217645?modelVersionId=1976509">ΣΙΗ-1.5</a>, fixed the “poisoned” iteration, and tweaked the weights a bit. Everything should be working fine now. I hope. Please. Help.I tested it on: <a target="_blank" rel="ugc" href="https://civitai.com/models/1217645?modelVersionId=1371790">ΣΙΗ</a>, <a target="_blank" rel="ugc" href="https://civitai.com/models/1217645?modelVersionId=1976509">ΣΙΗ-1.5</a>, <a target="_blank" rel="ugc" href="https://civitai.com/models/1217645?modelVersionId=1980567">ΣΙΗ-2048b</a>, and <a target="_blank" rel="ugc" href="https://civitai.com/models/833294/noobai-xl-nai-xl">NoobAI Vpred</a>. 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:<ol><li>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.</li><li>No trigger words needed - just load the LoRA and that’s it.</li><li>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.</li><li>I’ve barely tested compatibility with other LoRAs, so I can’t guarantee stability. Need to test.</li><li>I made a few comparisons - you can check them here: <a target="_blank" rel="ugc" href="https://civitai.com/posts/19416077">ΣΙΗ-1.5/ΣΙΗ-2048b</a> and <a target="_blank" rel="ugc" href="https://civitai.com/posts/19417365">NAI VPRED</a> and <a target="_blank" rel="ugc" href="https://civitai.com/posts/19439949">ΣΙΗ-2048b</a></li><li>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.</li></ol>

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:

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.

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

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.

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

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

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.

Files with SHA256: ff9ab7f9120777ec9f5244ea60c7b100b0e8e38768e1e2d518f6a8e297cf2771