not HL's AI slop styles [experimental garbage] - PSAIX
Prompts recommandés
1girl, looking at viewer, simple background, <lora:PSAIX_MERGE:1>, masterpiece, best quality, amazing quality, very aesthetic, highres
Prompts négatifs recommandés
lowres, displeasing, very displeasing, bad anatomy, watermarks, extra digit, fewer digits, cropped, worst quality, low quality, ugly, censored, text, signature, hair intakes
Paramètres recommandés
samplers
steps
cfg
clip skip
resolution
other models
Paramètres haute résolution recommandés
upscaler
upscale
denoising strength
Conseils
This model is super experimental and should not be expected to produce stable or high-quality results.
Meant more as a support LoRA for mixing and using with artist tags.
Points forts de la version
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
Sponsors du créateur
You can check out my other styles here
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. as always i just bad at training, lol
You can check out my other styles here
Continuation of HL's AI styles series
Contributeur
Détails du modèle
Type de modèle
Modèle de base
Version du modèle
Hash du modèle
Mots entraînés
Créateur
Discussion
Veuillez vous log in pour laisser un commentaire.












