Lora usage guide for on-site generator is at the very bottom of this description.

_______________________________________________________________________

Use ILXL [V1.0] E10 - ILXL_01 | ILXL [V1.0] E10 - ILXL_01 please!

________________________________________________________________________________________________

Hello. This is my third style Lora that is based on the style of a videogame called ''Postal 2'' made by legendary Running With Scissors that I adore and I'd encourage you to support them, as for this lora it should give you cool early 2000s look and vibe in your images!

________________________________________________________________________________________________

As of today (5th of June, 2025), I have re-trained the lora model under Illustrious 0.1 for the purpose and did reformat the description to match it, if you see the loras that have ''WAI'' on them, I'd kindly ask you not to use them unless you use EPS/V-Pred 2,0 based models.

From my testing, Hassaku XL (Illustrious) and WAI-NSFW-illustrious-SDXL checkpoints give great results as long as the lora is marked with ILXL_01 in it's name.

This one will be the main release for the time being now.

_________________________________________________________________________________________

There are no activation keys/tags but I must insist that you include ``realistic, scenery`` in your positive prompting, it will make all the image compositions look proper. Add ''3d'' if necessary.

_________________________________________________________________________________________

• Lora weights: from 1 to 1.2/1.4

• Clip Skip 2

• Euler A Sampler - 21/31 Steps / SGM Uniform or Beta Scheduler

  (if DMD2 is present, use Euler A and Turbo)

• For upscale use Latent (Antialiased)

• CFG Scale - 7.5 (or 1.6 ONLY with DMD2 lora being present)

• Inpainting / Adetailer is highly recommended.

• I highly recommend to use this Lora in conjuction with Hassaku XL 1.3 A and DMD2, DMD2 will significantly save you a lot of time when you generate/inpaint stuff (see the images I posted to see the prompting and settings that each image used).

_________________________________________________________________________________________

Thank you for reading, have fun generating your images, I'd would love to see your generations that have been made with this Lora! All the support is greatly appreciated.

This is a 1.0 release and I plan to update the lora to 1.1.

________________________________________________________________________________________________

________________________________________________________________________________________________

________________________________________________________________________________________________

Note to users who have used WAI labelled trained loras on this page, I'd highly encourage you to switch to the latest one being ILXL [V1.0] E10 - ILXL_01. / E04 - ILXL_01

This one will save you from frustation if your images turn out mushy or just bad in general. I apologize for the image quality that the WAI ones caused.

________________________________________________________________________________________________

________________________________________________________________________________________________

________________________________________________________________________________________________

As for those who use on-site generator,

Please use Hassaku or any of your favourite Illustrous based checkpoints for image generation that isn't under heavy load in conjuction with DMD2 lora

(if it does not show up on site generator, try this one or look up dmd2 4step color fix and it will show up).

Here are the settings that you should use for the on-site image generation that uses this Lora (Below is an example on E10 IL_01 version of the lora)

________________________________________________________________________________________________

Have fun. I'd would love to see your images! Hope this little guide helps. I appreciate all your support, if you like this lora then I appreciate it. Buzz and emoji reactions on the images help a lot and will contribute towards the 1.1 dataset