Noisy_Element_XL版本v2 (ID: 392530)

Spent a literal week training this model locally, since I had great difficulty training it online.

This was trained on 500+ images in 4 specific categories: full body, close up, Victorian, and Monet (the painter, not me lol). Therefore, this checkpoint technically has 4 triggers, just like a LoRA.

This model has the SDXL LCM LoRA and SDXL VAE baked into it, therefore there's no need to use external VAEs or LCM LoRA to get a good result. I'd intended to prune this model, but I'm not sure if it actually did prune it. (To be fair, I'm not sure what a pruned SDXL checkpoint would look like; I simply tried it to see if I couldn't reduce the file size.)

If you're doing a close-up portrait of a face, or simply using ADetailer to refine faces, it's highly recommended to use the "close up" trigger prompt, though it can perform without the trigger word.

I'd had rough experiences with SDXL in the past whenever I tried making images with full body shots, thus I tried to rectify it here. The prompt "full body" is a trigger word which should facilitate the full body landscape shots I'm fond of.

Recommended Usage:

Set the sampler to LCM, reduce the CFG to 1-2, reduce the steps to 8-16, and then generate at will.

If you insist on using non-LCM samplers, then be sure to increase the steps to about 30. But it is of my opinion that this model has worse artifacts than the SD1.5 version when using non-LCM samplers, so be aware of that.

描述:

Tried to fine-tune v1 somewhat, and this is the result. In my messing around with things I don't know, I feel I might have inadvertently made this an inpainting model, so there's that. Honestly, I wanted it to lean towards more realistic, but it unintentionally went more anime. It feels cleaner than v1, but a thorough test is needed to see if it can even do realistic characters. Though this is based off v1, I feel the effects of the Victorian/Monet triggers are greatly diminished here, due to my aforementioned messing with settings... theoretically all the trigger words from v1 should work here. In addition, I essentially merged my STFD LoRA into this checkpoint, so all of those trigger words should work here too.

训练词语: