Hoodwinker's SREF Styles版本hwsref1 (ID: 1275813)

Here's something a little different after a few art style LoRAs... this (work-in-progress) LoRA collection is exclusively trained on various SREF style codes found on Nijijourney version 6. For every LoRA made, I'll paste the original code. There's no set way I'm choosing these styles, just some from the internet, some I've stumbled across personally.

All demo images were made raw with no tweaks. ADetailer was used to fix faces.

hwsref1 ---sref 1333447729

A detailed style that blends a bit of anime and realism. Textures like the clothes and hair are VERY realistic. Most of the training material was portraits, but there's a few landscapes scattered around the dataset. AnythingElse V4 seems to like this LoRA the most.

Usage Tips

• The trigger word is "hwsrefX". Replace the X with the right number listed.

• Most NAI-based checkpoints are generally compatible with this LoRA. Check out the recommended resources to see which ones work the best.

• Use Booru language when prompting.

• LoRA strength can be 0.8 to 1.5. Higher strengths may cause more creative details.

• For more anime/illustrated styles, use any DPM or DDIM sampler. For more realistic styles, use Euler/Euler a samplers at 512x768 base resolution. Hires fix is not required.

• Use ADetailer to fix imperfect faces.

描述:

sref 1333447729

训练词语: hwsref1