
!!! LoRA can be difficult to use !!!
This is the WAI/ILLUSTRIOUS version of these loras.
All information about each lora can be found in the “About this version” section.
Many thanks to @wwHEY — I couldn’t have done it without her advice!
But she's not responsible for the crappy quality of my LoRAs. x)
描述:
Illustrious/WAI version. It is more like the artist style. Much more stable but less aesthetically pleasing and flexible than NoobAI-XL version.
Some information and tips from my experience.
-
Trained on the WAI-NSFW-illustrious-SDXL v8. But it seems to work fine on the v9 version as well.
-
Trained on artworks (edited in photoshop by me with some effects) of Kan Liu (666k).
-
The weight is around 0.7-0.8, but you can play with the values. Didn't experiment much yet.
-
Use a klskx tag.
-
Use ‘blurry background’, ‘depth of field’, ‘bokeh’ tags for blurred background.
-
Use tags ‘dynamic pose’, ‘dutch angle’ - for dynamics of the image.
-
Add ‘outdoors’ and ‘indoors’ tags depending on the scene. Optional.
-
Tags for lighting help aesthetics: 'backlighting', 'sidelighting', 'underlighting', 'sunrays', 'sunlight', 'dappled sunlight' etc.
-
Sometimes ‘hydrokinesis’ and ‘water’ appear. Just add them to the negative prompt. Or in the positive if you want to see it in the picture.
-
Artist tags seem to work pretty well and fit with this LoRA. Give it a try.
Still in the process of checking out this model
训练词语: klskx
名称: klskx_wai.safetensors
大小 (KB): 124727
类型: Model
Pickle 扫描结果: Success
Pickle 扫描信息: No Pickle imports
病毒扫描结果: Success