The goal was to make LHC more user friendly, by introducing the base style of various model mixes to it, while keeping the character knowledge of LHC in tact. This means that this model does not require artist to produce good results, though they can still be used. The components and method used for merging can be found in the version details.
Recommendations
Refer to the version changes for specific settings that are recommended. In general, they are the same or very similar to the model mixes used as a base.
Description
A simple merge of LHC and NTRmix-XII using the perpendicular component strategy used in NoobIEater. Additionally, I merged the Au_(d_elete) and nyalia Loras at 0.4 and 0.5 strength respectively.
The list of added characters is the same as the one for LHCv0.4, which is https://huggingface.co/Jyrrata/LHC_XL/blob/main/characters/alpha04.txt . Character knowledge seems slightly weaker than the base model, but the result has been much better than just using the Lora-extract.
Recommended settings:
Sampler/scheduler: dpm++ 2m / karras
CFG: 5.5
Steps: 30
Positive Prompt: add "masterpiece, best quality, amazing quality," at the end of your prompt
Negative Prompt: "lowres, (worst quality, bad quality:1.2), bad ???????, sketch, jpeg artifacts, signature, watermark,"
FAQ
Details
Files
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.