LoRA trained on Hua Cheng from Heaven Official's Blessing
requested by: @donutai (sorry for taking so long)
tags: hua cheng, 1boy, eyepatch, male focus, chinese clothes, jewelry, long hair
you can also remove "eyepatch"
models used
anime: YesMix - v2.0, MeinaAlter - V2, YabaL_Mix - V3
2,5D: GhostMix - v2.0-NoVAE, LusterMix - v1.5, MeinaUnreal - V3
negative embeddings: bad_prompt, negative_hand, ng_deepnegative_v1_75t, bad-artist, EasyNegative
Recommended settings:
Make sure you are aware on the usage instructions of LORA
VAE: vae-ft-mse-840000-ema-pruned (for realistic models & 2,5D), kl-f8-anime2, blessed2.vae (for anime models)
Sampler: DPM++ SDE Karras or DPM++ 2M Karras(euler a for img2img upscaling) from time to time im also using DPM++ 2M alt Karras
Steps: 20 to 35
Clipskip: 2
Upscaler : GitHub - pkuliyi2015/multidiffusion-upscaler-for-automatic1111 4x-UltraSharp(for 2,5D & realistic), 4xAnimesharp(for anime)
CFG Scale : 5 to 9 (mostly 7)
LORA weight for txt2img: 0.5-1 (for the examples i mostly used 0.8 and 1)
Denoise strength upscaling: 0.3 to 0.55
If you want to autocomplete the tags & trigger im using, I recommend using Booru style tag autocompletion for AUTOMATIC1111's Stable Diffusion web UI
For full body shots i recommend using: ComfyUI Impact Pack
or the a1111 alternative GitHub - Bing-su/adetailer
Description
FAQ
Comments (7)
Omg I've been waiting for you. I want someone to make it for me! I'm very happy now! Are you willing to make mxtx other characters as well?
Glad you like it :D
Sure, which one do you want me to do next?
@AhriMain Xie Lian :) <3
@jackaroo1432111 me too. @AhriMain All the characters are attractive. I especially like the 清歌柳 character from svsss the most, but not the main character, so the data will be insufficient compared to other characters. Even if it's not him, all the mxtx characters you made would be great, and my heart is pounding already.
THANK YOUUU <3
Details
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.











