Type | |
Stats | 395 0 |
Reviews | (70) |
Published | Jun 28, 2023 |
Base Model | |
Training | Steps: 2,940 Epochs: 12 |
Trigger Words | xie lian, 1boy, male focus, chinese clothes, hair bun |
Hash | AutoV2 2C4C721A30 |
LoRA trained on Xie Lian from Heaven Official's Blessing
requested by: @jackaroo1432111
tags: xie lian, 1boy, male focus, chinese clothes, hair bun
models used
anime: , YesMix - v2.0, YabaL_Mix - V3, StingerMix - v3.1, Sweet-mix - v2.0-flat, MeinaMix - Meina V10
2,5D: CuriousMerge 2.5D - v4.0, GhostMix - v2.0-NoVAE, The Agenda Mix - 2.0
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