Type | |
Stats | 1,002 93 3 |
Reviews | (150) |
Published | May 26, 2023 |
Base Model | |
Training | Steps: 2,850 Epochs: 19 |
Trigger Words | tranquility dragon karma |
Hash | AutoV2 01289C1831 |
LoRA trained on Tranquility Dragon Karma from League of Legends
requested by @bty_is_within_us
models used
anime: YabaL_Mix V3, MeinaAlter, PrimeMix
2,5D: HELLmix, DarkSun, CamelliaMIx_2.5D_V2, DreamShaper - 6
realistic: fantasticmix
tags: tranquility dragon karma, 1girl,
optional tags: bodysuit, hair ornament, heterochromia, pink eyes, blue eyes,
negative embeddings: embedding:bad-hands-5, embedding:ng_deepnegative_v1_75t, embedding:bad-artist, embedding: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
Steps: 20 to 35
Clipskip: 2
Upscaler : img2img in comfyui using 4x-UltraMix_Smooth
CFG Scale : 5 to 9 (mostly 7 and 8)
LORA weight for txt2img: 0.5-1 (for the examples i mostly used 0.8)
Denoise strength for img2img: 0.4 to 0.7
for the pictures i used comfyui