Type | |
Stats | 1,028 |
Reviews | (186) |
Published | Apr 29, 2023 |
Base Model | |
Training | Steps: 9,600 Epochs: 30 |
Trigger Words | past salem salem \(rwby\) |
Hash | AutoV2 ABCA80B69F |
Lora trained on Salem from RWBY
models used
anime: MeinaUnreal, CoffeeMix, PrimeMix, ExpMix_Line
2,5D: SoapMix, Lyriel, CamelliaMIx_2.5D_V2, Dark Sushi 2.5D
realistic: fantasticmix_real
salem tags: salem \(rwby\), 1girl, white hair, white skin, cracked skin, red eyes
optional: black dress, long hair
past salem tags: past salem, 1girl, blonde hair, blue eyes, white dress
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: orangemix.vae (for 2,5D pictures), vae-ft-mse-840000-ema-pruned, kl-f8-anime2, blessed2.vae (for anime models)
Sampler: DPM++ SDE Karras or DPM++ 2M Karras
Steps: 20
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
Denoise strength for img2img: 0.4 to 0.7
If you want the exact same settings, just drag and drop the picture into ComfyUI
for the pictures i used comfyui