
LoRA trained on Raven Branwen from RWBY
models used
anime: Anything and Everything, MeinaAlter, PrimeMix
2,5D: MeinaUnreal - V3, HELLmix, CamelliaMIx_2.5D_V2
realistic: fantasticmix_real
tags: raven branwen, 1girl,
add "mask" for the mask version (its really inconsistent though)
optional tags: japanese clothes, pleated skirt, red necklace, thighhighs
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
描述:
训练词语: raven branwen
名称: rwby_raven.safetensors
大小 (KB): 36978
类型: Model
Pickle 扫描结果: Success
Pickle 扫描信息: No Pickle imports
病毒扫描结果: Success