LoRA trained on Hiiragi Shinoa and Hyakuya Yuuichirou from Owari no Seraph

The first picture was generated using ControlNet for demonstration purposes. Dont try at home it will cost you many trys xD

Hiiragi Shinoa: hiiragi shinoa, 1girl, military uniform, purple hair, hair bow, gloves, skirt, thighhighs

Hyakuya Yuuichirou: hyakuya yuuichirou, 1boy, black hair, military uniform, white gloves

requested by: @Merkuriij

models used

anime: YesMix - v2.0, YabaL_Mix V3

2,5D: GhostMix - v2.0-NoVAE, LusterMix - v1.5

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