Needs Hires to properly work!
Ratings are appreciated so i can see what i can improve on for my next models!
If you appreciate these models you can support me with a cup of coffee :) ->
The model consists of about 260 high-quality images and was trained in 2600 training steps using LoHa.
It works with the usual outfits but also with more variety, which was missing from the other models i saw so far.
Recommended settings to get images similar to the examples:
Positive
best quality, masterpiece, Amane Kanata, short hair, multicolored hair, grey hair, colored inner hair, (blue hair ), purple eyes, <lora:amane_kanata:0.7>
Negative
easynegative, low quality, worst quality, loli, pink hair
LoRA strength: 0.6-0.8
Checkpoint + VAE: AOM2_Hard
CFG: 7
Sampler: DPM++ 2M Karras
Feel free to reach out with any questions or suggestions you may have!
描述:
训练词语: amane kanata,multicolored hair
名称: amane_kanata.safetensors
大小 (KB): 9356
类型: Model
Pickle 扫描结果: Success
Pickle 扫描信息: No Pickle imports
病毒扫描结果: Success
