
This model mainly focuses on the Alola-style leaf and the original leaf. The original leaf hasn't been trained much, so the effect might be not good enough.
I really like the design of this fan art. It is said that the original author is Chocogrotto. So I thought about whether the model of this character could be trained.
For now, the effect is acceptable, but the hands are very prone to breaking.
The training of this model and the images it generates are solely for learning purposes.
You could find the example prompts from the images above.
Trigger words: alolaleaf
Recommended weight: 1.0~0.6, adjust as needed until the character's appearance meets your requirements.
Upscale value recommendation is around 1.2~2.0 , denoising strength is 0.2
It is recommended to add 'other style' to the negative prompt for style consistency.
Continuous adjustment of the prompt words is needed to achieve a good representation.
The higher the weight, the more fixed the style of character.
There is a situation of overfitting.
描述:
训练词语: alolaleaf
名称: alolaleaf.safetensors
大小 (KB): 223101
类型: Model
Pickle 扫描结果: Success
Pickle 扫描信息: No Pickle imports
病毒扫描结果: Success