这是一个使用了DirectAlign方法的早期版本lora 效果不保证能做到最好 This is an early-version LoRA that adopts the DirectAlign method; its performance is not guaranteed to be optimal.
此模型基于ILLUSTRIOUS-v0.1模型训练 This model is trained based on the ILLUSTRIOUS-v0.1 model.
模型权重高低与生成图片无关,加载即使用(我在Forge WebUI测试 发现权重为负数也可以) The magnitude of the model weights has no correlation with image generation—you can use it right after loading (during my testing in Forge WebUI, I found that even negative weights work).
欢迎搭配其他基础模型&LoRA进行使用 You are welcome to use it in combination with other base models and LoRAs.
祝用的开心 Hope you enjoy using it!
GitHub link https://github.com/myAiLemon/FALumina
CivitAI link https://civitai.com/user/AiLieLemon
LibLibAI link https://www.liblib.art/userpage/7c113cc195604446a85f9b79eb973742/publish
ModelScope link https://www.modelscope.cn/models/AiLieLemon/DirectAlignMitigatesRewardTamperingLoRA
HuggingFace link https://huggingface.co/ilemon/DirectAlignMitigatesRewardTamperingLoRA
DirectAlign* : 用于减轻模型存在的奖励作弊 DirectAlign*: Used to mitigate reward tampering in models.
禁止对此模型进行融合贩卖,直接货币化贩卖等行为 It is prohibited to engage in behaviors such as merging this model for sale or directly monetizing and selling it.