为<a target="_blank" rel="ugc" href="https://civarchive.com/models/2458426/anima">Anima base-v1.0</a>制作的实验性通用型编辑Lora，使用小型验证性全动漫编辑数据集训练。你会需要<a target="_blank" rel="ugc" href="https://github.com/Mirumo0u0/ComfyUI-Cosmos-Reference">ComfyUI-Cosmos-Reference</a>来运行该lora对于难以起效的改变,可以尝试提高提示词的权重。（anima对高权重的耐受性极强，猛猛冲到顶也没关系）这只是一个初期实验lora,编辑能力低下且难以控制,将来会尝试更多功能不同、更强响应的编辑Lora。An experimental general-purpose editing LoRA made for <a target="_blank" rel="ugc" href="https://civarchive.com/models/2458426/anima">Anima base-v1.0</a>, trained on a small proof-of-concept all-anime editing dataset.You will need <a target="_blank" rel="ugc" href="https://github.com/Mirumo0u0/ComfyUI-Cosmos-Reference">ComfyUI-Cosmos-Reference</a> to run this LoRA.For edits that are hard to achieve, try increasing the prompt weight.

AnimaEdit-experimental

超早期训练lora，你可能遇到任何意料之外的情况

Files with SHA256: fb1959ecb45167d1905df0c59e0da180d53510fa064ec5877c9aec87262a792f