CivArchive
    Preview 147410084
    Preview 147410082
    Preview 147410092
    Preview 147410093
    Preview 147410096
    Preview 147410097
    Preview 147410099
    Preview 147410101
    Preview 147410102
    Preview 147410108
    Preview 147410110
    Preview 147410135
    Preview 147410137
    Preview 147410152
    Preview 147410154
    Preview 147410171
    Preview 147410173
    Preview 147410176
    Preview 147410178
    Preview 147410186

    通过 gpt image 2.5 修改产出,最终训练得到了这个 lora

    This LoRA was trained using outputs modified via GPT Image 2.5.

    使用了 30 张图片去训练,包含正面,侧面,背面,俯视,仰视

    Thirty images were used for training, covering front, side, and back views, as well as top-down and low-angle views.

    Q版白龙娘和年轻白龙娘都使用一个页面,不新开了

    The chibi White Dragon girl and the young White Dragon girl share the same page; no separate page has been created for them.

    展示图大差不差都是因为懒,前两天DSH弄坏电脑后,原先存的pose和服装提示词都没了,这些都是ollama部署的模型批量出的。

    The images shown are all pretty much the same—mostly out of laziness. A couple of days ago, DSH caused my computer to crash, and I lost all my saved prompts for poses and outfits. These were generated in batches using models deployed via Ollama.

    推荐一下自己的批量加载提示词节点 https://github.com/update-loulan/comfyui-prompt-batch-writer

    I’d like to share a custom node I created for batch-loading prompts: https://github.com/update-loulan/comfyui-prompt-batch-writer

    Description

    FAQ

    LORA
    MOSS Image

    Details

    Downloads
    70
    Platform
    CivitAI
    Platform Status
    Available
    Created
    10/31/2026
    Updated
    11/18/2026
    Deleted
    -
    Trigger Words:
    白龙娘

    Files

    moss-白龙娘.safetensors

    Mirrors

    HuggingFace (1 mirrors)
    CivitAI (1 mirrors)