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.
Anima版本我在使用的时候有问题,身体总是朝向画面左侧,我认为这是一个残次品,不建议下载使用。(可能和我没有重新修改训练集打标,使用的超长自然语言英文有关系)
I encountered issues while using the Anima version; the figure’s body consistently faces toward the left side of the frame. In my view, this is a flawed build, and I do not recommend downloading or using it. (This might be related to the fact that I didn’t re-annotate the training dataset, and I used very long, natural-language English prompts.)
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Claude娘和年轻Claude娘都使用一个页面,不新开了
The chibi-style Claude-chan and the younger-version Claude-chan now share a single page; no new page will be opened 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





