Skip to content

pigeonai-yang/oneirloom

v0.3.1-previewMIT

Visual prompting, reference analysis, craft construction, digital form, spatial concepts, and result diagnosis with 23 source skills.

oneirloom-model-qwen-image-2-1-comfyui-edit

在本地 ComfyUI 上编排 Qwen-Image-2.1 图像编辑流程:先判断需求属于真编辑还是重绘,据此接线、设置 denoise、控制画幅、分配多参考图角色,按官方 I2I 规则写编辑提示词,并在交付前验证改动范围、画幅与身份一致性。

Read SKILL.md at the source

Pinned to revision 43683138cd2c, so it is the text this page describes rather than whatever the author pushed since.

Files

Every link opens the file at its source, pinned to the revision this page describes.