zhens
/
JimLiu-baoyu-skills
mirror of https://github.com/JimLiu/baoyu-skills.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

refactor(baoyu-xhs-images): use skill interface instead of direct script invocation for image generation

This commit is contained in:
Jim Liu 宝玉 2026-03-08 19:24:03 -05:00
parent 90730bc551
commit fa82c3d910
1 changed files with 3 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

11
skills/baoyu-xhs-images/references/workflows/prompt-assembly.md
View File

@ -211,14 +211,9 @@ If preferences include watermark:
When generating multiple images in a series:
1. **Image 1 (cover)**: Generate without `--ref` — this establishes the visual anchor
2. **Images 2+**: Always pass image 1 as `--ref` to the image generation skill:
```bash
${BUN_X} <image-skill-baseDir>/scripts/main.ts \
--promptfiles prompts/02-content-xxx.md \
--ref path/to/01-cover-xxx.png \
--image 02-content-xxx.png --ar 3:4 --quality 2k
```
Replace `<image-skill-baseDir>` with the installed image generation skill directory.
2. **Images 2+**: Always pass image 1 as `--ref` to the installed image generation skill.
Read that skill's `SKILL.md` and use its documented interface rather than calling its scripts directly.
For each later image, use the assembled prompt file as input, set the output image path, keep aspect ratio `3:4`, use quality `2k`, and pass image 1 as the reference.
This ensures the AI maintains the same character design, illustration style, and color rendering across the series.
### Step 6: Combine