Individual skill
comfyui-reference-images
用本地或自托管远程 ComfyUI 制作角色参考图、场景图和视频首尾/中间帧;按 SDXL、Anima 家族查找并核验 Civitai/Hugging Face 模型,检查工作流、执行、恢复和验收。
skills/comfyui-reference-images/SKILL.md
Source commit 47cc68e1fe7a04213eb9aa53db9f08cb9a06d317
What was checked
- Matches the observed repository HEAD
- Yes
- Scanner rules are current
- Yes
- Repository scan complete
- No
- Skill scan complete
- Yes
- Observed behavior
- Network or broad shell
- Last checked
- Nov 11, 2026
These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.
Install this skill
Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.
An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.
Repository context
- Repository stars (not skill ratings)
- 9
- Repository last updated
- Sep 18, 2026
- License
- MIT
Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.
- agent-skills Repository topic
- anime Repository topic
- comfyui Repository topic
- minimax-h3 Repository topic
- video-generation Repository topic
- video-recipes Repository topic
- engineering Derived category
Files and excerpt
File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.
Browse files
SKILL.mdcore · 4,178 bytesreferences/batch-generation.mddoc · 10,293 bytesreferences/execution.mddoc · 5,161 bytesreferences/families-and-prompts.mddoc · 3,922 bytesreferences/local.mddoc · 1,458 bytesreferences/model-discovery.mddoc · 5,483 bytesreferences/remote.mddoc · 1,665 bytesreferences/toolkit.lock.jsonasset · 1,545 bytesreferences/toolkit.mddoc · 2,264 bytesscripts/prepare_graph.pyruns · 9,163 bytesscripts/resolve_workflow.pyruns · 3,140 bytestests/test_prepare_graph.pyruns · 9,192 bytes
Read excerpt
# ComfyUI 参考图
**这是无需账号的默认后端**:本地 ComfyUI 优先,其次才是需要登录的托管服务。用户只想“改一张现成图”(换装、去背景)时,先确认是否有可用的本地工作流;没有再用[GPT Image 2](../gpt-image2-reference-images/SKILL.md)等需要账号的路线。选哪一个后端要按用户当前使用的 Agent 与 provider 决定,见[生图后端怎么选](../../docs/image-generation-backends.md)。
**产出参考图后先给用户看**:说明这是视频推理的输入并默认继续(“我做出参考图拿去视频推理咯~你要是不满意就打断我,然后你给我更好的参考图”),用户给新图就以新图为准,见[生图后端怎么选](../../docs/image-generation-backends.md)第 5 节。
目标:交付适合下一镜头使用的图片,以及可追溯的生成记录。默认本地;图片工作流与服务器连接分开。需要能访问文件、HTTP API 和查看图片的 Agent。此目录可独立安装,不含模型权重或固定角色工作流。
先按[Toolkit 关联规则](references/toolkit.md)查找和获取匹配工作流,再执行以下步骤。具体图优先复用固定版本,未找到才按模型发布方流程补齐。
需要一组合集图片或视频首帧时,读[批量准备与任务恢复](references/batch-generation.md)。`scripts/prepare_graph.py` 只做离线参数绑定;生成仍需明确提交并等待 ComfyUI 结果。
## 按顺序执行