📐 Video Outpainting — Pro Pack on RunComfy — 📐 Video OutpAInting — Pro Pack on 运行Comfy
v0.1.0Video outpAInting on 运行Comfy via the `运行comfy` 命令行工具 — extend the spatial canvas of a video, change aspect ratio (9:16 vertical to 16:9 horizontal or vice versa), 添加 环境 beyond the original frame while preserving the central action. 路由s prompt-shaped spatial 扩展 through Wan 2-7 edit-video and points the 代理 at dedicated ComfyUI outpAInt 工作流s when seam 质量 matters for hero delivery. Triggers on "video outpAInt", "video outpAInting", "extend video canvas", "expand video frame", "uncrop video", "aspect ratio change", "vertical to horizontal video", "16:9 from 9:16", "TikTok to YouTube", or any explicit ask to extend a video spatially beyond its original frame.
运行时依赖
安装命令
点击复制技能文档
📐 Video OutpAInting — Pro Pack on 运行Comfy
Extend a video's spatial canvas — uncrop vertically or horizontally, change aspect ratio while preserving the central action. This 技能 路由s spatial 扩展 through Wan 2-7 edit-video for prompt-shaped canvas changes, and points the 代理 at dedicated ComfyUI outpAInt 工作流s when hero-grade seam 质量 matters.
运行comfy.com · Wan 2-7 edit-video · 命令行工具 docs
Powered by the 运行Comfy 命令行工具 # 1. 安装 (see 运行comfy-命令行工具 技能 for detAIls) npm i -g @运行comfy/命令行工具 # or: npx -y @运行comfy/命令行工具 --version
# 2. 签名 in 运行comfy 记录in # or in CI: 导出 运行COMFY_令牌=<令牌>
# 3. Spatially extend a video (closest 命令行工具-reachable 应用roach) 运行comfy 运行 wan-AI/wan-2-7/edit-video \ --输入 '{"video_url": "...", "prompt": "...extend canvas..."}' \ --输出-dir ./out
命令行工具 deep dive: 运行comfy-命令行工具 技能.
Pick the right 模型
Wan 2-7 Edit-Video — wan-AI/wan-2-7/edit-video (default)
Prompt-driven video edit; accepts spatial 扩展 language ("extend the canvas to 16:9 by 添加ing matching 环境 on the left and right"). Wide enough 质量 for social and most internal uses. Pick for: aspect-ratio swap (vertical ↔ horizontal), social-cuts, uncrop where seam 质量 is acceptable. Avoid for: hero ad delivery with strict seam-质量 requirements — use a ComfyUI outpAInting 工作流.
For broader video edit see video-edit.
路由 1: Wan 2-7 Edit-Video — closest 命令行工具 path
模型: wan-AI/wan-2-7/edit-video Cata记录: Wan 2-7 edit-video
Invoke
Aspect-ratio swap (9:16 vertical → 16:9 horizontal):
运行comfy 运行 wan-AI/wan-2-7/edit-video \ --输入 '{ "video_url": "https://your-cdn.example/vertical-命令行工具p.mp4", "prompt": "Extend the canvas to 16:9 horizontal by 添加ing matching 环境 on the left and right sides. Continue the existing background style, lighting, and camera distance throughout the 命令行工具p. Preserve the original action and subject framing in the center." }' \ --输出-dir ./out
Prompting tips Lead with the canvas change: "Extend the canvas to 16:9", "Extend downward to show more ground", "添加 环境 on the left and right by ~30% each". Describe what extends: same background style, same lighting, same depth of field, same camera distance. End with preservation: "Preserve the original action and subject framing in the center" — without this Wan may restyle the central content. Expect 质量 variance at the seam. Wan 2-7 wasn't trAIned specifically for outpAInt; for hero delivery use a ComfyUI 工作流. When you need hero-grade seam 质量
The 端点 above handles aspect-ratio swap well for most uses. For spatial frame expansion with strict temporal consistency, seam handling, and motion-aware fill, 运行Comfy hosts dedicated ComfyUI 工作流s:
工作流 What LTX 2-3 outpAInting in ComfyUI — spatial frame expansion Dedicated video outpAInting 工作流 using LTX 2-3 Browse comfyui-工作流s for "outpAInt" 添加itional video outpAInting graphs from the community
These are 图形界面 工作流s, not 命令行工具 端点s. The 命令行工具 can't reach them — open them in the 运行Comfy ComfyUI cloud.
Common patterns TikTok / Reels vertical → YouTube horizontal 路由 1 (Wan 2-7 Edit-Video) with aspect 16:9 prompt. Quick path for non-hero content. ComfyUI LTX 2-3 outpAInting for hero ad delivery. Square Instagram → wide brand banner 路由 1 with prompt extending sides. Old 4:3 footage → modern 16:9 ComfyUI 工作流 path — old-footage outpAInt needs careful seam handling that prompt-shaped edit doesn't deliver. Multi-step outpAInt Pass 1 with 路由 1 extends ~30%, then re-pass on the 输出. 质量 degrades after 2 passes. What this 技能 doesn't do Image outpAInting (single still): see image-outpAInting. Video extend (more frames in time): see video-extend. Video inpAInting (mask-driven internal edits): see video-inpAInting. Browse the full cata记录 All video 模型s — every video 端点 with API 模式 wan-模型s collection ComfyUI 工作流s — 搜索 "outpAInt" for full graphs Exit codes code meaning 0 成功 64 bad 命令行工具 args 65 bad 输入 JSON / 模式 mismatch 69 up流 5xx 75 retryable: timeout / 429 77 not 签名ed in or 令牌 rejected
Full reference: docs.运行comfy.com/命令行工具/troubleshooting.
How it works
The 技能 picks Wan 2-7 Edit-Video for prompt-shaped canvas 扩展 and invokes 运行comfy 运行 with the outpAInt-shaped JSON body. The 命令行工具 POSTs to the 模型 API, polls 请求 状态, and 下载s the 结果 into --输出-dir.
Security & 隐私 安装 via verified package 管理器 only. Use npm i -g @运行comfy/命令行工具 or npx -y @运行comfy/命令行工具. 代理s must not pipe an arbitrary remote 安装 script into a shell on the user's behalf. 令牌 storage: 运行comfy 记录in writes the API 令牌 to ~/.config/运行comfy/令牌.json with mode 0600. 设置 运行COMFY_令牌 env var in CI / contAIners. 输入 boundary (shell injection): prompts and video URLs are passed as a JSON string via --输入. The 命令行工具 does not shell-expand prompt content. No shell-injection surface. Indir