[PR #3280] [CLOSED] Add ComfyUI-ReShot #3161

New issue

Closed

opened 2026-10-28 21:15:43 +00:00 by bsakaguchi · 0 comments

bsakaguchi commented

2026-10-28 21:15:43 +00:00

Owner

📋 Pull Request Information

Original PR: https://github.com/Comfy-Org/ComfyUI-Manager/pull/3280
Author: @maosika-ai
Created: 9/14/2026
Status: ❌ Closed

Base: main ← Head: add-comfyui-reshot

📝 Commits (1)

1ec4460 Add ComfyUI-ReShot (depth / OpenPose skeleton / canny control videos for Seedance, MiniMax H3, Wan)

📊 Changes

1 file changed (+11 additions, -0 deletions)

View changed files

📝 custom-node-list.json (+11 -0)

📄 Description

Adds ComfyUI-ReShot — https://github.com/maosika-ai/ComfyUI-ReShot (Apache-2.0).

Six nodes that turn a reference video into a control video a video model will follow: Depth (Video Depth Anything), Pose (DWPose → OpenPose-style skeletons, tracked and smoothed across frames, keypoints JSON out) and Canny, each as IMAGE → IMAGE and VIDEO → VIDEO with the Seedance 2.0/2.5 / MiniMax H3 / Wan VACE presets (fps by timestamp, frame-size multiples) applied. Backed by the reshot package on PyPI; requirements.txt installs it. Has pyproject.toml with [tool.comfy], tests and example workflows.

The JSON was validated after the edit (json.load on the whole file).

_{🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.}

## 📋 Pull Request Information **Original PR:** https://github.com/Comfy-Org/ComfyUI-Manager/pull/3280 **Author:** [@maosika-ai](https://github.com/maosika-ai) **Created:** 9/14/2026 **Status:** ❌ Closed **Base:** `main` ← **Head:** `add-comfyui-reshot` --- ### 📝 Commits (1) - [`1ec4460`](https://github.com/Comfy-Org/ComfyUI-Manager/commit/1ec44601f6c14134cfd8c99e24ace15b0c5f097f) Add ComfyUI-ReShot (depth / OpenPose skeleton / canny control videos for Seedance, MiniMax H3, Wan) ### 📊 Changes **1 file changed** (+11 additions, -0 deletions) <details> <summary>View changed files</summary> 📝 `custom-node-list.json` (+11 -0) </details> ### 📄 Description Adds **ComfyUI-ReShot** — https://github.com/maosika-ai/ComfyUI-ReShot (Apache-2.0). Six nodes that turn a reference video into a control video a video model will follow: **Depth** (Video Depth Anything), **Pose** (DWPose → OpenPose-style skeletons, tracked and smoothed across frames, keypoints JSON out) and **Canny**, each as `IMAGE → IMAGE` and `VIDEO → VIDEO` with the Seedance 2.0/2.5 / MiniMax H3 / Wan VACE presets (fps by timestamp, frame-size multiples) applied. Backed by the `reshot` package on PyPI; `requirements.txt` installs it. Has `pyproject.toml` with `[tool.comfy]`, tests and example workflows. The JSON was validated after the edit (`json.load` on the whole file). --- <sub>🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.</sub>

bsakaguchi

2026-10-28 21:15:43 +00:00