[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-80103":3},{"id":4,"name":5,"fullName":6,"owner":7,"repo":5,"description":8,"homepage":9,"htmlUrl":9,"language":10,"languages":9,"totalLinesOfCode":9,"stars":11,"forks":12,"watchers":13,"openIssues":14,"contributorsCount":15,"subscribersCount":15,"size":15,"stars1d":16,"stars7d":17,"stars30d":18,"stars90d":15,"forks30d":15,"starsTrendScore":19,"compositeScore":20,"rankGlobal":9,"rankLanguage":9,"license":21,"archived":22,"fork":22,"defaultBranch":23,"hasWiki":24,"hasPages":22,"topics":25,"createdAt":9,"pushedAt":9,"updatedAt":26,"readmeContent":27,"aiSummary":28,"trendingCount":15,"starSnapshotCount":15,"syncStatus":29,"lastSyncTime":30,"discoverSource":31},80103,"ComfyUI-WanAnimatePlus","wuwukaka\u002FComfyUI-WanAnimatePlus","wuwukaka","Seamless video connection and multi-reference image support for Wan Animate.",null,"Python",161,6,57,1,0,3,51,103,18,2.54,"Apache License 2.0",false,"main",true,[],"2026-06-12 02:03:58","# ComfyUI-WanAnimatePlus\n\n[English](.\u002FREADME.md) | [中文](.\u002FREADME_ZH.md)\n\nMulti-reference image injection and seamless video connection for ComfyUI's WanAnimate pipeline.\n\n## Overview\n\n`ComfyUI-WanAnimatePlus` adds two core inputs to the original WanVideoWrapper's WanAnimate workflow:\n\n- **prefix_frames**: allows passing 1–5 additional reference images for multi-reference guided generation\n- **transition_video**: allows passing the last 21 frames of the previous video segment for seamless video connection\n\nWhen used together, canvas layout and frame offsets are automatically coordinated without conflicts.\n\nUse cases:\n\n- Multi-shot video sequence generation\n- Video continuation \u002F extension\n- Motion transfer with multi-reference control\n\n## Demo\n\n### prefix_frames & transition_video usage\n\n![Usage](docs\u002Fimages\u002Fimage_001.png)\n\n### prefix_frames demo\n\n[](https:\u002F\u002Fgithub.com\u002Fuser-attachments\u002Fassets\u002F6df01023-5daa-42ab-9817-27a3b49bd6af)\n\n### transition_video demo\n\n[](https:\u002F\u002Fgithub.com\u002Fuser-attachments\u002Fassets\u002F4c6d2d29-dc21-406c-8ae9-5201d4cc416b)\n\n## Features\n\n### prefix_frames (Multi-Reference Injection)\n\nAllows 1–5 additional reference images. Internally expands the canvas pixel space and encodes reference images across the front frames, with automatic frame offset coordination for control signals (pose \u002F face).\n\n- Supports 1–5 reference images (truncated if exceeding 5)\n- Auto-resizes reference images to target resolution\n- Automatically aligns frame offsets for pose \u002F face \u002F bg \u002F mask signals\n\n### transition_video (Seamless Video Connection)\n\nAllows passing the last 21 frames of the previous video segment. Writes these pixel frames directly into the front of the generation canvas, with sampled+reversed padding for control signal offsets.\n\n- Automatically coordinates with prefix when both are used\n\n## Installation\n\nPlace this repository into ComfyUI's `custom_nodes` directory:\n\n```bash\ncd ComfyUI\u002Fcustom_nodes\ngit clone https:\u002F\u002Fgithub.com\u002Fwuwukaka\u002FComfyUI-WanAnimatePlus.git\n```\n\nRestart ComfyUI after installation.\n\n> **Important**: To use `prefix_frames` and `transition_video`, you **must** replace the full workflow chain with WanAnimatePlus nodes. Mixing WanAnimatePlus nodes with original WanVideoWrapper nodes in the same workflow will result in degraded output.\n\n## Quick Start\n\n1. Start ComfyUI and confirm the WanAnimatePlus nodes appear under the `WanAnimatePlus` category\n2. **Replace the entire workflow chain** with WanAnimatePlus counterparts: `ModelLoader`, `VAELoader`, `ContextOptions`, `AnimateEmbeds`, `Sampler`, `Decode`, and supporting nodes\n3. Do **not** mix original WanVideoWrapper nodes in the same workflow\n4. Connect `prefix_frames` and\u002For `transition_video` inputs as needed\n5. Example workflows are available in the `example_workflows\u002F` directory\n\n## Nodes\n\nWanAnimatePlus exposes a complete workflow chain to avoid cross-package object mixing with the original WanVideoWrapper nodes.\n\nCore nodes:\n\n- `WanAnimatePlus ModelLoader`\n- `WanAnimatePlus VAELoader`\n- `WanAnimatePlus TextEncodeCached`\n- `WanAnimatePlus ClipVisionEncode`\n- `WanAnimatePlus ContextOptions`\n- `WanAnimatePlus AnimateEmbeds`\n- `WanAnimatePlus Sampler` \u002F `WanAnimatePlus Samplerv2`\n- `WanAnimatePlus Scheduler` \u002F `WanAnimatePlus Schedulerv2`\n- `WanAnimatePlus Decode` \u002F `WanAnimatePlus Encode`\n- `WanAnimatePlus LoraSelectMulti` \u002F `WanAnimatePlus SetLoRAs`\n- `WanAnimatePlus BlockSwap` \u002F `WanAnimatePlus SetBlockSwap`\n- `WanAnimatePlus TorchCompileSettings`\n- `WanAnimatePlus Uni3C ControlnetLoader` \u002F `WanAnimatePlus Uni3C Embeds`\n\n### WanAnimatePlus AnimateEmbeds\n\nCore node, replaces the original `WanVideoAnimateEmbeds`.\n\n**New inputs:**\n\n| Input | Description |\n|------|------|\n| `prefix_frames` | 1–5 additional reference images for multi-reference guided generation |\n| `transition_video` | Last 21 frames of the previous video segment for seamless video connection |\n\nOther inputs are identical to the original WanVideoAnimateEmbeds: `vae`, `width`, `height`, `num_frames`, `ref_images`, `pose_images`, `face_images`, `bg_images`, `mask`, `start_ref_image`, `clip_embeds`, etc.\n\n## Project Structure\n\n```text\nComfyUI-WanAnimatePlus\u002F\n├─ wanvideo\u002F                 # WanVideo core model code\n├─ nodes.py                  # Core WanAnimatePlus embeds \u002F encode \u002F decode nodes\n├─ nodes_sampler.py          # Core WanAnimatePlus sampler \u002F scheduler nodes\n├─ nodes_model_loading.py    # Core WanAnimatePlus model \u002F VAE \u002F LoRA \u002F block swap nodes\n├─ context_windows\u002F          # Context-window scheduling\n├─ cache_methods\u002F            # Cache acceleration\n├─ utils.py                  # Shared utilities\n├─ docs\u002F\n│  └─ images\u002F                # Documentation images\n├─ example_workflows\u002F        # Example workflows\n├─ __init__.py               # Node registration entry point\n├─ pyproject.toml\n├─ requirements.txt\n└─ LICENSE\n```\n\n## FAQ\n\n### 1. Nodes not showing after installation\n\n- Verify the repo path is `ComfyUI\u002Fcustom_nodes\u002FComfyUI-WanAnimatePlus`\n- Ensure the original `ComfyUI-WanVideoWrapper` is also installed\n- Restart ComfyUI and search for `WanAnimatePlus` in the node list\n\n### 2. Conflicts with original nodes?\n\nNo. All node names use the `WanAnimatePlus` prefix, completely avoiding conflicts with the original `WanVideo` prefixed nodes. Both can be installed simultaneously.\n\n### 3. How many images for prefix_frames?\n\n3 is recommended. Up to 5 are accepted (excess is truncated). The node works with fewer than 3 as well, but the coverage range will be smaller.\n\n### 4. How many frames for transition_video?\n\nInput is automatically cropped to 21 frames (padded with the first frame if insufficient).\n\n## Acknowledgments\n\nModified from [kijai\u002FComfyUI-WanVideoWrapper](https:\u002F\u002Fgithub.com\u002Fkijai\u002FComfyUI-WanVideoWrapper). Deep respect to the original author for their tremendous contributions to the WanVideo ecosystem.\n\n## Contact\n\n- Bilibili: [@wuwukasi](https:\u002F\u002Fspace.bilibili.com\u002F670281046)\n- Email: wuwukawayi@gmail.com\n\n## Sponsorship\n\nIf you find this project helpful, consider supporting me! Your support is what keeps this project going and motivates me to continue improving it.\n\nEvery contribution, no matter how small, means a lot and helps me dedicate more time to development and new features. Thank you!\n\n\u003Cp align=\"center\">\n  \u003Cimg src=\"docs\u002Fimages\u002Fimage_003.png\" alt=\"WeChat Sponsor QR\" width=\"400\"\u002F>\n  \u003Cimg src=\"docs\u002Fimages\u002Fimage_002.jpg\" alt=\"Alipay Sponsor QR\" width=\"400\"\u002F>\n\u003C\u002Fp>\n\n## License\n\nBased on the original project, released under **Apache License, Version 2.0**. Modified files include copyright attribution and modification notices in their headers.\n","ComfyUI-WanAnimatePlus 是一个为Wan Animate流程提供无缝视频连接和多参考图像支持的项目。它通过添加两个核心输入`prefix_frames`和`transition_video`来扩展原有的WanVideoWrapper功能，前者允许注入1-5张额外的参考图像以指导生成过程，后者则可以通过传递前一段视频的最后21帧实现视频间的平滑过渡。这两个功能协同工作时，能够自动协调画布布局与帧偏移，避免冲突。此项目适用于需要多镜头视频序列生成、视频延续或扩展以及带有多参考控制的动作转移等场景。基于Python开发，并采用Apache License 2.0授权。",2,"2026-06-11 03:59:16","CREATED_QUERY"]