{"id":49229556,"url":"https://github.com/nvidia/comfy_nv_video_prep","last_synced_at":"2026-04-24T11:01:22.477Z","repository":{"id":351430238,"uuid":"1170602651","full_name":"NVIDIA/comfy_nv_video_prep","owner":"NVIDIA","description":"ComfyUI Node for easy video preparation making TTM use easy","archived":false,"fork":false,"pushed_at":"2026-03-11T16:55:21.000Z","size":108,"stargazers_count":3,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2026-04-24T00:36:46.899Z","etag":null,"topics":["comfyui","comfyui-custom-node"],"latest_commit_sha":null,"homepage":"https://github.com/NVIDIA/comfy_nv_video_prep","language":"JavaScript","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"other","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/NVIDIA.png","metadata":{"files":{"readme":"README.md","changelog":"CHANGELOG.md","contributing":"CONTRIBUTING.md","funding":null,"license":"LICENSE","code_of_conduct":"CODE_OF_CONDUCT.md","threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":"SECURITY.md","support":"SUPPORT.md","governance":"GOVERNANCE.md","roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":"MAINTAINERS.md","copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2026-03-02T10:02:13.000Z","updated_at":"2026-03-14T13:41:29.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/NVIDIA/comfy_nv_video_prep","commit_stats":null,"previous_names":["nvidia/comfy_nv_video_prep"],"tags_count":2,"template":false,"template_full_name":null,"purl":"pkg:github/NVIDIA/comfy_nv_video_prep","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/NVIDIA%2Fcomfy_nv_video_prep","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/NVIDIA%2Fcomfy_nv_video_prep/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/NVIDIA%2Fcomfy_nv_video_prep/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/NVIDIA%2Fcomfy_nv_video_prep/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/NVIDIA","download_url":"https://codeload.github.com/NVIDIA/comfy_nv_video_prep/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/NVIDIA%2Fcomfy_nv_video_prep/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":32220295,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-04-24T10:26:35.452Z","status":"ssl_error","status_checked_at":"2026-04-24T10:25:27.643Z","response_time":64,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.5:443 state=error: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["comfyui","comfyui-custom-node"],"created_at":"2026-04-24T11:01:18.889Z","updated_at":"2026-04-24T11:01:22.472Z","avatar_url":"https://github.com/NVIDIA.png","language":"JavaScript","funding_links":[],"categories":[],"sub_categories":[],"readme":"# ComfyUI_VideoPrep\n\nNVIDIA Video Preparation nodes for ComfyUI — a suite of interactive tools for cropping, mask editing, segmentation, keyframe animation, and multi-layer compositing, designed for video generation pre-production workflows.\n\n# Overview\n\nComfyUI_VideoPrep provides 5 custom nodes that keep the entire video preparation stage inside ComfyUI. Artists can interactively crop, segment, edit masks, and keyframe-animate layers without leaving the canvas, then pipe results directly into downstream generation nodes (Wan, LTX, etc.).\n\n**Nodes included:**\n\n| Node | Description |\n|------|-------------|\n| **VideoPrep Interactive Crop** | Draggable crop rectangle with live preview; simultaneous image + mask cropping |\n| **VideoPrep Preview Bridge** | Image/mask pass-through with premultiplied alpha and multiple output modes |\n| **VideoPrep Preview Bridge (Advanced)** | Built-in persistent mask editor with brush/erase and Cut/Keep/Extend modes |\n| **VideoPrep TTM Interactive Editor** | Click-to-segment with SAM2, polygon editing, multi-layer keyframe animation |\n| **VideoPrep TTM Compose \u0026 Animate** | Multi-layer compositor with up to 4 subjects, background pan/zoom/rotate |\n\n# Getting Started\n\n```bash\n# Clone the repository\ngit clone ssh://git@gitlab-master.nvidia.com:12051/awd/alt_comfyui_ttm_nodes.git\n\n# Copy to ComfyUI custom_nodes\ncp -r alt_comfyui_ttm_nodes /path/to/ComfyUI/custom_nodes/ComfyUI_VideoPrep\n\n# Install dependencies\npip install -r /path/to/ComfyUI/custom_nodes/ComfyUI_VideoPrep/requirements.txt\n\n# Restart ComfyUI — VideoPrep nodes will appear in the node menu\n```\n\n# Requirements\n\n- **OS:** Windows 10/11, Linux (Ubuntu 20.04+)\n- **Runtime:** Python 3.10+, ComfyUI (latest stable)\n- **GPU:** NVIDIA GPU with CUDA support\n- **VRAM (Minimum):** 4 GB\n- **VRAM (Recommended):** 8 GB+ (for SAM2 segmentation features)\n\n### Python Dependencies\n\n- `numpy`\n- `opencv-python`\n- `imageio`, `imageio-ffmpeg`\n\n### Optional Dependencies\n\n- **[comfyui-sam2](https://github.com/neverbiasu/comfyui-sam2)** — for click-to-segment in the Interactive Editor. Install via ComfyUI Manager. SAM2 models auto-download on first use.\n\n# Usage\n\nLoad one of the example workflows from the `workflows/` directory:\n\n- `example_basic.json` — Basic interactive editor usage\n- `example_compose_animate.json` — Multi-layer composition and animation\n- `example_with_wan.json` — Integration with Wan video generation pipeline\n\n### Node Details\n\n\u003cdetails\u003e\n\u003csummary\u003e\u003cb\u003eVideoPrep Interactive Crop\u003c/b\u003e\u003c/summary\u003e\n\n- Click and drag to draw a crop region directly on the image\n- Resize by dragging corners/edges; move by dragging inside\n- Double-click to reset; grid snapping for latent alignment\n- **Inputs:** `image`, `mask` (optional), `crop_data`, `snap_to_grid`\n- **Outputs:** `cropped_image`, `cropped_mask`, `x`, `y`, `width`, `height`\n\n\u003c/details\u003e\n\n\u003cdetails\u003e\n\u003csummary\u003e\u003cb\u003eVideoPrep Preview Bridge\u003c/b\u003e\u003c/summary\u003e\n\n- Handles both images and masks reliably across workflow runs\n- Output modes: `original`, `premultiplied`, `cutout_black`, `cutout_white`\n- Preview modes: `cutout`, `overlay`, `mask_only`\n- **Inputs:** `image`, `mask` (optional), `output_mode`, `preview_mode`\n- **Outputs:** `image`, `mask`, `width`, `height`\n\n\u003c/details\u003e\n\n\u003cdetails\u003e\n\u003csummary\u003e\u003cb\u003eVideoPrep Preview Bridge (Advanced)\u003c/b\u003e\u003c/summary\u003e\n\n- Draw/erase masks directly on the image preview\n- Mask stored inside the workflow file — persists across runs, saves, and restarts\n- Multiple mask modes: Cut, Keep, Extend\n- Auto-imports existing alpha channels from input images\n- **Inputs:** `image`, `mask` (optional), `output_mode`, `mask_combine`, `mask_data`\n- **Outputs:** `image`, `mask`, `preview`, `width`, `height`\n\n\u003c/details\u003e\n\n\u003cdetails\u003e\n\u003csummary\u003e\u003cb\u003eVideoPrep TTM Compose \u0026 Animate\u003c/b\u003e\u003c/summary\u003e\n\n- Up to 4 animated subjects over an animated background\n- Per-layer keyframe transforms: position, rotation, scale\n- Background animation: pan, zoom, rotate with independent keyframe track\n- Timeline scrubber for animation preview\n- **Inputs:** `background`, up to 4× (`subject_N`, `mask_N`), `editor_data`, `total_frames`\n- **Outputs:** `frames`, `width`, `height`\n\n\u003c/details\u003e\n\n\u003cdetails\u003e\n\u003csummary\u003e\u003cb\u003eVideoPrep TTM Interactive Editor\u003c/b\u003e\u003c/summary\u003e\n\n- Click-to-segment using SAM2 (optional) for detailed mask creation\n- Include/exclude points for precise segmentation control\n- Manual polygon drawing fallback (if SAM2 is not installed)\n- Multi-layer keyframe animation: position, rotation, scale, hue\n- Animation timeline preview slider\n- **Inputs:** `image`, `editor_data`, `total_frames`\n- **Outputs:** `frames`, `masks`, `width`, `height`\n\n\u003c/details\u003e\n\n## Releases \u0026 Roadmap\n\n- Releases / Changelog: [CHANGELOG.md](CHANGELOG.md)\n\n# Contribution Guidelines\n\n**This project is currently not accepting any contributions.**\n\nAll source code is original NVIDIA-authored work. No third-party code is included.\n\n- Code of Conduct: [CODE_OF_CONDUCT.md](CODE_OF_CONDUCT.md)\n- Contributing policy: [CONTRIBUTING.md](CONTRIBUTING.md)\n\n## Governance \u0026 Maintainers\n\n- Governance: [GOVERNANCE.md](GOVERNANCE.md)\n- Maintainers: NVIDIA AWD Team — see [MAINTAINERS.md](MAINTAINERS.md)\n\n## Security\n\n- Vulnerability disclosure: [SECURITY.md](SECURITY.md)\n- **Do not file public issues for security reports.** Report to [psirt@nvidia.com](mailto:psirt@nvidia.com).\n\n## Support\n\n- Level: **Experimental**\n- How to get help: File an issue\n- Details: [SUPPORT.md](SUPPORT.md)\n\n# License\n\nThis project is licensed under the Apache License 2.0 — see the [LICENSE](LICENSE) file for details.\n\nCopyright (c) 2025 NVIDIA CORPORATION \u0026 AFFILIATES. All rights reserved.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fnvidia%2Fcomfy_nv_video_prep","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fnvidia%2Fcomfy_nv_video_prep","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fnvidia%2Fcomfy_nv_video_prep/lists"}