{"id":29893441,"url":"https://github.com/modeltc/comfyui-lightx2vwrapper","last_synced_at":"2025-10-09T19:34:08.731Z","repository":{"id":289821774,"uuid":"971901752","full_name":"ModelTC/ComfyUI-Lightx2vWrapper","owner":"ModelTC","description":"ComfyUI custom node for lightx2v ","archived":false,"fork":false,"pushed_at":"2025-07-25T13:27:07.000Z","size":147,"stargazers_count":18,"open_issues_count":0,"forks_count":4,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-07-25T15:44:09.339Z","etag":null,"topics":["comfyui","comfyui-nodes"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/ModelTC.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null}},"created_at":"2025-04-24T08:24:47.000Z","updated_at":"2025-07-25T13:27:11.000Z","dependencies_parsed_at":"2025-04-25T08:40:54.387Z","dependency_job_id":"dfdeff30-b734-4feb-b1ab-f7debfa8fcc4","html_url":"https://github.com/ModelTC/ComfyUI-Lightx2vWrapper","commit_stats":null,"previous_names":["gaclove/comfyui-lightx2vwrapper","modeltc/comfyui-lightx2vwrapper"],"tags_count":1,"template":false,"template_full_name":null,"purl":"pkg:github/ModelTC/ComfyUI-Lightx2vWrapper","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ModelTC%2FComfyUI-Lightx2vWrapper","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ModelTC%2FComfyUI-Lightx2vWrapper/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ModelTC%2FComfyUI-Lightx2vWrapper/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ModelTC%2FComfyUI-Lightx2vWrapper/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/ModelTC","download_url":"https://codeload.github.com/ModelTC/ComfyUI-Lightx2vWrapper/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ModelTC%2FComfyUI-Lightx2vWrapper/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":268166323,"owners_count":24206428,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","status":"online","status_checked_at":"2025-08-01T02:00:08.611Z","response_time":67,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"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-nodes"],"created_at":"2025-08-01T03:44:57.154Z","updated_at":"2025-10-09T19:34:03.711Z","avatar_url":"https://github.com/ModelTC.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"[![License](https://img.shields.io/badge/License-MIT-blue.svg)](https://opensource.org/licenses/MIT) [![Python](https://img.shields.io/badge/python-3.8%2B-blue)](https://www.python.org/downloads/) [![ComfyUI](https://img.shields.io/badge/ComfyUI-Custom%20Node-brightgreen)](https://github.com/comfyanonymous/ComfyUI) [![Hugging Face](https://img.shields.io/badge/%F0%9F%A4%97%20Models-lightx2v-yellow)](https://huggingface.co/lightx2v) [![Ask DeepWiki](https://deepwiki.com/badge.svg)](https://deepwiki.com/GacLove/ComfyUI-Lightx2vWrapper)\n\n# ComfyUI-Lightx2vWrapper\n\n[中文版](./README_CN.md) | English\n\nA ComfyUI custom node wrapper for LightX2V, enabling modular video generation with advanced optimization features.\n\n## Features\n\n- **Modular Configuration System**: Separate nodes for each aspect of video generation\n- **Text-to-Video (T2V) and Image-to-Video (I2V)**: Support for both generation modes\n- **Advanced Optimizations**:\n  - TeaCache acceleration (up to 3x speedup)\n  - Quantization support (int8, fp8)\n  - Memory optimization with CPU offloading\n  - Lightweight VAE options\n- **LoRA Support**: Chain multiple LoRA models for customization\n- **Multiple Model Support**: wan2.1, hunyuan architectures\n\n## Installation\n\n1. Clone this repository with submodules into your ComfyUI's `custom_nodes` directory:\n\n```bash\ncd ComfyUI/custom_nodes\ngit clone --recursive https://github.com/gaclove/ComfyUI-Lightx2vWrapper.git\n```\n\nIf you already cloned without submodules, initialize them:\n\n```bash\ncd ComfyUI-Lightx2vWrapper\ngit submodule update --init --recursive\n```\n\n2. Install dependencies:\n\n```bash\ncd ComfyUI-Lightx2vWrapper\n# Install lightx2v submodule dependencies\npip install -r lightx2v/requirements.txt\n# Install ComfyUI wrapper dependencies\npip install -r requirements.txt\n```\n\n3. Download models and place them in `ComfyUI/models/lightx2v/` directory\n\n## Node Overview\n\n### Configuration Nodes\n\n#### 1. LightX2V Inference Config\n\nBasic inference configuration for video generation.\n\n- **Inputs**: model, task_type, inference_steps, seed, cfg_scale, width, height, video_length, fps\n- **Output**: Base configuration object\n\n#### 2. LightX2V TeaCache\n\nFeature caching acceleration configuration.\n\n- **Inputs**: enable, threshold (0.0-1.0), use_ret_steps\n- **Output**: TeaCache configuration\n- **Note**: Lower threshold = more speedup (0.1 ~2x, 0.2 ~3x)\n\n#### 3. LightX2V Quantization\n\nModel quantization settings for memory efficiency.\n\n- **Inputs**: dit_precision, t5_precision, clip_precision, backend, sensitive_layers_precision\n- **Output**: Quantization configuration\n- **Backends**: Auto-detected (vllm, sgl, q8f)\n\n#### 4. LightX2V Memory Optimization\n\nMemory management strategies.\n\n- **Inputs**: optimization_level, attention_type, enable_rotary_chunking, cpu_offload, unload_after_generate\n- **Output**: Memory optimization configuration\n\n#### 5. LightX2V Lightweight VAE\n\nVAE optimization options.\n\n- **Inputs**: use_tiny_vae, use_tiling_vae\n- **Output**: VAE configuration\n\n#### 6. LightX2V LoRA Loader\n\nLoad and chain LoRA models.\n\n- **Inputs**: lora_name, strength (0.0-2.0), lora_chain (optional)\n- **Output**: LoRA chain configuration\n\n### Combination Node\n\n#### 7. LightX2V Config Combiner\n\nCombines all configuration modules into a single configuration.\n\n- **Inputs**: All configuration types (optional)\n- **Output**: Combined configuration object\n\n### Inference Node\n\n#### 8. LightX2V Modular Inference\n\nMain inference node for video generation.\n\n- **Inputs**: combined_config, prompt, negative_prompt, image (optional), audio (optional)\n- **Outputs**: Generated video frames\n\n## Usage Examples\n\n### Basic T2V Workflow\n\n1. Create LightX2V Inference Config (task_type: \"t2v\")\n2. Use LightX2V Config Combiner\n3. Connect to LightX2V Modular Inference with text prompt\n4. Save video output\n\n### I2V with Optimizations\n\n1. Load input image\n2. Create LightX2V Inference Config (task_type: \"i2v\")\n3. Add LightX2V TeaCache (threshold: 0.26)\n4. Add LightX2V Memory Optimization\n5. Combine configs with LightX2V Config Combiner\n6. Run LightX2V Modular Inference\n\n### With LoRA\n\n1. Create base configuration\n2. Load LoRA with LightX2V LoRA Loader\n3. Chain multiple LoRAs if needed\n4. Combine all configs\n5. Run inference\n\n## Model Directory Structure\n\nDownload models from: \u003chttps://huggingface.co/lightx2v\u003e\n\nModels should be placed in:\n\n```txt\nComfyUI/models/lightx2v/\n├── Wan2.1-I2V-14B-720P-xxx/     # Main model checkpoints\n├── Wan2.1-I2V-14B-480P-xxx/     # Main model checkpoints\n├── loras/          # LoRA models\n```\n\n## Tips\n\n- Start with default settings and adjust based on your hardware\n- Use TeaCache with threshold 0.1-0.2 for significant speedup\n- Enable memory optimization if running on limited VRAM\n- Quantization can reduce memory usage but may affect quality\n- Chain multiple LoRAs for complex style combinations\n\n## Troubleshooting\n\n- **Out of Memory**: Enable memory optimization or use quantization\n- **Slow Generation**: Enable TeaCache or reduce inference steps\n- **Model Not Found**: Check model paths in `ComfyUI/models/lightx2v/`\n\n## Example Workflows\n\nExample workflow JSON files are provided in the `examples/` directory:\n\n- `wan_i2v.json` - Basic image-to-video\n- `wan_i2v_with_distill_lora.json` - I2V with distillation LoRA\n- `wan_t2v_with_distill_lora.json` - T2V with distillation LoRA\n\n## Contributing Guidelines\n\nWe welcome community contributions! Before submitting code, please ensure you follow these steps:\n\n### Install Development Dependencies\n\n```bash\npip install ruff pre-commit\n```\n\n### Code Quality Check\n\nBefore committing code, run the following command:\n\n```bash\npre-commit run --all-files\n```\n\nThis will automatically check code formatting, syntax errors, and other code quality issues.\n\n### Contribution Process\n\n1. Fork this repository\n2. Create a feature branch (`git checkout -b feature/amazing-feature`)\n3. Commit your changes (`git commit -m 'Add some amazing feature'`)\n4. Push to the branch (`git push origin feature/amazing-feature`)\n5. Create a Pull Request\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmodeltc%2Fcomfyui-lightx2vwrapper","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fmodeltc%2Fcomfyui-lightx2vwrapper","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmodeltc%2Fcomfyui-lightx2vwrapper/lists"}