{"id":28578380,"url":"https://github.com/lightricks/ltx-video-q8-kernels","last_synced_at":"2025-06-11T01:09:49.716Z","repository":{"id":292094553,"uuid":"978201483","full_name":"Lightricks/LTX-Video-Q8-Kernels","owner":"Lightricks","description":null,"archived":false,"fork":false,"pushed_at":"2025-05-14T15:07:30.000Z","size":63,"stargazers_count":49,"open_issues_count":12,"forks_count":7,"subscribers_count":3,"default_branch":"master","last_synced_at":"2025-06-06T03:52:01.536Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/Lightricks.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"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":"2025-05-05T16:13:06.000Z","updated_at":"2025-06-04T01:51:21.000Z","dependencies_parsed_at":"2025-05-08T06:13:57.809Z","dependency_job_id":"b4ff49e3-6ba1-4a2b-875b-05ced822aa76","html_url":"https://github.com/Lightricks/LTX-Video-Q8-Kernels","commit_stats":null,"previous_names":["lightricks/ltx-video-q8-kernels"],"tags_count":1,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Lightricks%2FLTX-Video-Q8-Kernels","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Lightricks%2FLTX-Video-Q8-Kernels/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Lightricks%2FLTX-Video-Q8-Kernels/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Lightricks%2FLTX-Video-Q8-Kernels/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Lightricks","download_url":"https://codeload.github.com/Lightricks/LTX-Video-Q8-Kernels/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Lightricks%2FLTX-Video-Q8-Kernels/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":259178542,"owners_count":22817388,"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","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":[],"created_at":"2025-06-11T01:09:45.868Z","updated_at":"2025-06-11T01:09:49.704Z","avatar_url":"https://github.com/Lightricks.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"\n### LTXVideo Q8 – `q8_kernels`\n\nThis package implements the operations required to perform inference with the LTXVideo FP8-quantized model.\n\n---\n\n## 📚 Table of Contents\n\n- [Installation](#-installation)\n  - [Windows](#-windows)\n    - [Cloned ComfyUI](#-cloned-comfyui)\n    - [Portable ComfyUI](#-portable-comfyui)\n  - [Linux](#-linux)\n  - [Troubleshooting](#-troubleshooting)\n- [ComfyUI Integration](#-comfyui-integration)\n\n---\n\n### 🔧 Installation\n\n\u003e **Note:** CUDA Toolkit **12.8 or later** is required. The instructions below assume CUDA 12.8 is installed.\n\n---\n\n#### 🪟 Windows\n\n1. Install the **[Microsoft Build Tools](https://visualstudio.microsoft.com/downloads/?q=build+tools#build-tools-for-visual-studio-2022)**.  \n   During installation, select **\"Desktop development with C++\"**.\n\n2. Make sure the **CUDA Toolkit** is installed by following the instructions [here](https://docs.nvidia.com/cuda/cuda-installation-guide-microsoft-windows/index.html).\n\n---\n\n##### 📦 Cloned ComfyUI\n1. Run the following commands inside your ComfyUI python environment.\n\n   ```bash\n   python.exe -m pip install -U torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu128\n\n   python.exe -m pip install -U packaging wheel ninja setuptools\n\n   python.exe -m pip install --no-build-isolation git+https://github.com/Lightricks/LTX-Video-Q8-Kernels.git\n   ```\n\n##### 📦 Portable ComfyUI\n\n1. Open a **Command Prompt** in the portable ComfyUI installation folder.\n\n2. Check the version of the embedded Python:\n   ```bash\n   .\\python_embeded\\python.exe --version\n   ```\n\n3. Install the matching Python version (e.g., 3.12.10):\n   - Download from the [official Python website](https://www.python.org/downloads/windows/),  \n     or use [pyenv for Windows](https://github.com/pyenv-win/pyenv-win?tab=readme-ov-file#installation).\n\n4. Locate your Python installation.  \n   If installed from official Python website, it is typically located at:  \n   `C:\\Users\\YOUR_USERNAME\\AppData\\Local\\Programs\\Python\\Python312`\n\n5. Copy the `include` and `libs` directories from the full Python installation into the `python_embeded` folder in your ComfyUI directory.\n\n6. Run the following commands in the Command Prompt:\n\n   ```bash\n   .\\python_embeded\\python.exe -m pip install -U torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu128\n\n   .\\python_embeded\\python.exe -m pip install -U packaging wheel ninja setuptools\n\n   .\\python_embeded\\python.exe -m pip install --no-build-isolation git+https://github.com/Lightricks/LTX-Video-Q8-Kernels.git\n   ```\n\n---\n\n#### 🐧 Linux\n\n1. Make sure the **CUDA Toolkit** is installed using the instructions [here](https://docs.nvidia.com/cuda/cuda-installation-guide-linux/).  \n   \u003e Your CUDA version must match the version used by your installed PyTorch (e.g., CUDA 12.8).\n\n2. Run the following commands in your ComfyUI Python environment:\n\n   ```bash\n   pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu128\n   pip install packaging wheel ninja setuptools\n   pip install --no-build-isolation git+https://github.com/Lightricks/LTX-Video-Q8-Kernels.git\n   ```\n\n---\n\n#### 🧩 Troubleshooting\n\n- If you encounter issues with the `typing-extensions` package, run:\n\n  ```bash\n  pip install typing-extensions\n  ```\n\n  Then repeat the installation steps.\n\n---\n\n### 🎥 ComfyUI Integration\n\nTo run inference with ComfyUI:\n \n1. Install the **[ComfyUI-LTXVideo](https://github.com/Lightricks/ComfyUI-LTXVideo)** custom nodes pack.\n2. Use the **LTXVideo Q8 Patcher** node on the loaded model.\n3. See the example ComfyUI flow [here](https://github.com/Lightricks/ComfyUI-LTXVideo/blob/fa234963e5b24d11085dfdb8a51cf6d38d73472c/example_workflows/ltxv-13b-i2v-base-fp8.json).","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Flightricks%2Fltx-video-q8-kernels","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Flightricks%2Fltx-video-q8-kernels","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Flightricks%2Fltx-video-q8-kernels/lists"}