Instructions to use hgjc/ltx-ugc-bundle with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- LTX.io
How to use hgjc/ltx-ugc-bundle with LTX.io:
# Install the LTX-2 pipelines git clone https://github.com/Lightricks/LTX-2.git cd LTX-2 uv sync --frozen
# Download the weights from this repo, plus the Gemma text encoder hf download hgjc/ltx-ugc-bundle --local-dir models/ltx-ugc-bundle hf download google/gemma-3-12b-it-qat-q4_0-unquantized --local-dir models/gemma-3-12b
# Fast pipeline (distilled model, no distilled LoRA needed) uv run python -m ltx_pipelines.distilled \ --distilled-checkpoint-path models/ltx-ugc-bundle/<distilled-checkpoint>.safetensors \ --spatial-upsampler-path models/ltx-ugc-bundle/<spatial-upsampler>.safetensors \ --gemma-root models/gemma-3-12b \ --prompt "A beautiful sunset over the ocean" \ --output-path output.mp4 # For image-to-video, add: --image path/to/image.jpg 0 0.8# HQ pipeline (two-stage, higher quality) uv run python -m ltx_pipelines.ti2vid_two_stages_hq \ --checkpoint-path models/ltx-ugc-bundle/<checkpoint>.safetensors \ --distilled-lora models/ltx-ugc-bundle/<distilled-lora>.safetensors 0.8 \ --spatial-upsampler-path models/ltx-ugc-bundle/<spatial-upsampler>.safetensors \ --gemma-root models/gemma-3-12b \ --prompt "A beautiful sunset over the ocean" \ --output-path output.mp4 # For image-to-video, add: --image path/to/image.jpg 0 0.8 - Notebooks
- Google Colab
- Kaggle
| import { app } from "../../../scripts/app.js"; | |
| import { api } from "../../../scripts/api.js"; | |
| // Adds a menu option to toggle follow the executing node | |
| // Adds a menu option to go to the currently executing node | |
| // Adds a menu option to go to a node by type | |
| app.registerExtension({ | |
| name: "pysssss.NodeFinder", | |
| setup() { | |
| let followExecution = false; | |
| const centerNode = (id) => { | |
| if (!followExecution || !id) return; | |
| const node = app.graph.getNodeById(id); | |
| if (!node) return; | |
| app.canvas.centerOnNode(node); | |
| }; | |
| api.addEventListener("executing", ({ detail }) => centerNode(detail)); | |
| // Add canvas menu options | |
| const orig = LGraphCanvas.prototype.getCanvasMenuOptions; | |
| LGraphCanvas.prototype.getCanvasMenuOptions = function () { | |
| const options = orig.apply(this, arguments); | |
| options.push(null, { | |
| content: followExecution ? "Stop following execution" : "Follow execution", | |
| callback: () => { | |
| if ((followExecution = !followExecution)) { | |
| centerNode(app.runningNodeId); | |
| } | |
| }, | |
| }); | |
| if (app.runningNodeId) { | |
| options.push({ | |
| content: "Show executing node", | |
| callback: () => { | |
| const node = app.graph.getNodeById(app.runningNodeId); | |
| if (!node) return; | |
| app.canvas.centerOnNode(node); | |
| }, | |
| }); | |
| } | |
| const nodes = app.graph._nodes; | |
| const types = nodes.reduce((p, n) => { | |
| if (n.type in p) { | |
| p[n.type].push(n); | |
| } else { | |
| p[n.type] = [n]; | |
| } | |
| return p; | |
| }, {}); | |
| options.push({ | |
| content: "Go to node", | |
| has_submenu: true, | |
| submenu: { | |
| options: Object.keys(types) | |
| .sort() | |
| .map((t) => ({ | |
| content: t, | |
| has_submenu: true, | |
| submenu: { | |
| options: types[t] | |
| .sort((a, b) => { | |
| return a.pos[0] - b.pos[0]; | |
| }) | |
| .map((n) => ({ | |
| content: `${n.getTitle()} - #${n.id} (${n.pos[0]}, ${n.pos[1]})`, | |
| callback: () => { | |
| app.canvas.centerOnNode(n); | |
| }, | |
| })), | |
| }, | |
| })), | |
| }, | |
| }); | |
| return options; | |
| }; | |
| }, | |
| }); | |