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
| # Hack: string type that is always equal in not equal comparisons | |
| class AnyType(str): | |
| def __ne__(self, __value: object) -> bool: | |
| return False | |
| # Our any instance wants to be a wildcard string | |
| any = AnyType("*") | |
| class Repeater: | |
| def INPUT_TYPES(s): | |
| return {"required": { | |
| "source": (any, {}), | |
| "repeats": ("INT", {"min": 0, "max": 5000, "default": 2}), | |
| "output": (["single", "multi"], {}), | |
| "node_mode": (["reuse", "create"], {}), | |
| }} | |
| RETURN_TYPES = (any,) | |
| FUNCTION = "repeat" | |
| OUTPUT_NODE = False | |
| OUTPUT_IS_LIST = (True,) | |
| CATEGORY = "utils" | |
| def repeat(self, repeats, output, node_mode, **kwargs): | |
| if output == "multi": | |
| # Multi outputs are split to indiviual nodes on the frontend when serializing | |
| return ([kwargs["source"]],) | |
| elif node_mode == "reuse": | |
| # When reusing we have a single input node, repeat that N times | |
| return ([kwargs["source"]] * repeats,) | |
| else: | |
| # When creating new nodes, they'll be added dynamically when the graph is serialized | |
| return ((list(kwargs.values())),) | |
| NODE_CLASS_MAPPINGS = { | |
| "Repeater|pysssss": Repeater, | |
| } | |
| NODE_DISPLAY_NAME_MAPPINGS = { | |
| "Repeater|pysssss": "Repeater 🐍", | |
| } | |