Instructions to use Alissonerdx/LTX-LoRAs with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- LTX-2
How to use Alissonerdx/LTX-LoRAs with LTX-2:
# 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 Alissonerdx/LTX-LoRAs --local-dir models/LTX-LoRAs hf download google/gemma-3-12b-it-qat-q4_0-unquantized --local-dir models/gemma-3-12b
# Text/image-to-video with the LoRA on the HQ two-stage base pipeline uv run python -m ltx_pipelines.ti2vid_two_stages_hq \ --checkpoint-path path/to/checkpoint.safetensors \ --distilled-lora path/to/distilled_lora.safetensors 0.8 \ --spatial-upsampler-path path/to/spatial_upsampler.safetensors \ --gemma-root models/gemma-3-12b \ --lora models/LTX-LoRAs/<weights>.safetensors 1.0 \ --prompt "your prompt here" \ --output-path output.mp4 # For image-to-video, add: --image path/to/image.jpg 0 0.8 - Notebooks
- Google Colab
- Kaggle
what fails is
i have a fast action fighting scene. trying to remove the sunglass on one character fails.. it cannot detect it at all..
to be practically usefull. need difficult footages.
Thank you for for the future updates
replace the dog walking on the beach to a Tiger.. Fails
replace the background to a jungle with volcano eruption in the distant mountain. Fails
so only generic objects and items works well
Remove the sunglass on her face .. Works
Replace the shirt with Coat : Works
Yes, this wasn't designed to replace backgrounds. Sometimes you'll need to increase the CFG and there's a caption standard; you need to describe the exact location of the object you want to replace. If you don't follow the correct way to write the prompt, it will be difficult to make it work. For example, if the object are in front, use foreground ... background, left, right, top, bottom.
Yes, this wasn't designed to replace backgrounds. Sometimes you'll need to increase the CFG and there's a caption standard; you need to describe the exact location of the object you want to replace. If you don't follow the correct way to write the prompt, it will be difficult to make it work. For example, if the object are in front, use foreground ... background, left, right, top, bottom.
thanks il try increasing.. CFG.. btw it works great on the generic items on the dataset you mention.. I hope to see more variety of dataset in the future.. thank you for this wonderful Lora