Instructions to use Lightricks/LTX-2.3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use Lightricks/LTX-2.3 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline from diffusers.utils import load_image, export_to_video # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("Lightricks/LTX-2.3", dtype=torch.bfloat16, device_map="cuda") pipe.to("cuda") prompt = "A man with short gray hair plays a red electric guitar." image = load_image( "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/guitar-man.png" ) output = pipe(image=image, prompt=prompt).frames[0] export_to_video(output, "output.mp4") - LTX.io
How to use Lightricks/LTX-2.3 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 Lightricks/LTX-2.3 --local-dir models/LTX-2.3 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-2.3/<distilled-checkpoint>.safetensors \ --spatial-upsampler-path models/LTX-2.3/<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-2.3/<checkpoint>.safetensors \ --distilled-lora models/LTX-2.3/<distilled-lora>.safetensors 0.8 \ --spatial-upsampler-path models/LTX-2.3/<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
Why is it impossible to control the volume of speaking characters?
Example
I tried every possible combination of "talk really quietly" I could think of, then asked Gemma 26B A4B for more, tried probably 20 combinations of various takes on “whisper" and "murmur". The result? Literally impossibly to change the volume of spoken audio, nor is it possible to change speaking distance.
Example:
Person on other side of room sounds like they are right next to the primary camera subject. No "speaks softly" or "from a distance" logic works.
Please advise, and fix. I couldn't even find a place to report this as a bug, so I guess this will have to do.
For anyone that wants to propose I just bring my own audio, yes I'm aware that can be done, and no, I don't think it's a reasonable ask. A pretty glaring bug exists, so the community is seeking remedy.
yeah no whispering 😁