Instructions to use LiconStudio/LTX-2.3-Multiple-Subject-Reference with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use LiconStudio/LTX-2.3-Multiple-Subject-Reference with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("LiconStudio/LTX-2.3-Multiple-Subject-Reference", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
Like seedance2
I just moved the 3 nodes from the examples to the default LTX workflow, loaded your lora, and the results are really good—similar to Seedance2. We only need reference images and prompts (which must carefully describe the reference images) to generate a video. Thank you so much! I'm looking forward to your next version.
I just moved the 3 nodes from the examples to the default LTX workflow, loaded your lora, and the results are really good—similar to Seedance2. We only need reference images and prompts (which must carefully describe the reference images) to generate a video. Thank you so much! I'm looking forward to your next version.
Thank you for your feedback, the prompt relay node may stronger your result as my further test.

