Instructions to use LiconStudio/LTX-2.5-Multiple-Subject-Reference with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use LiconStudio/LTX-2.5-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-2.5-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
Voice references
#4
by vashadow - opened
I would also love to see this handle a way to import an audio clip of the characters voice so I can keep that consistent as well. Believe it or not I am finding out that voice consistency is the hardest part of overall consistency.
I would also love to see this handle a way to import an audio clip of the characters voice so I can keep that consistent as well. Believe it or not I am finding out that voice consistency is the hardest part of overall consistency.
I've already solved it actually, still testing, will release it couple weeks later.