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", torch_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
apple silicon local workflow recommendations
hello!
first of all, thank you for your amazing work.
i'm building a fully local animation pipeline on a macbook pro with apple silicon (m5 pro, 48 gb unified memory) using comfyui desktop.
my goal is creating consistent pixar-style characters for short 5–10 second i2v animations from character sheets, with lip sync added afterward.
i'm currently trying to find the most efficient workflow for this hardware, since optimization on apple silicon is still quite challenging.
would you recommend msr v2 as the primary solution for this workflow, or are there any other models, techniques, or workflows that you would combine with it?
i'd really appreciate your advice.
hello!
first of all, thank you for your amazing work.
i'm building a fully local animation pipeline on a macbook pro with apple silicon (m5 pro, 48 gb unified memory) using comfyui desktop.
my goal is creating consistent pixar-style characters for short 5–10 second i2v animations from character sheets, with lip sync added afterward.
i'm currently trying to find the most efficient workflow for this hardware, since optimization on apple silicon is still quite challenging.
would you recommend msr v2 as the primary solution for this workflow, or are there any other models, techniques, or workflows that you would combine with it?
i'd really appreciate your advice.
If synchronized audio generation isn’t essential for your workflow, I would recommend Bernini instead. However, the main drawback is that it may run quite slowly on your hardware, so I suggest testing both Bernini and MSR V2 and comparing their speed and results on your MacBook.
thanks a lot for the recommendation! i really appreciate your input. i'll start with msr v2, since it seems like the more practical choice for apple silicon. thanks again!