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
2 stage workflow
#2
by CoachBate - opened
Your github nodes mention several steps to do the two stages sampling but those aren't trivial. Please provide another workflow with your examples.
Your github nodes mention several steps to do the two stages sampling but those aren't trivial. Please provide another workflow with your examples.
The included sample workflow is already a complete two-stage workflow. The “Two-stage latent upscaling” section in the README is only explaining the internal sampling flow, not additional steps that need to be built manually. You can directly use LTX2.5-MSR-sample-workflow.json as the two-stage example.