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
It it possible to remove the PromptRelay in workflow ?
#26
by makao008 - opened
Hi, as title.
I want to use the Ltx Gemma API to save vgram (no need to download and run text encoder, encode the prompt with online API).
Hi, as title.
I want to use the Ltx Gemma API to save vgram (no need to download and run text encoder, encode the prompt with online API).
Yes of course, but the normal clip node performs worse than prompt relay as my test.