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
Correct way to prompt?
#27
by Decadence-1 - opened
It's somewhat unclear how to prompt correctly:
- how do title characters correctly? I've seen people using names, character1, image1, etc. Does it matter?
- how to structure prompt correctly, introduce character description inside prompt on in separate "intro"?
Decadence-1 changed discussion title from Correct way to prompt. to Correct way to prompt?
It's somewhat unclear how to prompt correctly:
- how do title characters correctly? I've seen people using names, character1, image1, etc. Does it matter?
- how to structure prompt correctly, introduce character description inside prompt on in separate "intro"?
There is no strict format for prompts. You can use character names, “image1,” or any other labels, as long as the naming remains consistent throughout the prompt. You can also refer to the prompt structure used in my validation files as an example.