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", 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
MSR and Prompt Relay
Hi... I've made other good tests with your Lora and now the main human character is perfect.
But not the dog that is still not consistent with the reference image.
I will try now RUNEXX workflow of MSR to see if the dog works.
Other thing you said that some people would have made a Prompt Relay Workflow including MSR but I did not find anything and Rune has not done it.
If you have any link to that workflow it would be perfect.
Thank you.
I have one from hugging face, but I havent tested yet, I may publish it in the model file once it passed my test. Or, you could try to find it on huggingface.
Hi... I've made other good tests with your Lora and now the main human character is perfect.
But not the dog that is still not consistent with the reference image.
I will try now RUNEXX workflow of MSR to see if the dog works.Other thing you said that some people would have made a Prompt Relay Workflow including MSR but I did not find anything and Rune has not done it.
If you have any link to that workflow it would be perfect.
Thank you.