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
LOVE IT!!!!! GREAT WORK
Thank you for this great work, i made some minor changes, on your base workflow, and optimize it a little :-)
Thank you again...
https://civitai.com/models/2992309/ltx-25-multi-reference-image-workflow-msr
If i can help in anyway, just tell me!!!
also i made a workflow to quickly create the images that is used by your model.
you can find it here: https://civitai.com/models/2987948/blazing-fast-character-multiangles-flux2-with-ltx-ic-lora-reference-sheet-description
Thank you for this great work, i made some minor changes, on your base workflow, and optimize it a little :-)
Thank you again...https://civitai.com/models/2992309/ltx-25-multi-reference-image-workflow-msr
If i can help in anyway, just tell me!!!
also i made a workflow to quickly create the images that is used by your model.
you can find it here: https://civitai.com/models/2987948/blazing-fast-character-multiangles-flux2-with-ltx-ic-lora-reference-sheet-description
Thanks so much for sharing these! I really appreciate you optimizing the workflow and putting together another one for creating reference images. You’re already helping a lot by sharing these with the community! 😊
Feedback from different setups is always valuable, so please let me know about any issues you run into or ideas for improvement. Thanks again for supporting MSR!