Instructions to use LiconStudio/Ltx2.3-VBVR-lora-I2V with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use LiconStudio/Ltx2.3-VBVR-lora-I2V with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("Lightricks/LTX-2.3", dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("LiconStudio/Ltx2.3-VBVR-lora-I2V") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
Update for ltx 2.5?
Please? Some day?
I think this lora can be loaded by 2.5 directly, try that first.
I think this lora can be loaded by 2.5 directly, try that first.
I did, I'm using it all the time actually. I just thought that since it was a massive must have for ltx 2.3 maybe we can get an update specifically for ltx 2.5
I think this lora can be loaded by 2.5 directly, try that first.
I did, I'm using it all the time actually. I just thought that since it was a massive must have for ltx 2.3 maybe we can get an update specifically for ltx 2.5
Actually, based on my testing, using LTX 2.5 as the base model for training doesn't necessarily produce better results than 2.3. I may still train a 2.5-specific version and see how it goes in the future, but probably not anytime soon, as I have quite a few other projects lined up with limited compute resources.