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
- Draw Things
Simple test!
Thanks for the great work! Here are a few test videos I made.
Thank you so much for the test feedback! It looks like there’s still room for improvement. I’m currently experimenting with different training schemes to achieve the best possible results.
fire, liquid, gas , for VFX cinematics .. thank you
In actual testing, this LoRa model demonstrates better compliance than the one on Civitai, and its training dataset is 20 times larger.
please take your time Licon and give us the new lora ur lora has improved the motion quite a lot thank you so much
Sometimes the V3 on Civitai performs much better, such as 360 turn in some cases.
May I ask whether there are any cases involving a moving car and its interaction with the surrounding environment?
May I ask whether there are any cases involving a moving car and its interaction with the surrounding environment?
no,https://video-reason.com/,you could view directly about the dataset from the official website
please take your time Licon and give us the new lora ur lora has improved the motion quite a lot thank you so much
strength ?
Thanks for the great work! Here are a few test videos I made.
at what strength is the lora