Instructions to use TenStrip/LTX2.3-10Eros with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use TenStrip/LTX2.3-10Eros with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline from diffusers.utils import load_image, export_to_video # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("TenStrip/LTX2.3-10Eros", dtype=torch.bfloat16, device_map="cuda") pipe.to("cuda") prompt = "A man with short gray hair plays a red electric guitar." image = load_image( "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/guitar-man.png" ) output = pipe(image=image, prompt=prompt).frames[0] export_to_video(output, "output.mp4") - Notebooks
- Google Colab
- Kaggle
Gguf please
#5
by ryg81 - opened
Hey, any chance for gguf models?
It seems very complex, main issue is that the data changes tensor dimension and comfyui gguf loaders do not like to see that when loading an LTX model with those shapes from my attempts.
darn.. hope something can be figured out. those of us VRAM poor plebs would be in gratitude.
https://huggingface.co/vantagewithai/LTX2.3-10Eros-GGUF/tree/main I linked them on the main page a while back. Didn't try any of them but I assume theres quality loss.
Oops didn't catch the update. Thank you for the notice.
Time to do some testing !