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
New 10Eros_v1.3 checkpoint
#46
by LokkenJP - opened
Hello. I've seen you've updated 10Eros to a v3 version.
Also seen this is being used on the new DMD workflow. I'm trying to figure that out, but meanwhile, it's ok to use the new v3 checkpoint on your older basic v4 workflow? (so far v4 has been the most stable and better quality of the workflows you've uploaded in my setup)
For v1.3 it's designed from ground up for using the DMD lora. Not sure what kind of outputs will be with distilled lora but I'm entirely sure they're not as good.