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
10Eros_10SNodes_TripleSample_I2V First Pass issue
#7
by WarTourist - opened
Hey, great stuff. I couldn't get anything but the first pass working on 10Eros_10SNodes_TripleSample_I2V until I wired the denoised_output from the First Pass node into the LTXVSeparateAVLatent node. From hf, the output what was wired, not the denoised version. I wondered why the music video did all three passes, and that was what jumped out at me. Hope that helps someone!![[37%][31%] SamplerCustomAdvanced - Google Chrome 5_4_2026 8_25_58 PM](https://cdn-uploads.huggingface.co/production/uploads/68bcc5215ebc9deb25ab1d93/ZkY63e8s5awI0p2guBIZK.png)
I will adjust that. I did both paths in testing and both worked on my version but that may cause issues on other setups.