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
Hard to prompt on 1.3
#49
by justinone123 - opened
Firstly, congrats on the quality upgrade in 1.3, it's incredible.
However, I'm finding it really difficult to prompt on it. Previous versions work absolutely fine using the same prompts, but this one is really stubborn.
Any tips? Less is more? I'm trying to be as direct as possible.
justinone123 changed discussion status to closed
justinone123 changed discussion status to open
It prompts way more like base, I put a solid default enhancer on the workflow textbox it likes to take those default style base prompts. These kinds of cinematic prompts: https://maxvideoai.com/examples/ltx
Not gonna matter for long it's just a temporary floor model to fix the problems in v1.2.