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
I2V Consistency
#15
by svippixel - opened
Hello author, could you please tell me what prompts I should add to maintain consistency in the figures in the image? Thank you.
Unique face likenesses will always be changed with dialogue usually. You pretty much have to have an end frame guide with the same character to maintain it. My next node plan is a likeness guider which will try to add targeted conditioning with a separate image or reference, I wanna see if that can work.
OK, thanks
This comment has been hidden (marked as Low Quality)
Ella se quita la ropa y se menea sensualmente