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
Transformer only
#48
by Privac - opened
Can we have a high quality bf16/fp32 transformer only version of the model like any other models used in ComfyUI and that people can easily quantize themselves instead of a low quality, huge prepacked checkpoint?
Transformer is easily lifted out of the bf16, but detaching it from the text projections and using the base model's text projections severely effects nsfw outputs and audio.
Is it possible to lift both the transformer and your text projections out then? I know a lot of people benefit from being able to load models separately in comfy
For anybody wondering you can get the split files here https://huggingface.co/AX1Y2JP/LTX2.3-10Eros_split
Privac changed discussion title from V1.3 Transformer only to Transformer only
Privac changed discussion status to closed