Instructions to use VAST-AI/EdenLive-14B-Causal-Diffusers with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use VAST-AI/EdenLive-14B-Causal-Diffusers 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("VAST-AI/EdenLive-14B-Causal-Diffusers", 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
|
Download proxy_encoder/NOTICE.md from VAST-AI/EdenLive-14B-Causal-Diffusers: direct link, hf CLI and curl.
- Browser
- Download file 895 Bytes
-
https://huggingface.co/VAST-AI/EdenLive-14B-Causal-Diffusers/resolve/main/proxy_encoder/NOTICE.md
- Command line
-
hf download hf://VAST-AI/EdenLive-14B-Causal-Diffusers/proxy_encoder/NOTICE.md
-
curl -L -o NOTICE.md https://huggingface.co/VAST-AI/EdenLive-14B-Causal-Diffusers/resolve/main/proxy_encoder/NOTICE.md
895 Bytes
Converted checkpoint layout
The paths in the original notice below refer to the DINOv3 backbone and projection. In this Diffusers checkpoint, those files are located at:
proxy_encoder/model.safetensors(originalbackbone/)transformer/diffusion_pytorch_model-proxy-projection.safetensors(originalprojection.safetensors)
The original notice is retained below.
NOTICE — vision-encoder
The weights in this directory (backbone/ and projection.safetensors) are DINOv3 by
Meta Platforms, Inc. or derivative works of it made by Vast AI. They are distributed under
the DINOv3 License (see LICENSE.md here and in backbone/), not under the Apache 2.0
license that covers the rest of this repository. Use must comply with that license,
including its trade-control and prohibited-use terms. Research publications that use these
weights must acknowledge the use of DINOv3.