Instructions to use VAST-AI/EdenLive-14B-Diffusers with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use VAST-AI/EdenLive-14B-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-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 image_processor/NOTICE.md from VAST-AI/EdenLive-14B-Diffusers: direct link, hf CLI and curl.
- Browser
- Download file 708 Bytes
-
https://huggingface.co/VAST-AI/EdenLive-14B-Diffusers/resolve/main/image_processor/NOTICE.md
- Command line
-
hf download hf://VAST-AI/EdenLive-14B-Diffusers/image_processor/NOTICE.md
-
curl -L -o NOTICE.md https://huggingface.co/VAST-AI/EdenLive-14B-Diffusers/resolve/main/image_processor/NOTICE.md
708 Bytes
NOTICE — clip
The image encoder originates from LAION CLIP ViT-H/14 trained on LAION-2B using OpenCLIP, by Romain Beaumont on Stability AI compute: https://huggingface.co/laion/CLIP-ViT-H-14-laion2B-s32B-b79K
The upstream model card declares the MIT license. The original OpenCLIP MIT permission and copyright notice are reproduced in LICENSE.md: https://github.com/mlfoundations/open_clip/blob/main/LICENSE
Conversion into a Diffusers-compatible component does not remove the original MIT attribution. EdenLive's Apache-2.0 code license does not replace the MIT license applicable to this component. Processing and loading use the separately licensed Hugging Face Transformers / Diffusers libraries.