VAST-AI/EdenLive-14B-Diffusers

EdenLive 14B — Diffusers

EdenLive generates video from a proxy video, a reference image, and a text prompt. This repository includes the 14B bidirectional and causal models for Diffusers.

Usage

Install the EdenLive integration and dependencies:

pip install "git+https://github.com/skygoo2000/diffusers.git@edenlive" \
  torch torchvision "transformers>=4.56.0" accelerate sentencepiece ftfy imageio imageio-ffmpeg

Prepare a reference image and a proxy video with at least 49 frames sampled at 16 fps.

import torch
from diffusers import EdenLivePipeline
from diffusers.utils import export_to_video, load_image, load_video

pipe = EdenLivePipeline.from_pretrained(
    "VAST-AI/EdenLive-14B-Diffusers",
    torch_dtype={"default": torch.bfloat16, "proxy_encoder": torch.float32, "proxy_projection": torch.float32},
).to("cuda")

frames = pipe(
    image=load_image("reference.png"),
    video=load_video("proxy-16fps.mp4"),
    prompt="A character explores a snowy landscape.",
    num_frames=49,
).frames[0]
export_to_video(frames, "edenlive.mp4", fps=16)

See the usage guide for causal generation, dynamic prompts, and LightTAE, and the inference examples for multi-GPU usage.

License

EdenLive components use Apache 2.0. DINOv3 components are covered by the DINOv3 License. CLIP components use the MIT license.