Over++: Generative Video Compositing for Layer Interaction Effects
Paper • 2512.19661 • Published • 12
import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("luchaoqi/overplusplus", dtype=torch.bfloat16, device_map="cuda")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]Over++: Generative Video Compositing for Layer Interaction Effects
Overview
This Hugging Face repository contains the transformer weights for the model used in the CogVideo pipeline here.
You can load the transformer weights using the command below:
python inference/cogvideox_fun/predict_v2v.py \
--config.experiment.save_foreground=True \
--config.experiment.save_path="output_temp" \
--config.data.data_rootdir="examples" \
--config.experiment.run_seqs="boy-water,pexles_car_drift" \
--config.experiment.skip_if_exists=False \
--config.data.dilate_width=0 \
--config.video_model.guidance_scale=6 \
--config.video_model.transformer_path="PATH/TO/CHECKPOINTS/diffusion_pytorch_model.safetensors"
For more details, please refer to the GitHub repository here
- Downloads last month
- 3
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support