Instructions to use Kry4ta1/Effecteraser-VOR-Inference with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use Kry4ta1/Effecteraser-VOR-Inference with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("Kry4ta1/Effecteraser-VOR-Inference", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
Download scripts/infer_2step.sh from Kry4ta1/Effecteraser-VOR-Inference: direct link, hf CLI and curl.
- Browser
- Download file 750 Bytes
-
https://huggingface.co/Kry4ta1/Effecteraser-VOR-Inference/resolve/main/scripts/infer_2step.sh
- Command line
-
hf download hf://Kry4ta1/Effecteraser-VOR-Inference/scripts/infer_2step.sh
-
curl -L -o infer_2step.sh https://huggingface.co/Kry4ta1/Effecteraser-VOR-Inference/resolve/main/scripts/infer_2step.sh
750 Bytes
| set -euo pipefail | |
| ROOT="$(cd "$(dirname "${BASH_SOURCE[0]}")/.." && pwd)" | |
| : "${INPUT_DIR:?Set INPUT_DIR to a directory of input videos}" | |
| : "${MASK_DIR:?Set MASK_DIR to a directory of same-named mask videos}" | |
| OUTPUT_DIR="${OUTPUT_DIR:-$ROOT/outputs/dmd_2step}" | |
| GPU="${GPU:-0}" | |
| PYTHON_BIN="${PYTHON_BIN:-python}" | |
| cd "$ROOT/src" | |
| CUDA_VISIBLE_DEVICES="$GPU" "$PYTHON_BIN" -u infer.py \ | |
| --model_name "$ROOT/checkpoints/dmd_2step" \ | |
| --common_model_name "$ROOT/checkpoints/common" \ | |
| --config_path "$ROOT/configs/wan2.1/wan_civitai.yaml" \ | |
| --lightvae_path "$ROOT/checkpoints/common/lightvae.pth" \ | |
| --skip_lora --dmd_steps 2 --guidance_scale 1.0 \ | |
| --input_dir "$INPUT_DIR" --input_mask_dir "$MASK_DIR" --save_dir "$OUTPUT_DIR" | |