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_all.sh from Kry4ta1/Effecteraser-VOR-Inference: direct link, hf CLI and curl.
- Browser
- Download file 622 Bytes
-
https://huggingface.co/Kry4ta1/Effecteraser-VOR-Inference/resolve/main/scripts/infer_all.sh
- Command line
-
hf download hf://Kry4ta1/Effecteraser-VOR-Inference/scripts/infer_all.sh
-
curl -L -o infer_all.sh https://huggingface.co/Kry4ta1/Effecteraser-VOR-Inference/resolve/main/scripts/infer_all.sh
622 Bytes
| set -euo pipefail | |
| ROOT="$(cd "$(dirname "${BASH_SOURCE[0]}")/.." && pwd)" | |
| : "${INPUT_DIR:?Set INPUT_DIR to a directory of input videos}" | |
| : "${MASK_DIR:?Set MASK_DIR to a directory of same-named mask videos}" | |
| GPU_1STEP="${GPU_1STEP:-0}" | |
| GPU_2STEP="${GPU_2STEP:-1}" | |
| GPU="$GPU_1STEP" OUTPUT_DIR="${OUTPUT_DIR_1STEP:-$ROOT/outputs/dmd_1step}" \ | |
| bash "$ROOT/scripts/infer_1step.sh" > "$ROOT/infer_1step.log" 2>&1 & | |
| pid1=$! | |
| GPU="$GPU_2STEP" OUTPUT_DIR="${OUTPUT_DIR_2STEP:-$ROOT/outputs/dmd_2step}" \ | |
| bash "$ROOT/scripts/infer_2step.sh" > "$ROOT/infer_2step.log" 2>&1 & | |
| pid2=$! | |
| wait "$pid1" | |
| wait "$pid2" | |