GeoFlow

This repository contains a standalone sampler for generating videos with the GeoFlow LoRA on top of Wan2.1.

Release Checklist

• Release model weights
• Release inference code
• Release eval code
• Release reward model code

Setup

Install the Python dependencies:

pip install -r requirements.txt

Download the GeoFlow checkpoint from Hugging Face:

https://huggingface.co/ackermannj/geoflow

For example, with the Hugging Face CLI:

huggingface-cli download ackermannj/geoflow --local-dir checkpoints/geoflow

Create a prompt file with one prompt per line:

printf "A camera moves forward through a narrow stone alley at sunset.\\n" > prompts.txt

Sampling

Run the sampler with accelerate:

accelerate launch --num_processes 1 scripts/inference/sample_videos.py \
    --model_path wan-ai/Wan2.1-T2V-1.3B-Diffusers \
    --lora_path checkpoints/geoflow \
    --prompt_file prompts.txt \
    --output_dir generations/geoflow \
    --height 480 \
    --width 832 \
    --num_frames 81 \
    --num_inference_steps 50 \
    --mixed_precision bf16

For multi-GPU sampling, increase --num_processes. Prompts are split across processes automatically.

The sampler supports .txt prompt files and .jsonl files containing a "prompt" field.