Dilated Controlnet for Wan2.1 (hed)
This repo contains the code for dilated controlnet module for Wan2.1 model.
Dilated controlnet has less basic blocks and also has stride parameter. For Wan14B model controlnet blocks count = 6 and stride = 4.
See Github code.
How to
Clone repo
git clone https://github.com/TheDenk/wan2.1-dilated-controlnet.git
cd wan2.1-dilated-controlnet
Create venv
python -m venv venv
source venv/bin/activate
Install requirements
pip install -r requirements.txt
Inference examples
Inference with cli
python -m inference.cli_demo \
--video_path "resources/physical-4.mp4" \
--prompt "A balloon filled with water was thrown to the ground, exploding and splashing water in all directions. There were graffiti on the wall, studio lighting, and commercial movie shooting." \
--controlnet_type "hed" \
--controlnet_stride 4 \
--base_model_path Wan-AI/Wan2.1-T2V-14B-Diffusers \
--controlnet_model_path TheDenk/wan2.1-t2v-14b-controlnet-hed-v1
Inference with Gradio
python -m inference.gradio_web_demo \
--controlnet_type "hed" \
--base_model_path Wan-AI/Wan2.1-T2V-14B-Diffusers \
--controlnet_model_path TheDenk/wan2.1-t2v-14b-controlnet-hed-v1
Detailed Inference
python -m inference.cli_demo \
--video_path "resources/physical-4.mp4" \
--prompt "A balloon filled with water was thrown to the ground, exploding and splashing water in all directions. There were graffiti on the wall, studio lighting, and commercial movie shooting." \
--controlnet_type "hed" \
--base_model_path Wan-AI/Wan2.1-T2V-14B-Diffusers \
--controlnet_model_path TheDenk/wan2.1-t2v-14b-controlnet-hed-v1 \
--controlnet_weight 0.8 \
--controlnet_guidance_start 0.0 \
--controlnet_guidance_end 0.8 \
--controlnet_stride 4 \
--num_inference_steps 50 \
--guidance_scale 5.0 \
--video_height 480 \
--video_width 832 \
--num_frames 81 \
--negative_prompt "Bright tones, overexposed, static, blurred details, subtitles, style, works, paintings, images, static, overall gray, worst quality, low quality, JPEG compression residue, ugly, incomplete, extra fingers, poorly drawn hands, poorly drawn faces, deformed, disfigured, misshapen limbs, fused fingers, still picture, messy background, three legs, many people in the background, walking backwards" \
--seed 42 \
--out_fps 16 \
--output_path "result.mp4"
Acknowledgements
Original code and models Wan2.1.
Citations
@misc{TheDenk,
title={Dilated Controlnet},
author={Karachev Denis},
url={https://github.com/TheDenk/wan2.1-dilated-controlnet},
publisher={Github},
year={2025}
}