wan2.2-t2v-a14b-controlnet-hed-v1

Controlnet for Wan2.2 A14B (hed)

This repo contains the code for controlnet module for Wan2.2. See <a href="https://github.com/TheDenk/wan2.2-controlnet">Github code</a>.
Same approach as controlnet for Wan2.1.

<video controls autoplay src="https://cdn-uploads.huggingface.co/production/uploads/63fde49f6315a264aba6a7ed/4XS5ZzMUtOuua01D6qDfX.mp4"></video>

For ComfyUI

Use the cool ComfyUI-WanVideoWrapper.
<img width="600" height="480" alt="t2i_workflow" src="https://github.com/user-attachments/assets/4788c2d0-8ff0-405e-9b6d-0e0b1347865b" />
The latest version of the diffusers is required.
You can install it like this:

pip install git+https://github.com/huggingface/diffusers.git

Inference examples

Simple inference with cli

python -m inference.cli_demo \
    --video_path "resources/bubble.mp4" \
    --prompt "Close-up shot with soft lighting, focusing sharply on the lower half of a young woman's face. Her lips are slightly parted as she blows an enormous bubblegum bubble. The bubble is semi-transparent, shimmering gently under the light, and surprisingly contains a miniature aquarium inside, where two orange-and-white goldfish slowly swim, their fins delicately fluttering as if in an aquatic universe. The background is a pure light blue color." \
    --controlnet_type "hed" \
    --base_model_path Wan-AI/Wan2.2-T2V-A14B \
    --controlnet_model_path TheDenk/wan2.2-t2v-a14b-controlnet-hed-v1

Minimal code example

import os
os.environ['CUDA_VISIBLE_DEVICES'] = "0"
os.environ["TOKENIZERS_PARALLELISM"] = "false"

import torch
from diffusers.utils import load_video, export_to_video
from diffusers import AutoencoderKLWan, UniPCMultistepScheduler
from controlnet_aux import MidasDetector

from wan_controlnet import WanControlnet
from wan_transformer import CustomWanTransformer3DModel
from wan_t2v_controlnet_pipeline import WanTextToVideoControlnetPipeline

base_model_path = "Wan-AI/Wan2.2-T2V-A14B"
controlnet_model_path = "TheDenk/wan2.2-t2v-a14b-controlnet-hed-v1"
vae = AutoencoderKLWan.from_pretrained(base_model_path, subfolder="vae", torch_dtype=torch.float32)
transformer = CustomWanTransformer3DModel.from_pretrained(base_model_path, subfolder="transformer", torch_dtype=torch.bfloat16)
controlnet = WanControlnet.from_pretrained(controlnet_model_path, torch_dtype=torch.bfloat16)
pipe = WanTextToVideoControlnetPipeline.from_pretrained(
    pretrained_model_name_or_path=base_model_path,
    controlnet=controlnet,
    transformer=transformer,
    vae=vae, 
    torch_dtype=torch.bfloat16
)
pipe.scheduler = UniPCMultistepScheduler.from_config(pipe.scheduler.config, flow_shift=12.0)
pipe.enable_model_cpu_offload()

controlnet_processor = MidasDetector.from_pretrained('lllyasviel/Annotators')
img_h = 704 # 704 480
img_w = 1280 # 1280 832
num_frames = 121  # 121 81 49

video_path = 'bubble.mp4'
video_frames = load_video(video_path)[:num_frames]
video_frames = [x.resize((img_w, img_h)) for x in video_frames]
controlnet_frames = [controlnet_processor(x) for x in video_frames]

prompt = "Close-up shot with soft lighting, focusing sharply on the lower half of a young woman's face. Her lips are slightly parted as she blows an enormous bubblegum bubble. The bubble is semi-transparent, shimmering gently under the light, and surprisingly contains a miniature aquarium inside, where two orange-and-white goldfish slowly swim, their fins delicately fluttering as if in an aquatic universe. The background is a pure light blue color."
negative_prompt = "bad quality, worst quality"

output = pipe(
    prompt=prompt,
    negative_prompt=negative_prompt,
    height=img_h,
    width=img_w,
    num_frames=num_frames,
    guidance_scale=5,
    generator=torch.Generator(device="cuda").manual_seed(42),
    output_type="pil",

    controlnet_frames=controlnet_frames,
    controlnet_guidance_start=0.0,
    controlnet_guidance_end=0.8,
    controlnet_weight=0.8,

    teacache_treshold=0.6,
).frames[0]

export_to_video(output, "output.mp4", fps=16)

Acknowledgements

Original code and models Wan2.2.

Citations

@misc{TheDenk,
    title={Wan2.2 Controlnet},
    author={Karachev Denis},
    url={https://github.com/TheDenk/wan2.2-controlnet},
    publisher={Github},
    year={2025}
}

Contacts

<p>Issues should be raised directly in the repository. For professional support and recommendations please <a>[email protected]</a>.</p>