---
license: mit
---
Thanks for Tencent release the controlenet training code, so Just a test version for Hunyuan tile model. More test is on going. join my personal qq group 294060503 for more discussion

Please follow https://github.com/Tencent/HunyuanDiT/blob/main/controlnet/README.md to run the model.

![image/jpeg](https://cdn-uploads.huggingface.co/production/uploads/641edd91eefe94aff6de024c/928OhsRzsu7azmoWLGUXx.jpeg)

![image/png](https://cdn-uploads.huggingface.co/production/uploads/641edd91eefe94aff6de024c/yQ9PSkdpP9hss8Y4CXwAO.png)

Inference
You can use the following command line for inference.

a. Using canny ControlNet during inference

python3 sample_controlnet.py  --no-enhance --load-key distill --infer-steps 50 --control-type canny --prompt "在夜晚的酒店门前，一座古老的中国风格的狮子雕像矗立着，它的眼睛闪烁着光芒，仿佛在守护着这座建筑。背景是夜晚的酒店前，构图方式是特写，平视，居中构图。这张照片呈现了真实摄影风格，蕴含了中国雕塑文化，同时展现了神秘氛围" --condition-image-path controlnet/asset/input/canny.jpg --control-weight 1.0
b. Using pose ControlNet during inference

python3 sample_controlnet.py  --no-enhance --load-key distill --infer-steps 50 --control-type depth --prompt "在茂密的森林中，一只黑白相间的熊猫静静地坐在绿树红花中，周围是山川和海洋。背景是白天的森林，光线充足" --condition-image-path controlnet/asset/input/depth.jpg --control-weight 1.0
c. Using depth ControlNet during inference

python3 sample_controlnet.py  --no-enhance --load-key distill --infer-steps 50 --control-type pose --prompt "一位亚洲女性，身穿绿色上衣，戴着紫色头巾和紫色围巾，站在黑板前。背景是黑板。照片采用近景、平视和居中构图的方式呈现真实摄影风格" --condition-image-path controlnet/asset/input/pose.jpg --control-weight 1.0

you need to add the tile into the config.json file and place it in the cpkts/t2i/models/controlnet
and rename to pytorch_model_ema.pt