Tencent HunyuanDiT Inpainting Controlnet
Please update your comfyui to the latest version, use ControlNetApply SD3 and HunyuanDiT to apply the controlnet model
please download the preprocessor for comfyui from here
https://github.com/TTPlanetPig/Comfyui_TTP_CN_Preprocessor
Download the Hunyuan 1.2 Safetensors package from here:
https://huggingface.co/comfyanonymous/hunyuan_dit_comfyui/blob/main/hunyuan_dit_1.2.safetensors
An amazing controlnet model which can provide you incredible consistent and creativity to the original image!
it is trained with various resolution of images and masks to provide nice robust to the the base model. now it can create the new image with the same style of the original one, following are some example to show the result!
Let's have a game!
which one is original one? select wisely
Left one is No1 and right one is No2
I have done my own test, for the most people they will select No1 as original image, however, No2 is the original one and No1 is the image with inpainting control with Hunyuan DiT model.
Other capablity!
Recovery from 70% mask area but still keep consistency!
Example: Maksed image:
a muscle man with blue eyes：
a man in batman suit with eye cover:
Multiple area inpainting with different prompts and correctly understand the depth of field!
Masked 3 individual area:
An Asian man with long sleeve T-shirt, in the background there is a yellow dog：
Multiple area inpainting with high consistency!
high quality inpainting adapter to the original photo style or light!
Masked image:
in the end, enjoy the HunyuanDiT
Join my QQ group if you appreiate my job: 294060503 or contact my wechat: tangtuanzhu
workflow: in the PNG img
