TTPlanet's picture
Update README.md
b891429 verified
metadata
license: mit

The model will be released once Hunyuan DiT comfyui controlnet is fully supported.

Tencent HunyuanDiT Inpainting Controlnet

An amazing controlnet model which can provide you incrediable consistent and crativity 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! comfyui inpainting preprocessor to combine the mask and img: https://github.com/TTPlanetPig/Comfyui_TTP_CN_Preprocessor

Let's have a game!

which one is original one? select wisely

Left one is No1 and right one is No2

imageNo1 imageNo2

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: 描述文本 a muscle man with blue eyes: 描述文本 a man in batman suit with eye cover: 描述文本

Multiple area inpainting with different prompts,and correctly understand the depth of field!

Masked 3 individual area: 描述文本 An Asian man with long sleeve T-shirt, in the background there is a yellow dog: 描述文本

Multiple area inpainting with high consistency!

imageNo1 imageNo1 imageNo2

Amazing outpainting!

imageNo1 imageNo2

high quality inpainting adapter to the original photo style or light!

Masked image: 描述文本

imageNo1 imageNo2

imageNo1 imageNo2

in the end, enjoy the HunyuanDiT

Join my QQ group if you appreiate my job: 294060503 or contact my wechat: tangtuanzhu