Precise control of graphics! Tencent Hunyuan Wenshengtu open source model launches three ControlNet plug-ins

Tencent HunyuanVincent Figure Large ModelHunyuanDiT recently released three new controllable plug-ins ControlNet in the community, namely tile (high-definition magnification), inpainting (image restoration and expansion) and lineart (line draft drawing), further expanding its ControlNet matrix. The addition of these plug-ins enables the Hunyuan DiT model to cover a wider range of application scenarios, including art, creativity, architecture, photography, beauty and e-commerce, and other 80% cases and scenarios, providing more accurate image generation and greater freedom of creation for global enterprises and individual developers and creators.

The Tile plug-in can expand the information of the picture, achieve ultra-clear magnification, and even reach 4K to 8K clarity, which is suitable for scenes with extreme pursuit of picture details. The Inpainting plug-in can fill the smeared and mottled parts of the picture according to the needs of the creator, achieve effects such as background replacement and character subject change, and handle large-area image redrawing. The Lineart plug-in uses different line types to create real-life, animation and architectural pictures, which is suitable for generating architectural renderings and coloring manuscripts.

Precise control of graphics! Tencent Hunyuan Wenshengtu open source model launches three ControlNet plug-ins

also,TencentHunyuan DiT has previously released ControlNet models with conditions such as canny (edge), depth, and pose (human posture) to support developers in reasoning, and has open-sourced the ControlNet training solution, enabling developers and creators to train customized ControlNet models.

Since the announcement of the full upgrade and open source in May, Hunyuan DiT has become the industry's first Chinese native DiT architecture.Open Source Model, continued to build the developer ecosystem, released a dedicated acceleration library, improved reasoning efficiency, shortened image generation time, and further open-sourced reasoning code. In July, Hunyuan DiT was upgraded to version 1.2, and a small video memory version was open-sourced, which only requires 6G video memory to run, making it more friendly to developers who deploy locally on personal computers.

At present, the number of stars of Hunyuan DiT on Github has exceeded 3.1k, making it the most popular domestic DiT open source model.

Official Website

https://dit.hunyuan.tencent.com/

Code

https://github.com/Tencent/HunyuanDiT

Model

https://huggingface.co/Tencent-Hunyuan/HunyuanDiT

paper

https://tencent.github.io/HunyuanDiT/asset/Hunyuan_DiT_Tech_Report_05140553.pdf

statement:The content is collected from various media platforms such as public websites. If the included content infringes on your rights, please contact us by email and we will deal with it as soon as possible.
Information

Pindrop launches AI audio forgery detection tool Pulse Inspect, with an accuracy rate of 99%

2024-8-16 9:38:25

Information

Alibaba releases Q1 financial report for fiscal year 2025: Tongyi model downloads exceed 20 million

2024-8-16 9:54:44

Search