Attachment: Tencent Hunyuan - Open Source DiT Large Model COMFYUI Text-to-Image Workflow

Hunyuan-DiT is a diffusion model from text to image that can finely understand English and Chinese. To build Hunyuan-DiT, the project meticulously designed transformer structures, text encoders, and positional encodings. From scratch, Hunyuan also built a complete data pipeline to update and evaluate data for iterative model optimization.

For fine-grained language understanding, Hunyuan trained a multimodal large language model to optimize image captions. Lastly, Hunyuan-DiT can engage in multi-round multimodal dialogues with users to generate and refine images based on context. Through the project's carefully designed overall human evaluation protocol, with more than 50 professional human evaluators, Hunyuan-DiT has set a new advanced level in Chinese-to-image generation compared to other open-source models.

Model Mirror Access

https://hf-mirror.com/Tencent-Hunyuan/HunyuanDiT

Chinese Language Understanding Preview

Long Text Generation

Multi-Round Dialogue Generation

----------------------------------------------------------------------

The Hunyuan Trainer Script Has Been Updated, AiARTiST Can Provide Model Training Services for You.

----------------------------------------------------------------------

Lib members can enjoy online accelerated generation, conveniently used with the CADS series LoRA.

Model List: https://www.liblib.art/search?keyword=AiARTiST

55% Free Models, 95% Open Source Models

40% Membership Models, 5% Closed Source Models

Commercial Models:

AiARTiST-CADS2.0 XL Business Advertising Assistance System (Enterprise Customization)

https://www.liblib.art/modelinfo/a56ebacdba7d4e30b97bb124bc3fc28f <<Direct Link

----------------------------------------------------------------------

Other Model Promotions:

Open Source Model UNIT-lib XL (includes 1GIRL weight, stacking enhances portraits):

AiARTiST XL Basic Unit CADS2 LoRA Compatible Version Site Link

https://www.liblib.art/modelinfo/b10dfccc06f34dfa9031f1d070d846ee

UNIT2XL Basic Unit 2-Graphic Design and IP Image AiARTiST Site Link

https://www.liblib.art/modelinfo/a202d2e89e2946539a52a5a4e937262d

UNIT-lib XL Open Member Download, Support Integration, Members Also Enjoy Online Accelerated Generation

For a brighter 3D effect, pair with ACG Playground V6 Open Source Edition :

https://www.liblib.art/modelinfo/4bb107737a1349f7a053bbf618e46977 <<Free Download

ControlNET Configuration Optimization Plan and Local Configuration Plan, please join the group:

Contact details at https://afdian.net/a/AiARTiST-lib exclusive for power users

----------------------------------------------------------------------

Model Usage Declaration:

1. You are not allowed to host this model and its derivative versions (such as fusion model versions) on websites/apps intended to earn income or donations.

2. You may not directly sell this model and its derivative versions (such as fusion model versions) unless you have made sufficient manual modifications for it to be fully determined as your own work in a legal sense. If you violate this clause, all legal consequences are your personal responsibility, and I am not responsible.

3. You cannot use the model to intentionally create or share illegal or harmful content for dissemination and output. Please adhere to public morality and use this model for positive purposes.

----------------------------------------------------------------------

Leave a message for test questions, business cooperation see personal homepage +V Zyuan980

AiARTiST | Metaverse China·Shandong Digital Human/AiGC/Metaverse Direction

Be a good toolman, serve the artist. Contact:https://afdian.net/a/AiARTiST-lib