HunyuanDiT
HunyuanDiT copied to clipboard
Hunyuan-DiT : A Powerful Multi-Resolution Diffusion Transformer with Fine-Grained Chinese Understanding
wisemode.cn开源社区类似于huggingface,是国内成长中的AI开源社区,希望HunyuanDiT模型和代码也都发布到wisemodel社区
Or only run on single graphic card like V100/A100?
```text 2024-05-16 03:24:16.542 | INFO | hydit.inference:__init__:160 - Got text-to-image model root path: ckpts/t2i 2024-05-16 03:24:21.606 | INFO | hydit.inference:__init__:172 - Loading CLIP Text Encoder... 2024-05-16 03:24:24.485 | INFO |...
Thanks for your error report and we appreciate it a lot. 目前设置的seed范围为0-2^32-1,好像是设置不了-1随机种子
Thanks for your error report and we appreciate it a lot. **Checklist** 1. I have searched related issues but cannot get the expected help. 2. The bug has not been...
看了你们的“dialoggen/dialoggen_demo.py”代码,总感觉你们阉割了多轮对话的功能,现在只能用来完善提示词,接下来有开源完整多轮对话的demo计划么?
Thanks for your error report and we appreciate it a lot. **Checklist** 1. I have searched related issues but cannot get the expected help. 2. The bug has not been...
图片质量比SDXL不差,但是怎么生成文字?比 sd3 还是不行啊
(HunyuanDiT) PS E:\IMAGE\HunyuanDiT> python app/hydit_app.py --no-enhance flash_attn import failed: No module named 'flash_attn' 2024-05-16 11:42:25.899 | INFO | hydit.inference:__init__:160 - Got text-to-image model root path: ckpts\t2i 2024-05-16 11:42:25.916 | INFO...
        **Describe the feature** **Motivation** A clear and concise description of the motivation of the feature. Ex1. It is inconvenient when \[....\]. Ex2....