OOTDiffusion

OOTDiffusion copied to clipboard

 Thank you for your great project! My inference results are not good. Could you take a look? Thank you very much! I ran the following command: python run_ootd.py --model_path...

puduliu

我GPU 24G已经跑起来了，大家可以一起交流下

1

我GPU 24G已经跑起来了，大家可以一起交流下，应该比issue交流有效率些 我wx：hungtien 好友申请备注：ootd

NielHung

my day a100 error is low on memory

1

shuaijiang111111111

yakshi26

i tried enabling and setting the variables and etc etc not working and please help Traceback (most recent call last): File "D:\OOTDiffusion\run\gradio_ootd.py", line 27, in openpose_model_dc = OpenPose(1) File "D:\OOTDiffusion\preprocess\openpose\run_openpose.py",...

NoOneEqualsToNone

ImportError: cannot import name 'cached_download' from 'huggingface_hub' (C:\APP\anaconda3\envs\ootd\lib\site-packages\huggingface_hub\__init__.py)

4

how to solve the problem?

promising678

Hello, Thank you for sharing this project; it looks fantastic! I wanted to ask about the licensing terms for this repository since I couldn't understand the licence file descriptions. Would...

mselmansezgin

非常感谢各位分享本项目！有两个小问题想要请教一下： https://github.com/levihsu/OOTDiffusion/blob/13ef0faba266cdde9febc8ad39be2395bbb89d9c/ootd/inference_ootd_hd.py#L113 1.我们注意到作为UNet的condition定义的prompt_embeds中对应的文本其实是空的。请问此处没有单独使用prompt_image作为condition，而是用长度为2的序列prompt_embeds做condition，单纯是为了便于进行cross attention的运算吗？（满足key的长度大于1） 2.stable diffusion中text prompt默认的token数似乎为77，即构建了一个长度为77的序列作为condition来与UNet进行cross attention运算，而本项目中没有进行padding将token数强行扩大为77而是直接运用了长度为2的序列，请问这样操作有什么理由吗？

qiqigit

Clarification on `--sample` Parameter

1

The README code suggests using `--sample 4`. I am curious, for the final results and evaluation, do you use all samples or just one? If it's the latter, should I...

ShenZheng2000

CUDA out of memory - CUDA 12.3

8

Hey, is it possible to run this code for CUDA 12.3? I installed the right torch version for it. I keep getting this error about CUDA being out of memory....

zzubrzycka