sp1cae

Shanghai See you someday, somewhere

Results 12 comments of


                                            sp1cae

最低需要多少显存？24G能跑得了吗？

> 我用命令行的方式调用instant-mesh-large模型显存就够用了，用app.py可视化的那个估计是加载了多个模型导致显存不足，问题解决了 python run.py configs/instant-mesh-large.yaml examples/hatsune_miku.png --save_video 这个命令吗， 3090还是会显存不够

最低需要多少显存？24G能跑得了吗？

> 我主要是想要生成3d模型，没有生成视频，而且图片本身就已经去了背景，我也是用3090，显存够了，命令如下： python run.py configs/instant-mesh-large.yaml Examples/hatsune_miku. png --no_rembg --export_texmap > > > > 我用命令行的方式调用instant-mesh-large模型显存就够用了，用app.py可视化的那个估计是加载了多个模型导致显存不足，问题解决了 > > > > > > python run.py configs/instant-mesh-large.yaml Examples/hatsune_miku.png --save_video这个命令吗， 3090还是会显存不够解决了谢谢~

ValueError: PhotoMaker currently does not support multiple trigger words in a single prompt. Trigger word: img, Prompt: a beautiful girl on Italy street, best quality.

same error

[SpeechSynthesis/Tactron2] Training crashes with AttributeError: module 'torch._C' has no attribute '_jit_set_autocast_mode'

same error

OSError: Can't load tokenizer for 'google/t5-v1_1-xxl'. If you were trying to load it from 'https://huggingface.co/models', make sure you don't have a local directory with the same name. Otherwise, make sure 'google/t5-v1_1-xxl' is the correct path to a directory containing all relevant files for a T5TokenizerFast tokenizer.

> > > It seems that it is a web issue. Try more times at different time, when it successfully download several .json files, Web UI works. > > >...

[BUG]使用v1.2版本的权重和v1.2的distill权重进行推理生成的图片全黑

same error with torch

can you support FLUX controlnet？

me too

Internvl技术交流群，方便Internvl实战交流

需要更新

[Bug]: Unable to load the latest ControlNet

same issue

[Bug]: Unable to load the latest ControlNet

> same issue Ran into this too, and solved mine by upgrading my python version to 3.10 work +1

1
2
›