-
Hi, when I do inference using fine tuned modelscope t2v model, it produces 3 or 4 videos for each text prompt. I was wondering is this behaviour normal and what is the difference between the videos?
…
-
This is a very good work, I tried to deploy this project on mac and ended up saying "Torch not compiled with CUDA enabled" because my M3 pro does not have cuda, is there a good solution for running th…
-
1. 已经git pull了最新的code
2. 在使用llava1.6_llama3.1_8B的时候报错
{'loss': 1.4909668, 'grad_norm': 11.20178784, 'learning_rate': 0.0, 'memory(GiB)': 34.69, 'train_speed(iter/s)': 0.03356, 'ep
och': 0.0, 'globa…
-
运行在容器中 running in a container
使用gpu会报显存不足 use gpu
```shell
ERROR: Model running Error: CUDA out of memory. Tried to allocate 2.37 GiB. GPU 0 has a total capacty of 23.69 GiB of which 2.03 GiB is fr…
-
Traceback (most recent call last):
File "/data/AnyText/inference.py", line 3, in
pipe = pipeline('my-anytext-task', model='damo/cv_anytext_text_generation_editing', model_revision='v1.1.0')
…
-
There is a BERT based model used in Ant group for inference on geo similarity compare.
https://modelscope.cn/models/damo/mgeo_geographic_entity_alignment_chinese_base/summary
https://modelscope.cn/m…
-
比如 阿里的日语模型 https://www.modelscope.cn/models/iic/speech_UniASR_asr_2pass-ja-16k-common-vocab93-tensorflow1-offline/summary
可以增加一个添加其他模型的功能吗
-
-
### Is there an existing issue for this?
- [X] I have searched the existing issues and checked the recent builds/commits of both this extension and the webui
### Are you using the latest version of …
-
启动docker容器之后重复调用pipeline接口不会再生成视频，必须重启docker之后才能再次调用，我想问是我这边有什么参数配置方面的问题还是大家都会这样？