We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
显卡:V100-32GB,其余环境按requirements.txt安装,diffusers库从源码安装
使用最新模型(t2v, i2v均可),将cli_demo.py的数据类型从bf16改成float16 prompt: a girl riding a bike
会得到: /opt/conda/lib/python3.11/site-packages/diffusers/image_processor.py:147: RuntimeWarning: invalid value encountered in cast images = (images * 255).round().astype("uint8")
看起来并不是转换出了问题而是生成的结果有nan 不使用fp16而是使用bf16的话会OOM,所以只能使用fp16
正常生成图像
The text was updated successfully, but these errors were encountered:
UPDATE: 可以暂时使用FP32推理来代替,FP32可以正常使用。
Sorry, something went wrong.
这个模型不太支持FP16,因此在readme中,我们强烈推荐使用BF16,FP32肯定没问题,如果显存够并且能接受更慢的时间
zRzRzRzRzRzRzR
No branches or pull requests
System Info / 系統信息
显卡:V100-32GB,其余环境按requirements.txt安装,diffusers库从源码安装
Information / 问题信息
Reproduction / 复现过程
使用最新模型(t2v, i2v均可),将cli_demo.py的数据类型从bf16改成float16
prompt: a girl riding a bike
会得到:
/opt/conda/lib/python3.11/site-packages/diffusers/image_processor.py:147: RuntimeWarning: invalid value encountered in cast
images = (images * 255).round().astype("uint8")
看起来并不是转换出了问题而是生成的结果有nan
不使用fp16而是使用bf16的话会OOM,所以只能使用fp16
Expected behavior / 期待表现
正常生成图像
The text was updated successfully, but these errors were encountered: