Ximing Xing
Ximing Xing
i have a question about classifier free guides in unidffuser, what is the `null_context` in of cfg in unidffuser, text prompts or img, since unidffuser is able to execute t2i...
[Mark]
I used CUDA version 11.7 and did not find this issue, I kept the issue open to see if I encountered the same thing
My GPU server GCC version is 12.1.0. Anyway, thanks for asking this question, I think it's helpful for other players!
HI, mattdesl, Sorry, I haven't used diffvg with mps backend on Mac either, so I may not be able to advise you on that. Regarding the use of CPU interrupts,...
try docker ```shell docker run --name svgdreamer --gpus all -it --ipc=host ximingxing/svgrender:v1 /bin/bash ```
To run PyTorch code on Mac M1's GPU, specify it using the command `torch.device("mps")`
Dear wuutiing, The fp32 optimization requires a minimum of V100, which is 32GB of memory. To use 3090 inference, you can use fp16 via `state.mprec='fp16'`: ```shell python svgdreamer.py x=iconography skip_sive=True...
You can try the docker image we provide, ```bash docker run --name svgdreamer --gpus all -it --ipc=host ximingxing/svgrender:v1 /bin/bash ``` In addition, the installation of diffvg requires the gcc version,...
Can you tell me which method and the machine configuration you use？