cuda error
from diffusers import StableDiffusionPipeline
pipe = StableDiffusionPipeline("stablediffusionapi/chilloutmix",torch_dtype=torch.float16)
pipe = pipe("")
can you show me how to use this model to enhance one photo with portrait, because i want to use the ChillOutMix model to enhance portrait face beauty and some other features of portrait.
please tell me, and currently, i have a following problem when i call the pipe.
RuntimeError: CUDA error: CUBLAS_STATUS_INVALID_VALUE when calling cublasGemmStridedBatchedExFix( handle, opa, opb, m, n, k, (void*)(&falpha), a, CUDA_R_16F, lda, stridea, b, CUDA_R_16F, ldb, strideb, (void*)(&fbeta), c, CUDA_R_16F, ldc, stridec, num_batches, CUDA_R_32F, CUBLAS_GEMM_DEFAULT_TENSOR_OP)
Are you doing this locally on through Google Colab / Kaggle / Paperspace / etc?
If you are trying locally (i.e. on your own PC/laptop and your own video card), have you installed CUDA drivers? What video card do you have?
If you are trying in a cloud, is GPU enabled?
Disclaimer: probably I won't be able to help you further, but this questions are ey ones for understanding of StableDiffusion usage and uprising problems.