ffhelly

Has this issue been resolved yet? I also have this issue, even if the image is converted to base64, it is still this error

same issue

> 嗨，你解决了问题吗？ 我也有问题。“OSError：无法加载模型 damo-vilab/text-to-video-ms-1.7b：模型未缓存本地”，但我无法连接到 huggingface。 从镜像站拉一份到本地。或者开科技下载

same too. 8x 4090 . so slow.

image_embedder.py line 75 code def __init__( self, arch="ViT-H-14", version="laion2b_s32b_b79k", device="cuda", max_length=77, freeze=True, antialias=True, ucg_rate=0.0, unsqueeze_dim=False, repeat_to_max_len=False, num_image_crops=0, output_tokens=False, ): super().__init__() model, _, _ = open_clip.create_model_and_transforms( arch, device=torch.device("cpu"), pretrained=version, ) del...

俺也一样。 不论是用那个模型 都这样的 ./build/examples/k2_rnnt2_cli models/paraformer_cli/zh.wav Segmentation fault (core dumped)