theoldsong
theoldsong
执行 报错
`ValueError: This ORT build has ['TensorrtExecutionProvider', 'CUDAExecutionProvider', 'CPUExecutionProvider'] enabled. Since ORT 1.9, you are required to explicitly set the providers parameter when instantiating InferenceSession. For example, onnxruntime.InferenceSession(..., providers=['TensorrtExecutionProvider', 'CUDAExecutionProvider', 'CPUExecutionProvider'],...
“python demo.py --config config/dataset_name.yaml --driving_video path/to/driving --source_image path/to/source --checkpoint path/to/checkpoint --relative --adapt_scale” Run code error“ValueError: Could not find a format to read the specified file in mode 'i' ” Whether...
Hello big guy, the environment is set up and can only be generated with the default materials. I tried to search for a long time, but I couldn't find how...
Errors are reported when creating a virtual environment in Anaconda `ResolvePackageNotFound: - gnutls=3.6.15 - libxcb=1.14 - gmp=6.2.1 - libgfortran-ng=7.3.0 - libtasn1=4.16.0 - libstdcxx-ng=9.1.0 - libidn2=2.3.2 - libunistring=0.9.10 - lame=3.100 -...
I have seen that many people have implemented this program under 8G VRAM, and the speed is still fast. The author does not provide a similar implementation method. How can...
RT，尤其是细节，都是用的推荐的参数数值 和演示的还有很大差距 https://iceclear.github.io/projects/stablesr/
模型下了半天，结果还是各种报错，看Issues里有人说triton不用装，结果不装报错，triton好像只支持linux，找了一个大佬封装的win版本，结果又报错，这个必须cuda12.1才能用吗？ WARNING[XFORMERS]: xFormers can't load C++/CUDA extensions. xFormers was built for: PyTorch 2.3.0+cu121 with CUDA 1201 (you have 2.3.1+cu118) Python 3.8.10 (you have 3.8.19) Please reinstall xformers (see https://github.com/facebookresearch/xformers#installing-xformers) Memory-efficient...
之前折腾过一次，模型就下了半天时间。总共花了一天时间都没搞定，各种报错。 今天突然想起来又折腾了一下午 所有报错解决了，但这加载模型都用了半个小时，而且没进webui显存就被占用完了，最高直接用到30G显存。 眼看就要看到光明了，结果报错了，显存不足。。。 这个项目是不是不适合win系统？ win用户准备尝试的，建议慎重考虑，浪费时间不说，最后可能一场空。 后期作者有对win做优化的考虑吗？ Loaded model config from [options/SUPIR_v0.yaml] Loaded state_dict from [./ckpts/sd_xl_base_1.0_0.9vae.safetensors] Loaded state_dict from [./ckpts/SUPIR-v0Q.ckpt] Loading vision tower: openai/clip-vit-large-patch14-336 Loading checkpoint shards: 33%|██████████████████▋ | 1/3...
Besides the streaming_t2v.ckpt model introduced by the official website, how many other models need to be downloaded? Known models include Video to Video and text to video ms-1.7b. May I...
RT