muximuxi

Results 11 issues of muximuxi

您好~感谢开源 使用sd webui安装sadTalker后,按照说明文件在其模块设置中选择“full”的处理方式,最后生成的视频是0字节,如果选择“crop”的话,生成的视频没有声音,请问是怎么回事,该如何解决呢?

[ 87%] Building CUDA object CMakeFiles/ngp.dir/src/testbed_sdf.cu.o [ 87%] Building CXX object CMakeFiles/ngp.dir/src/tinyobj_loader_wrapper.cpp.o [ 89%] Building CUDA object CMakeFiles/ngp.dir/src/triangle_bvh.cu.o /home/instant-ngp/include/neural-graphics-primitives/envmap.cuh(67): error: explicit type is missing ("int" assumed) /home/instant-ngp/include/neural-graphics-primitives/envmap.cuh(67): error: qualified name...

你好~感谢开源~ 在执行text2video是,生成视频结果中,会出现多个人物,而不是当前人物在动,请问这这是什么原因,应该怎么修改? python scripts/inference/text2video.py --sd_model_name majicmixRealv6Fp16 --unet_model_name musev_referencenet --referencenet_model_name musev_referencenet --ip_adapter_model_name musev_referencenet -test_data_path ./configs/tasks/example.yaml --output_dir ./output --n_batch 1 --target_datas yongen --vision_clip_extractor_class_name ImageClipVisionFeatureExtractor --vision_clip_model_path ./checkpoints/IP-Adapter/models/image_encoder --time_size 12 --fps 12 结果: https://github.com/TMElyralab/MuseV/assets/19643523/b5f4e432-d434-4ad9-b234-8276d5af7296

请问,oneshot的时候,大概跑多少个epoch会有比价好的效果?

您好! 根据提示将octopus_weights.hdf5下载并放到weights文件夹下,使用sample_data, 并执行第一步python _infer_single.py后,报错: ValueError: Layer #5 (named "conv2d_1"), weight <tf.Variable 'conv2d_1/kernel:0' shape=(3, 3, 8, 16) dtype=float32> has shape (3, 3, 8, 16), but the saved weight has shape (8,...

您好~感谢开源。 按照test.py 执行,加入原图和风格图像以后,在output 里面没有结果生成,也没有报错,请问是什么原因呢

**General Question** Before asking a question, make sure you have: * Searched the tutorial on modelscope [doc-site](https://modelscope.cn/docs) * Googled your question. * Searched related issues but cannot get the expected...

在使用web_api.py时,问题如题,请问怎么解决,是哪里出问题了吗?而且只有batch api的接口有返回结果,stream api无返回结果

If I use my own data in SDF , how to load it and get the .npy file?