O-O1024

Results 20 issues of O-O1024

1、没有把项目根目录添加到 sys.path,根本无法 import,我就是在项目根目录运行的 2、invert.py 文件有很多问题!!! 2.1、args.device、args.truncation_mean、lpips.PerceptualLoss 都是未定义的。lpips下也没找到 PerceptualLoss,是不是 readme 文件写漏了一些步骤? 2.2、truncation_mean 怎么用来生成随机数了 g_ema = g_ema.style(torch.randn(args.truncation_mean

### Provide environment information ![image](https://user-images.githubusercontent.com/44624598/211563804-eba2216e-89f8-4140-bfa7-1979acbf7927.png) ### What OS are you using? win10 ### Describe the Bug Adjusting order of labels, if drag label on other label, this label will be...

bug

![image](https://user-images.githubusercontent.com/44624598/211891109-08adde7e-fd80-466a-91ad-3edb6370458d.png)

duplicate

把 stylegan模型转出 ONNX,再转成 paddle模型,出现这个错误 ========= 1 OPs are not supported yet =========== ========== RandomNormalLike ============ ========== RandomNormal ============ 或这个 ========== RandomUniformLike ============ 或这个 ========== RandomUniform ============ 或这个 随机数在生成模型中是很常见的, 全都不支持,就不能部署了 如图...

if it supports int8 quantization, the model size can be reduced 3/4. May be faster.

The position of input box is fixed, some times don't fully be shown, and cannot be dismissed by ESC key ![input box img](https://github.com/comfyanonymous/ComfyUI/assets/44624598/34bc6a47-6316-4cd5-b5ee-858ed45c16c0)

这种情况连GFPGAN都无法修复 ![搜狗截图20240406162035](https://github.com/TMElyralab/MuseTalk/assets/44624598/6f6b79cc-46e4-4394-a9de-adb5e4dcd667)

不清楚是不是因为面部在边缘,关键点检测不够准确导致的 https://github.com/TMElyralab/MuseTalk/assets/44624598/fe318972-da03-4cec-b4a6-a5736fe8b9ad https://github.com/TMElyralab/MuseTalk/assets/44624598/f80f718b-a32d-4006-9ec9-eb97802d29a3

It seems all versions should be downloaded. Is it really necessary ? ![搜狗截图20240523170817](https://github.com/myshell-ai/OpenVoice/assets/44624598/fa17c66a-f379-4960-8fac-8ed654177580)

加载 PhotoMaker V2 权值出错了 ``` !!! Exception during processing!!! Error(s) in loading state_dict for PhotoMakerIDEncoder: Unexpected key(s) in state_dict: "qformer_perceiver.perceiver_resampler.layers.0.0.norm1.bias", "qformer_perceiver.perceiver_resampler.layers.0.0.norm1.weight", "qformer_perceiver.perceiver_resampler.layers.0.0.norm2.bias", "qformer_perceiver.perceiver_resampler.layers.0.0.norm2.weight", "qformer_perceiver.perceiver_resampler.layers.0.0.to_kv.weight", "qformer_perceiver.perceiver_resampler.layers.0.0.to_out.weight", "qformer_perceiver.perceiver_resampler.layers.0.0.to_q.weight", "qformer_perceiver.perceiver_resampler.layers.0.1.0.bias", "qformer_perceiver.perceiver_resampler.layers.0.1.0.weight", "qformer_perceiver.perceiver_resampler.layers.0.1.1.weight", "qformer_perceiver.perceiver_resampler.layers.0.1.3.weight",...