Andy KoKo
Andy KoKo
在最新ios16测试版上问题好像挺严重的,iphone11和ipad mini 5都一样情况。 1.切换频道无法关闭上个频道的声音,好多个频道的声音同时在播放。 2.很难切换到全屏模式。 3.播放时左右滑动切换频道会卡住。 4.每个频道都会重新加载一次epg列表,并且加载过程中画面会卡住几秒。 反倒是tvos 16上几乎完美,偶尔有闪退,总体来说应该是apple tv目前使用体验最好的了,解码速度相当快。
The timestamp of whisper is not very accurate. The following is the comparison between Microsoft Cognitive Services Speech and whisper. ``` 1 00:00:00,120 --> 00:00:01,379 (Microsoft) [00:00:00.000 --> 00:00:02.000] (whisper)...
Because the return time of the larger model is too long, I turned to codegen-350M. And it only takes 1-2s to return the prompt code on my M1 computer. I...
I noticed that the coreml model cannot switch resolutions arbitrarily like ckpt. As a result, I need to repeatedly generate multiple huge model packages. I use [Guernika Model Converter](https://huggingface.co/Guernika/CoreMLStableDiffusion) to...
Interactive Segmentation 插件很方便,但是我在测试为一张白底产品图生成背景的时候遇到了问题,如果使用Interactive Segmentation插件一键选出背景,那么产品便会不自然的融合成背景的一部分,而我手动画出蒙版,与产品保留一些空隙则能很自然的融合到背景,视角,比例,透视也接近现实。 希望增加蒙版的收缩和扩展功能,来优化这个问题。 下面是对比图: 
``` This project breaks the limitation that Stable Diffusion CoreML Model only supports a single resolution. No need for complicated model conversion, no need for duplicate and huge models to...
macos m1, After running StableStudio.app, will download the Windows version of the ComfyUI installation package.
- New Scheduler: LCM, DPM++ SDE Karras, Euler Ancenstral, etc. - New Model: LCM, SDXL Turbo, SDXL lightning etc. - New any model inpaiting support: special inpaiting model has better...
Due to the influence of computer performance and model size, the waiting time may be a little long. Can we use WebSocket to communicate to get real-time line-by-line display code?...
Salesforce releases a new model codegen2, CodeGen2 is capable of infilling, and supports more programming languages. [https://huggingface.co/Salesforce/codegen2-1B](https://huggingface.co/Salesforce/codegen2-1B) I tested codegen2-1B, and the code quality has improved, but it seems that...