Mayorc1978
Mayorc1978
Have you solved that? I strongly think that even if the output is set to 1024, actual output without distortion/noise artifacts will probably happen only for the size of 256x256...
Did you solve this, cause I get broken results testing as well, tried face_model_0 and universal_0 Get results similar to yours.
SimSwap provides a method to identify different faces (creating an identity vector for each face) and use a method to match a face to another face within an identity threshold....
Thanks for clarifying this, but I wasn't able to find it in the search, probably because the request was done in Chinese previously.
> I'm wondering if it's possible to enable the "gpt-engineer" to access the web for searching documentations. Definitely, supports for embeddings, pdfs, and web search is a must, else it...
> Doesn't the latest gpt model support functions now? > > It should be possible in theory to implement web access. Supporting paid-only features sounds like a poor choice to...
Any Windows binaries planned?
> Hi, could you try the windows exe distribution in https://github.com/TabbyML/tabby/releases/tag/v0.7.0 ? Giving it a try, thanks.
Same problems (but doesn't even download any model), get a crash (werfault.exe in Process Explorer with cuda117, but no error code in the shell), tried both versions, cuda122 version gives...
Not really sure cause I've not checked yet, but maybe Encoder4Editing works.