JC1DA

icon location *****Open-Source FTW***** Research Engineer @ MSFT

Results 28 comments of JC1DA

gan inversion code release

Also interested in the GAN inversion to generate shapes from custom images. @XingangPan is there any ETA? Thanks

Where is the 3D mesh model getting saved?

I have the same question. Is there any way we can generate the stl files similar to the example code in shadegan? @XingangPan

streamlit-webrtc does not work on chrome (tested on Android and macOS)

I have kind of similar issue, and it took a lot of time (less than 1 minute) to initialize the connection on mobile devices . FYI, I have my service...

Inference using own input

Hi, I have the same question. Used this repo (https://github.com/rosinality/stylegan2-pytorch) to generate the latent and reconstruct the image but when I plugged the latent into the code, it doesn't work...

will open source the implementation of cnn with opencl

HI, It's already in Assets directory :) Check this path: app/src/main/assets

[WIP] Tokenize and compute probs for vis layer during generation

Overall, the backend changes LGTM. Looking forward to another PR to add probs for fast-forward tokens

Handle invalid utf-8 bytes in engine class instead of model class

@hudson-ai can you help check this PR?

Handle invalid utf-8 bytes in engine class instead of model class

> Seems reasonable to me, but I'm not sure I have a strong opinion on whether this should be done in the engine vs in the model. Can you help...

[Feature] Support llguidance for constrained decoding

Hi @Ying1123 @merrymercy @zhyncs Can you guys help take a look at this PR? We'd love to bring more choices for constraint decoding to sglang community :)

[Feature] Support llguidance for constrained decoding

> ok I'll help take a look asap. Thanks for your contribution! thanks @zhyncs, really appreciate it