TheGenerativeGeneration

He probably means the other repository, incubator-mxnet/example/ssd/. @seyoungleecho Just copying mobilenet.py and the appropriate part in symbol-factory.py from this repository seems to work.

I tried that but the people became increasingly distorted with each new training/person added. I'm trying this approach now https://github.com/XavierXiao/Dreambooth-Stable-Diffusion/issues/12 but that so far still ends up with just one...

I get the same problem on Windows on a fresh install

No, the model is not executed on CPU, but one tensor is half-precision (cuda.HalfTensor) and the other full (cuda.FloatTensor). The problem seems to be that the safety checker uses the...

#419

Wouldn't the transformation of the quaternion be (x,y,z,w) -> (-x,y,-z,w) if we invert the y-axis direction? At least according to this: https://gamedev.stackexchange.com/a/201978

I also made a Dockerfile, though I had to use mxnet and onnx on CPU: https://hub.docker.com/r/wawa9000/ghost (models for inference are included)

I have the same problem, although I'm not even doing anything particularly heavy in my loop. ``` while ctx.state.playing: with lock: is_speaking = info["is_speaking"] audio_frame_id = info["audio_frame_id"] ``` I even...

Has this been solved? I also have problems with the model giving quite bad output after conversion to GGUF (repetitive behavior).

My pleasure! In the readme it actually says that they changed a few things in their renderer in comparison to the original one https://github.com/ashawkey/torch-merf#modification-of-web-renderer