311_code

Run Llama 3 70b locally combining ram and vram like with other apps?

1

Sorry I am pretty novice here in LLM space. I have noticed that some users are able to run the llama 3 70b model as a gguf locally with quantization...

[Feature Request] A way to export as Stereo cubemap or a VR180 jpg for viewing in VR headsets?

2

Would love the ability to create a 180 Degree side by side image and view it in full 3D in Simple VR video player and with any VR headset, or...

[Feature Request]: Ability to encode a vae image like in comfyui (used to increase finetuning or dreambooth likeness)

1

### Is there an existing issue for this? - [X] I have searched the existing issues and checked the recent builds/commits ### What would your feature do ? In comfyui...

Disable internet/http requirement

1

I have noticed that you cannot run batch if network adapter disabled or internet is not working and will get http error. I would like to make a request to...

[Feat] Dora extraction

1

I use the Lora extraction option from a dreambooth or finetuned checkpoint all the time as it seems to produce better results than just training a Lora. Would love to...

Request: Need models in onnx and .pt format (not just .bin and .config)

6

I was requesting the model in another format because I cannot convert it without the proper model configuration file (I've tried) Need them in onnx or .pt format specifically for...

Can't pause/rewind/ff new depth-anything beta build videos

6

The new Unity beta build with depth-anything works great for me, the only issue I have is the numpad 5, 6, 4 no longer fast forward rewind or pause when...

[Feat] Geowizard implementation

1

There is a new model released this week that is supposed to be like marigold, but much faster. Could be useful for Depthviewer, would love to see implemented natively. https://github.com/fuxiao0719/GeoWizard...

xformers for potential speedup, or torch 2.01 arguments

5

I had read that using xformers (pip install xformers) could possibly results in a large speedup in the marigold and depth-anything realtime conversion. The issue is I can't find any...

[Bug]: Backups (diffusers) getting much different results than same .safetensors

21

First off love Onetrainer, but just wanted to share this issue I noticed. This is a buddy with his face slightly changed with a midjourney lora. The prompt was supposed...