Stax124

Please check that you have your `venv` activated: - `.\venv\Scripts\activate.ps1` for PowerShell - `.\venv\Scripts\activate.bat` for CMD - `source venv/Scripts/activate` for Linux shells Then try installing it again with `pip install...

@patrickvonplaten I was able to get KDiffusion samplers with Karras sigmas with some modifications to your KDiffusion experimental model: https://github.com/Stax124/voltaML-fast-stable-diffusion/blob/4b6a23c5a09ee6375b6dbc86ba1d207df80eea7b/core/diffusers/kdiffusion/KDiffusionModel.py#L513 I am getting similar results to A111 (using AnythingV4 -...

Closing as TensorRT support was deprecated in favor of AITemplate

Project has been migrated to AITemplate since this request was posted. AIT has similar pipeline to diffusers, so therefore should be much easier to read.

Closing as TensorRT support was deprecated in favor of AITemplate

> I get the same error trying voltaML for the first time. Is this a dead repo? No, quite the opposite is true, you can take a look at the...

@aifartist We already found a patch for the 4090 and we are aware of the problems with Ada Lovelace architecture. Documentation for this bug will be available in our own...

> you can try to disable use_mem_eff https://github.com/facebookincubator/AITemplate/blob/main/examples/05_stable_diffusion/src/modeling/attention.py#L72 I tried that but it is still non deterministic. Latents generate correctly with the fixed seed. It must be somewhere in the...

I can verify that this bug is present. We have a table solution written in Vue and swapping pages or refreshing data in any way leads to insane memory leaks...

TensorRT has recommended CUDA 12.x, try to update the drivers if you have the option