junsukha

Results 6 issues of junsukha

In `labml_nn/diffusion/stable_diffusion/model/unet_attention.py`, `def flash_attention(self, q: torch.Tensor, k: torch.Tensor, v: torch.Tensor):` has `torch.stack((q,k,v), dim=2) ` where, I believe, q is of different shape from k and v. How does torch.stack work...

``` Traceback (most recent call last): File "main.py", line 4, in from nerf.provider import NeRFDataset File "/home/jun/Documents/Make-It-3D/nerf/provider.py", line 16, in from .utils import get_rays, safe_normalize File "/home/jun/Documents/Make-It-3D/nerf/utils.py", line 26, in...

Hi! thank you for sharing the work. I would appreciate if you could give some advice on how to modify zero123's unet architecture. I want to add a custom layer...

Hi, thank you for sharing the work! I need T2V model so tried using checkpoints here [https://huggingface.co/LargeWorldModel/LWM-Text-1M-Jax/tree/main](url) with `run_sample_video.sh`. But it seems the vqgan checkpoint is missing. Should I use...

Hi! Thanks for the great work. After switching between workflows, the green bonding box highlighting the node currently running is gone. For example, in a workflow 1, I run Queue...

As the title. ``` runtime error Exit code: 1. Reason: Installing correct gradio version... Found existing installation: gradio 3.50.2 Uninstalling gradio-3.50.2: Successfully uninstalled gradio-3.50.2 Collecting gradio==3.50.0 Downloading gradio-3.50.0-py3-none-any.whl (20.3 MB)...