wandrzej

> looks like adding the following code at the _very top_ of `run_app.py` helps: > > ``` > import os > os.environ['PYTORCH_CUDA_ALLOC_CONF'] = "max_split_size_mb:1000" > import torch > torch.cuda.empty_cache() >...

> Our short term goals are around ONNX, DNN training and AutoML. RL is something we have considered and is on our list but just not something we plan to...

tried with colab also getting `ModuleNotFoundError: No module named 'psbody'` but before that ``` Successfully installed psbody-mesh Removed build tracker: '/tmp/pip-req-tracker-mz6iz1j0' ``` maybe I'm doing this in the wrong folder

the latest update seems to have messed up the variable types in switches - I had workflows that used NUMBER as input, and now it seems it's not going to...

To be honest, as InstantID is now implemented in diffusers, I hope we might get a proper implementation. https://github.com/huggingface/diffusers/blob/main/examples/community/pipeline_stable_diffusion_xl_instantid.py On top of other issues, just like with PhotoMaker we have...

I know the other issue was closed, but wanted to ask about an option to alter the prompt on the sliding window? So the music would transition from one prompt...

what has inclusivity to do with it? What you describe is using someone's likeness without consent - an important topic, but one that is not relate to inclusivity in any...

@alexanderrichard Could you clarify a bit the intermediate representations of each model. I think the final visulization is done with the avatar renderer from the _Driving-Signal Aware Full-Body Avatars_ paper,...

from the demo description: "4) Then, sit back and wait for the rendering to happen! This may take a while (e.g. 30 minutes)" Not sure if it will help to...

just re-posing a character. and it's exactly what I was trying to do, although with 2 frame video and get the same error. I'm assuming there's some minimum length of...