-
As I understand your model denoiser_model.onnx is a repackaged version of
DeepFilterNet3_onnx.tar.gz , so to make that more clear then maybe it can make sense to give it a name starting with
Dee…
-
Hi, from my understanding of the code, in line 303 of Models/interpretable_diffusion/gaussian_diffusion.py, the sample refers to x_{t-1}. However, within the langevin_fn, the input to the denoiser in …
-
### 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?
I don't know if you are interested in and if…
-
I trained a 128x64 model (with sparse=False); if I record the ~39 *denoiser outputs* during the course of a single sampling loop and compute their mse loss (*not* weighted by lambda_sigma because this…
-
Hi,
Thanks for your impressive work! I want to know if, you train the denoiser with Pointnet++ from scratch? Have you ever try to train denoiser with pretrained weights of PointNet++, or any other …
-
Hi,
Are there plans to add in denoise capabilities to this opensource repository? It looks like Aurora has that ability according to this video?
https://www.youtube.com/watch?v=8tDJn8ms-y8
An…
-
Running the following on master works fine:
```
$ python examples/sdxl.py --seed 0
output validated with distance=0.00034500996116548777
```
Changing the code to use the SplitVanillaCFG causes …
-
Dear Authors,
Thank you for your great work! In your paper (page 7), you mention that the dictionary of base is polynomial in the dimension d (not exponential) and this may help you overcome the "c…
-
When training more than 3,000 images, how should each parameter be adjusted to make the effect better?
-
A denoiser would be really cool!