Conversation
sajadn
commented
Nov 20, 2025
- add unit tests
- very minor cleanings
- add missing iter to the DiffusionDataModuleConfig
Signed-off-by: sajadn <snorouzi@nvidia.com>
Signed-off-by: Sajad Norouzi <snorouzi@nvidia.com>
Signed-off-by: Sajad Norouzi <snorouzi@nvidia.com>
Signed-off-by: sajadn <snorouzi@nvidia.com>
4b75aa7 to
2f46b43
Compare
Signed-off-by: sajadn <snorouzi@nvidia.com>
Signed-off-by: sajadn <snorouzi@nvidia.com>
|
/ok to test fa1b884 |
Signed-off-by: sajadn <snorouzi@nvidia.com>
|
/ok to test c376224 |
Signed-off-by: sajadn <snorouzi@nvidia.com>
c376224 to
644970d
Compare
Signed-off-by: sajadn <snorouzi@nvidia.com>
|
/ok to test 3e93c2a |
abhinavg4
left a comment
There was a problem hiding this comment.
Looks good. Let;s merge once tets pass
| "output_params": ["-f", "mp4"], | ||
| } | ||
|
|
||
| print("video_save_path", video_save_path) |
There was a problem hiding this comment.
Good cleanup! Removing debug print statements keeps the output clean in production.
| def build_datasets(self, context: DatasetBuildContext): | ||
| return self.dataset.train_dataloader(), self.dataset.val_dataloader(), self.dataset.test_dataloader() | ||
| return ( | ||
| iter(self.dataset.train_dataloader()), |
There was a problem hiding this comment.
Nice improvement! Wrapping dataloaders with iter() makes the interface more explicit and reduces potential confusion in downstream usage.
| DiTModelProvider: Configuration for the DiT-S model. | ||
| """ | ||
| return DiTModelProvider( | ||
| return DiTXLModelProvider( |
There was a problem hiding this comment.
Nit: In docstring it notes "DiT-S" but we provide DiTXLModelProvider.
| "mediapy>=1.2.4", | ||
| "megatron-bridge", | ||
| "wandb[media]>=0.23.0", | ||
| ] |
There was a problem hiding this comment.
Just to make sure, are mediapy and wandb included in OSRB?
Any dependency needs to be approved for open-source.
There was a problem hiding this comment.
oops, this is a great question. I'm not sure about that.
|
/ok to test 99ada83 |
|
Approved from Automation perspective |
|
/ok to test f007a7f |
* edm and data preprocess tests. Signed-off-by: sajadn <snorouzi@nvidia.com> * Minor cleanings for DiT. Signed-off-by: Sajad Norouzi <snorouzi@nvidia.com> * add dit unit test. Signed-off-by: Sajad Norouzi <snorouzi@nvidia.com> * add iter to the DiffusionDataModule. Signed-off-by: sajadn <snorouzi@nvidia.com> * add missing copyright. Signed-off-by: sajadn <snorouzi@nvidia.com> * use 'no caption' if caption is not present. Signed-off-by: sajadn <snorouzi@nvidia.com> * fix dit inference bug. Add wanbd to inference code. Signed-off-by: sajadn <snorouzi@nvidia.com> * update the DiT configs to be aligned with the original paper. Signed-off-by: sajadn <snorouzi@nvidia.com> * add wandb[video] and mediapy to uv. Signed-off-by: sajadn <snorouzi@nvidia.com> * adjust pos_ids in mock_dataset to have batch dimension, fuse adaLN layers, use DiTSelfAttention. Signed-off-by: sajadn <snorouzi@nvidia.com> * fix the diffusion sample size bug. Signed-off-by: sajadn <snorouzi@nvidia.com> * fix broken tests. Signed-off-by: sajadn <snorouzi@nvidia.com> --------- Signed-off-by: sajadn <snorouzi@nvidia.com> Signed-off-by: Sajad Norouzi <snorouzi@nvidia.com> Co-authored-by: Abhinav Garg <abhinavg@stanford.edu> Signed-off-by: Lawrence Lane <llane@nvidia.com>
* edm and data preprocess tests. Signed-off-by: sajadn <snorouzi@nvidia.com> * Minor cleanings for DiT. Signed-off-by: Sajad Norouzi <snorouzi@nvidia.com> * add dit unit test. Signed-off-by: Sajad Norouzi <snorouzi@nvidia.com> * add iter to the DiffusionDataModule. Signed-off-by: sajadn <snorouzi@nvidia.com> * add missing copyright. Signed-off-by: sajadn <snorouzi@nvidia.com> * use 'no caption' if caption is not present. Signed-off-by: sajadn <snorouzi@nvidia.com> * fix dit inference bug. Add wanbd to inference code. Signed-off-by: sajadn <snorouzi@nvidia.com> * update the DiT configs to be aligned with the original paper. Signed-off-by: sajadn <snorouzi@nvidia.com> * add wandb[video] and mediapy to uv. Signed-off-by: sajadn <snorouzi@nvidia.com> * adjust pos_ids in mock_dataset to have batch dimension, fuse adaLN layers, use DiTSelfAttention. Signed-off-by: sajadn <snorouzi@nvidia.com> * fix the diffusion sample size bug. Signed-off-by: sajadn <snorouzi@nvidia.com> * fix broken tests. Signed-off-by: sajadn <snorouzi@nvidia.com> --------- Signed-off-by: sajadn <snorouzi@nvidia.com> Signed-off-by: Sajad Norouzi <snorouzi@nvidia.com> Co-authored-by: Abhinav Garg <abhinavg@stanford.edu>