[Advanced DreamBooth LoRA SDXL] Support EDM-style training (follow up of #7126) #7182
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
linoytsaban
changed the title
|
The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. The docs are available until 30 days after the last update. |
sayakpaul
reviewed
Mar 8, 2024
examples/advanced_diffusion_training/train_dreambooth_lora_sdxl_advanced.py
Outdated
Show resolved
Hide resolved
sayakpaul
reviewed
Mar 8, 2024
Comment on lines
1835
to
1845
| def get_sigmas(timesteps, n_dim=4, dtype=torch.float32): | ||
| sigmas = noise_scheduler.sigmas.to(device=accelerator.device, dtype=dtype) | ||
| schedule_timesteps = noise_scheduler.timesteps.to(accelerator.device) | ||
| timesteps = timesteps.to(accelerator.device) | ||
|
|
||
| step_indices = [(schedule_timesteps == t).nonzero().item() for t in timesteps] | ||
|
|
||
| sigma = sigmas[step_indices].flatten() | ||
| while len(sigma.shape) < n_dim: | ||
| sigma = sigma.unsqueeze(-1) | ||
| return sigma |
There was a problem hiding this comment.
Add a todo here to revisit different sampling algorithms for obtaining the sigmas. Ideally, Tero Karras should just drop a PR here just sayin' 🤷♂️
sayakpaul
approved these changes
Mar 8, 2024
|
Did you notice anything particularly notable @linoytsaban? |
|
@sayakpaul wanna take one more look? |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
This PR adds support for EDM-style training to the advanced script, based off PR #7126