DRAFT - refactor to use sapiens / normal / identity loss / #6
Conversation
This file contains 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
|
FYI sapiens / human lift is coming https://x.com/rawal_khirodkar/status/1841188158857191860?s=46&t=-tkSIrsyNobBjIvQ2IAQwQ |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.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.
currently getting OOM.
but the normal image looks much sharper.
if you have a100 - 40gb + facebook sapiens models - this may boost results to SOTA.
the normalmap_vis should work first - and spit out the normal image.
python normalmap_vis.py '/home/oem/Desktop/OLD/image_1.png' test.png test.pnythe inference i rebuild to use a class - it has identity loss added to make face look better.
this refactored inference commit should work fine as is - just cherry pick
https://github.com/johndpope/MagicMan/blob/cabc9460c583e19211ec214f834f462bcc2ace64/inference.py
I test tomorrow on a100..