Add Omnidreams driving application on the v2 API - #499
Closed
jarcherNV wants to merge 2 commits into
Closed
Conversation
The first v2 application that generates from something other than a prompt: it continues from a first frame and follows an HDMap for every frame it generates. The model is the single-view distilled checkpoint the v1 flashdreams-omnidreams package already configures, so this package is the application around it and holds no model code. Per-step conditioning goes through an HDMapSource seam rather than through ISession, so that a Ludus scene rendered from driver input can be added later without changing anything above it. The one implementation today reads recorded video. The source is also what says how long a run is, since a recording ends when the road does. The Python module is omnidreams_v2 because v1 owns the omnidreams name and this imports it, the same way t2v_self_forcing imports self_forcing.
|
Auto-sync is disabled for draft pull requests in this repository. Workflows must be run manually. Contributors can view more details about this message here. |
Collaborator
Author
|
Closing this PR as it was written before the new threading changes and I think it would be easier just to write this again rather than attempt to rebase, port, and clean it up after those changes were merged. |
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
The first v2 application that generates from something other than a prompt: it continues from a first frame and follows an HDMap for every frame it generates. The model is the single-view distilled checkpoint the v1 flashdreams-omnidreams package already configures, so this package is the application around it and holds no model code.
Per-step conditioning goes through an HDMapSource seam rather than through ISession, so that a Ludus scene rendered from driver input can be added later without changing anything above it. The one implementation today reads recorded video. The source is also what says how long a run is, since a recording ends when the road does.
The Python module is omnidreams_v2 because v1 owns the omnidreams name and this imports it, the same way t2v_self_forcing imports self_forcing.