docs(together-video): add FLUX 3 to the model reference - #66
Open
MaanavD wants to merge 1 commit into
Open
Conversation
FLUX 3 is served on Together as `black-forest-labs/FLUX-3` and appears in the serverless video models table at $0.17/video, but the skill's model reference does not list it, so an agent picking a model from this skill never sees it. Adds the row and updates the feature table: FLUX 3 generates audio, takes first, last and storyboard keyframes, runs 5 to 20 seconds, and outputs 1080p.
Broly Security ScanNote ✅ Clean scan Note Re-scan this PR anytime with
|
MaanavD
marked this pull request as ready for review
August 17, 2026 22:54
Author
|
@zainhas (are you the DRI?) |
Collaborator
Yes thanks, I'll take a look! |
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
2 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Together serves
black-forest-labs/FLUX-3and lists it in the serverless model table, but thetogether-videoskill's model reference does not include it, so an agent using this skill will not consider it.Adds FLUX 3 to the model table and to the audio generation, first and last keyframe, and 1080p feature rows, plus a new row for durations beyond 10 seconds. The dimensions column gives both the human-readable resolutions and the
hdandfhdvalues the API accepts, since the API takes named tiers rather than pixel dimensions.python3 scripts/quick_validate.py skills/together-videoreportsOK together-video, 1 skill validated, 0 errors.