[Inference Providers] Add image-text-to-image and image-text-to-video support for wavespeed
#1882
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
Wauplin
approved these changes
Dec 16, 2025
Contributor
Wauplin
left a comment
Wauplin
left a comment
There was a problem hiding this comment.
Hacky but nice it works! 😄
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Outdated suggestions cannot be applied.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.
Discussed internally in this thread.
This PR adds support for the
image-text-to-imageandimage-text-to-videotasks for wavespeed provider. These tasks support models that accept both optional image + text input.For these tasks, we use the same endpoints as for
image-to-imageandimage-to-video, when no image is provided, we send a 1x1 fully transparent image. Note that wavespeed's doesn't follow a consistent endpoint naming pattern that would allow us to have the same logic as for fal in #1879.I've tested it (i.e. text only input) with FLUX-2 and and the results looks reasonable to me:
"A robot playing chess in a garden"
"A butterfly landing on a flower"
wavespeed_video_placeholder_4.mp4