[Inference Providers] deepinfra: add text-to-video support - #4719
Draft
ovuruska wants to merge 1 commit into
Draft
[Inference Providers] deepinfra: add text-to-video support#4719ovuruska wants to merge 1 commit into
ovuruska wants to merge 1 commit into
Conversation
Add DeepInfraTextToVideoTask for DeepInfra's asynchronous video generation:
POST /v1/openai/videos submits the job, then get_response polls
/v1/openai/videos/{id} until it succeeds or fails and returns the resulting
video bytes. prompt/model applied after caller parameters.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
What
Adds
DeepInfraTextToVideoTaskso thedeepinfraprovider supportstext-to-video.DeepInfra's video generation is asynchronous, so this submits and polls:
_prepare_route:/v1/openai/videos(POST submits the job)._prepare_payload_as_dict: forwardsprompt; appliesprompt/modelafter caller parameters so neither can be overridden.get_response: reads the jobid, polls/v1/openai/videos/{id}untilstatusissucceeded/failed, then downloadsdata[0].urland returns the video bytes. RaisesValueErroron failure/malformed output.Wired in
_providers/__init__.pyunderdeepinfra. Existing tasks untouched.Test
Added
test_text_to_video_{url,payload,model_not_overridable,response}toTestDeepInfraProvider(response test mocks the poll + download). All pass locally.🤖 Generated with Claude Code