-
Notifications
You must be signed in to change notification settings - Fork 455
add support for image-to-image models on Replicate #1427
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
add support for image-to-image models on Replicate #1427
Conversation
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
thanks for the PR @zeke, could you please update the task mapping as well?
replicate: { |
…nference API (#1439) This PR is a prerequisite for #1427. It refactors the payload construction for `hf-inference` by isolating it into a separate async function. Note that adding a new async function to build the payload is necessary because `HFInferenceImageToImageTask.preparePayload` cannot be made async, yet the payload construction requires asynchronous operations. A similar pattern has already been implemented for [automaticSpeechRecognition](https://github.com/huggingface/huggingface.js/blob/361a0fad4c68943592f0bcbe41592d785eedcb81/packages/inference/src/tasks/audio/automaticSpeechRecognition.ts#L36) with fal.
Hi @zeke, |
Starting over here, since it seems a lot has changed: #1564 |
A redo of #1427 cc @SBrandeis @Vaibhavs10 --------- Co-authored-by: SBrandeis <simon@huggingface.co>
This PR adds support for the
image-to-image
task type for Replicate models.Example:
cc @hanouticelina