Sketch-to-Image Pipeline Implementation Bounty [$900]

[JJassonn69]

Overview

We're excited to expand the capabilities of our AI-Network by introducing a new sketch-to-image pipeline. This innovative feature will allow users to generate creative images from simple sketches, adding multiple avenues for AI-enhanced art creation to our AI network. 🔥

We’re inviting the community to assist in implementing this new pipeline within the AI-worker component of the AI-Network. By contributing to this pipeline, you will empower artistic visions and speed up the creation utilizing the decentalized Livepeer AI-Network. 🚀

Required Skillset

• Proficient in FastAPI.
• Strong background in Python.
• Familiarity with Docker and Hugging Face 🤗.

Bounty Requirements

1. Implementation: Develop a working /sketch-to-image route and pipeline within the AI-worker repository. This new pipeline must be accessible via Docker on port 8800.
2. Functionality: The pipeline should accept an initial sketch image and a text prompt to generate a corresponding image. It should also offer adjustable parameters such as negative_prompt, controlnet_conditioning_scale, num_inference_steps, width, and height based on the model's requirements.

Scope Exclusions

• This bounty does NOT require the complete end-to-end implementation of this pipeline on the go-livepeer side, including payment processing or job routing. These aspects will be managed by the AI SPE team or addressed in a future bounty.

Implementation Tips

To learn how to create a new pipeline, refer to the Hugging Face spaces. You can also explore the following pull requests to see how other pipelines were implemented:

• Pull Request #96
• Pull Request #103

In some cases, you may not be able to integrate the new pipeline directly into the regular AI Runner Docker container due to dependency conflicts or missing packages. If this occurs, you can follow the approach outlined in livepeer/ai-worker#185 to create a custom container for the pipeline. This approach uses the regular AI runner as the base while keeping the base container lean.

Additionally, keep the following best practices in mind:

• Build on Previous Work: Review existing implementations of sketch-to-draw available in Hugging Face documentation and this space. These can serve as helpful starting points.
• Consult Developer Resources: Our developer documentation for the worker and runner includes useful tips for mocking pipelines and debugging directly, which can accelerate the development process.
• Update OpenAPI Specification: Use the runner/gen_openapi.py script to generate an updated OpenAPI specification.
• Generate Go-Livepeer Bindings: In the main repository directory, run the make command to generate the necessary bindings, ensuring compatibility with the go-livepeer repository.

How to Apply

1. Express Interest: Comment on this issue to show your interest and explain why you would be a great fit for this task.
2. Await Review: Our team will review the applications and select the most suitable candidate.
3. Get Assigned: If chosen, the GitHub issue will be assigned to you.
4. Start Working: Begin the task! If you need assistance or have questions, comment on the issue or join discussions in the #developer-lounge channel on our Discord server.
5. Submit Your Work: Create a pull request in the relevant repository and request a review.
6. Notify Us: Comment on this GitHub issue once your pull request is ready for review.
7. Receive Your Bounty: After your pull request is approved, we will arrange the bounty payment.
8. Earn Recognition: Your contributions will be highlighted in our project’s changelog.

We’re excited to see your interest in contributing to our project! 💛

Warning

Please ensure the issue is assigned to you before starting work. To prevent duplication of efforts, unassigned issue submissions will not be accepted.

[yaodingyd]

👋 I would like to give this a try. I have a lot experience in python with flask/FastAPI, and k8s/docker, decent experience in AI related fields

[diszrythm]

I am interested in this task. I have strong background in python, but I come from Reasearch and Development sector related to signal processing domain. It will be a great learning experience for me.

[rickstaa]

Hey @yaodingyd,

Thanks so much for your interest in contributing to our open-source ecosystem! Apologies for the delayed response—we've been busy wrapping up deliverables ahead of Token2049 🚀. I had a chance to review your profile, and I believe you're a great fit for this bounty. I've gone ahead and assigned it to you.

Looking forward to your contributions!

[rickstaa]

I am interested in this task. I have strong background in python, but I come from Reasearch and Development sector related to signal processing domain. It will be a great learning experience for me.

Hey @diszrythm,

Thank you for your enthusiasm in contributing to our ecosystem! 🚀 Unfortunately, I've already assigned this bounty to @yaodingyd, but don't worry—there will be plenty more opportunities coming up that you can jump on. 🔧 Stay tuned!