Improve README accuracy and links

[glenn-jocher]

Summary

• updates the root README for the current three-model Replicate workflow
• corrects nested model README details for Python version and YOLOE weights
• preserves existing badges, backlinks, and social links

Validation

• git diff --check
• lychee --no-progress --accept 200,429 README.md yolo11n/README.md yoloe11s/README.md yolov8s-worldv2/README.md
• python -m py_compile test_prediction.py yolo11n/predict.py yoloe11s/predict.py yolov8s-worldv2/predict.py yolo11n/download.py yoloe11s/download.py yolov8s-worldv2/download.py
• python test_prediction.py --help
• parsed all three cog.yaml files with PyYAML

🛠️ PR Summary

_{Made with ❤️ by Ultralytics Actions}

🌟 Summary

🚀 This PR expands the ultralytics/replicate repo from a single YOLO11n deployment into a multi-model Replicate deployment setup, with clearer docs, model-specific download steps, and updated workflow guidance.

📊 Key Changes

• 📦 Broadened repository scope from only YOLO11n to support multiple Ultralytics models:
  • yolo11n
  • yolov8s-worldv2
  • yoloe11s
• 📝 Reworked the main README.md to describe the repo as a general Ultralytics-to-Replicate deployment template rather than a YOLO11n-only project.
• 🗂️ Updated repository structure docs to show new model directories and shared test assets.
• ⚙️ Revised deployment instructions so users can deploy any supported model, including running each model’s download.py before cog push.
• 🤖 Clarified GitHub Actions behavior:
  • Workflow naming changed from “Push YOLO11n to Replicate” to “Push YOLO to Replicate”
  • CI/CD now builds, tests, and deploys each configured model on main
• 📋 Added an “Available Models” table summarizing Replicate endpoints, predictor classes, and model purposes.
• 🔽 Documented explicit model staging via download.py instead of relying only on runtime auto-download behavior.
• 🧪 Improved local testing instructions by using a sample asset (assets/bus.jpg) and making YOLO11n testing steps more explicit.
• 🐍 Updated yolo11n documentation to note Python 3.12 instead of 3.11.
• 🧠 Improved yoloe11s docs to clarify pre-build weight staging and CLIP dependency setup for prompt-based inference.

🎯 Purpose & Impact

• 🌍 Makes the repo more useful to a wider audience by supporting multiple model types, not just one detection model.
• 🚀 Simplifies deployment to Replicate with clearer, repeatable per-model setup steps.
• 🧩 Improves maintainability by organizing one Cog configuration per model, making future additions easier.
• ✅ Reduces deployment surprises by explicitly downloading required weights before build time.
• 📚 Improves onboarding for both developers and non-experts through clearer documentation and examples.
• 🔄 Strengthens automation so changes pushed to main can validate and deploy all configured models consistently.

[UltralyticsAssistant]

👋 Hello @glenn-jocher, thank you for submitting a ultralytics/replicate 🚀 PR! This is an automated message to help streamline review, and an engineer will assist you soon. Please review the checklist below to help ensure a smooth integration 😊

• ✅ Define a Purpose: Clearly explain the purpose of your fix or feature in your PR description, and link to any relevant issues. Ensure your commit messages are clear, concise, and adhere to the project's conventions.
• ✅ Synchronize with Source: Confirm your PR is synchronized with the ultralytics/replicate main branch. If it's behind, update it by clicking the 'Update branch' button or by running git pull and git merge main locally.
• ✅ Ensure CI Checks Pass: Verify all Ultralytics Continuous Integration (CI) checks are passing. If any checks fail, please address the issues.
• ✅ Update Documentation: Update the relevant documentation for any new or modified features.
• ✅ Add Tests: If applicable, include or update tests to cover your changes, and confirm that all tests are passing.
• ✅ Sign the CLA: Please ensure you have signed our Contributor License Agreement if this is your first Ultralytics PR by writing "I have read the CLA Document and I sign the CLA" in a new message.
• ✅ Minimize Changes: Limit your changes to the minimum necessary for your bug fix or feature addition. "It is not daily increase but daily decrease, hack away the unessential. The closer to the source, the less wastage there is." — Bruce Lee

For more guidance, please refer to our Contributing Guide. Don't hesitate to leave a comment if you have any questions. Thank you for contributing to Ultralytics! 🚀

[UltralyticsAssistant]

🔍 PR Review

_{Made with ❤️ by Ultralytics Actions}

Good README cleanup overall and the multi-model framing is much clearer. The main gap is that the manual deployment instructions no longer include the documented pre-build download step, and the YOLOE per-model README may now under-document the assets required for that deployment.

💬 Posted 2 inline comments

[UltralyticsAssistant]

Merged! 🎉 Thanks, @glenn-jocher — this is a great step forward for ultralytics/replicate.

By expanding the repo from a single YOLO11n deployment into a clear multi-model template, this PR makes Replicate deployments more scalable, easier to understand, and much more useful for the community. The improved docs, explicit model staging, and workflow updates all help turn this into a stronger foundation for future Ultralytics model support.

As Henry Ford said, “Coming together is a beginning; keeping together is progress; working together is success.” This update reflects that perfectly: a cleaner, more maintainable deployment structure that helps more users bring Ultralytics models to production with confidence.

Really appreciate the thoughtful improvements here. 🚀