WhatsApp AI Virtual Try-On Integration Service

I’m putting together a WhatsApp concierge that lets online fashion sellers send a garment photo, take payment through Razorpay, and instantly receive an AI-generated “model shot” back in the same chat. The core logic and UI flow are already mapped; what I’m missing is the glue that makes each piece talk to the next—securely, reliably, and at scale.

Here’s the flow I need you to wire up:

1. Receive an inbound image on WhatsApp via either Wati, Interakt, or Twilio (whichever you already work fastest with).
2. Ping Razorpay’s APIs to confirm payment.
3. Forward the image to a ComfyUI workflow running on a RunPod serverless endpoint that leverages OOTDiffusion or ControlNet for the actual virtual try-on.
4. Return the final dressed-model image to the same WhatsApp conversation.

Key expectations
• You’ve set up ComfyUI on RunPod before and can show me a working endpoint.
• You’re comfortable with at least one of the above WhatsApp Business APIs and can demonstrate prior message-automation work.
• You can share a portfolio link or repo containing AI image manipulation samples—ideally virtual try-ons.

Deliverables
• Fully deployed serverless endpoint on RunPod with ComfyUI, pre-loaded with my workflow JSON.
• Node.js or Python micro-service (your choice) that:
– Listens for WhatsApp webhook events,
– Checks Razorpay order status,
– Streams the image to RunPod and fetches the result,
– Sends the processed image back to WhatsApp.
• A brief README covering environment variables, setup steps, and one-click deployment instructions.
• Short loom or screen recording proving the full round-trip from WhatsApp message to returned image.

Acceptance criteria
The conversation round-trip—from customer photo to final AI render—must complete in under 60 seconds for a 1 MB JPEG on a standard RunPod “Medium” instance, with no manual intervention.

If this sounds like your wheelhouse, drop me a note with links to earlier try-on projects or ComfyUI automations you’ve shipped.