A bot that describes photos and draws from text

Send the bot a photo — it describes it; type words — it creates a picture, and the result goes to your email.

  • A description of any photo you send
  • A picture from a text prompt
  • The bot figures out the request type
  • The result arrives by email
Nvidia
Set it upScriptera

How it works

To create devino records from Telegram without manual input, use a ready-made scenario.

  1. Starts when: 📱 Telegram Trigger
  2. Then: 📋 Extract Message Data
  3. Check: 🔀 Route by Content Type - Image or Text
  4. If yes: 📸 Get Image file from Telegram
  5. Then: Analyze image using GPT-4O-Mini
  6. Check: 🔀 Merge AI Results
  7. Then: Send a message of image-to-text results
  8. Then: HTTP Nvidia Vila
  9. If no: Get Text from Telegram
  10. Then: NVIDIA API NVIDIA Stable Diffusion 3
  11. Then: Convert to Binary File
  12. Then: Send a message of text-to-image results

You can launch this Telegram + devino integration in Scriptera: describe the task in plain words — the scenario is built, launched and monitored for you.

Similar scenarios