microsoft / microsoft/WindowsAppSDK

No prompt for ImageDescriptionGenerator

Open
#5,186 4 comments 2 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

area-WCR Status: Investigating
Dominant language
C++
Stars
4.7k
Forks
471
Avg merge
3d 13h
Merged PRs (30d)
28

Description

The `ImageDescriptionGenerator` is missing an option to make a prompt to guide the response to what sort of description is requested. The prompt could be to ignore objects in the background, or ask specific questions about the subject in the image.

When I was using the Phi3Vision model directly this was a huge benefit and opened up quite a few scenarios for analyzing images.

Contributor guide

No contributing guide indexed for this repository

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start by locating the ImageDescriptionGenerator implementation and its public API, then compare its capabilities with the prompt option available when using the Phi3Vision model directly. Define the prompt input and verify that callers can guide image descriptions toward a requested subject or scope.

Written by the indexing model from the issue text.

Assessment

Tech stack
cpp
Domain
ai, desktop
Issue type
Feature
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Mostly clear
Newbie friendliness
35/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.