Contact person: Business Client

Phone:Show

Email:Show

Location: United States

Budget: Recommended by industry experts

Time to start: As soon as possible

Project description:
"I’m building a web-based tool that lets users drop in an image (or simply click “skip image”) and instantly receive an engaging Instagram caption plus a curated set of hashtags. The core experience I have in mind is:

• Image upload or paste-URL → the system analyses the visual content to understand theme, mood, objects and setting.
• Text prompt (optional) → users can give a hint about the tone or a keyword they want included.
• One-click “Generate” → the app returns a punchy caption and a mix of high-reach, niche and branded hashtags, all ready to copy.

Everything runs in the browser; I’m not launching a mobile app for now. Because I’m open on the tech stack, you’re free to run with React, Angular, Vue, or any framework you think best suits a fast, responsive SPA. On the back end I expect a lightweight API layer (Node, Python/FastAPI or similar) that calls whichever vision-language model you prefer—OpenAI Vision, CLIP, Google’s Gemini, etc.—and layers on a bit of fine-tuning so the captions feel “on brand” rather than generic.

**3. Free Tier + Stripe Payments (IMPORTANT)

Users can generate up to 5 free captions per day.

Implement simple account system (email/password or OAuth).

When limit reached → show upgrade modal.

Stripe integration for paid plan (“Unlimited Captions” or similar).

Track usage per user in database.

4. Deployment

Provide README + deploy script / configuration for one of:

Vercel

Render

[login to view URL]

Standard VPS (Docker is fine)

5. Testing

Postman collection OR minimal test suite showing API endpoints work.
Acceptance criteria: the returned caption must reference at least one salient element detected in the image, and the hashtag list should include a mix of high-volume and contextual tags with no duplicates.

If this scope sounds clear and achievable, let me know what stack you’d pick and a rough timeline—then we can lock in milestones and get coding." (client-provided description)