Chrome Extension Enhancement (UI Fix and Feature Addition)
Budget: $30 – $250 USD
Chrome Extension Developer (MidJourney + ChatGPT Integration, Visual Prompt Automation)
We’ve built a functional MVP of a Chrome extension called Smarter Image Generator. It generates MidJourney-ready image prompts from a script using the ChatGPT API. The prompts are broken into visual beats and displayed with timestamps. Our UI supports manual and automated workflows. We're now seeking an experienced Chrome extension developer to take over development, polish the user experience, and help scale the tool.
What’s Already Working:
Upload .txt script or paste directly into the popup
Split script into visual beats (by word count or GPT)
Generate visual prompts via ChatGPT (based on selected style preset)
Style presets include:
Friendly name
Comma-delimited styles (e.g. "monochrome, cinematic")
Custom system prompt (used with ChatGPT)
Prompts are generated, numbered, and include timestamp filenames
Automation mode allows prompts to be batch processed
Manual mode allows user to choose from MidJourney-generated images
Prompts include start/end time for video editor syncing
Settings saved with API key validation (color feedback)
Buttons open MidJourney or embedded settings view inside the popup
Remaining Features / Fixes:
Here’s what needs to be completed or improved based on our working code:
Bugs / Fixes:
Ensure all buttons (Settings, Open MidJourney, Start) always work after popup reopens
Script text and filename should persist even after closing the popup
Generated prompts should not reset unless a new file is uploaded or pasted
Display generated prompts as clean, scrollable HTML (not inside text boxes)
Retry button logic still references systemPrompt error and needs cleanup
Improvements:
Allow user to hide or close the embedded Settings iframe inside the popup
Add toggle for “Include Start/End Timestamps in Filename”
Allow user to define image naming convention (e.g. [beatId]-[summary])
Display thumbnails of generated MidJourney images inside the extension (optional)
Local history/log of previously generated prompts for recovery
Ideal Developer:
Deep experience with Chrome extension APIs (manifest v3+)
Strong knowledge of DOM scripting, JS modules, and async APIs
Familiar with MidJourney Web UI behavior and injection constraints
Familiarity with ChatGPT API, prompt engineering, and error handling
Bonus: experience with image or video automation/editor workflows
Delivery:
Work will be done directly on top of our current working extension (ZIP provided)
Code must be modular, commented, and cleanly structured
We’ll review all changes, iterate collaboratively, and expand scope over time
The remaining tasks for the extension—fixing bugs, polishing the UI, improving the prompt workflow, and adding minor features like timestamp toggles and filename customization—should take approximately 20 to 30 hours to complete. This estimate includes time for testing, revisions, and clear communication throughout the process.
Bid for those many hours
We’ve built a functional MVP of a Chrome extension called Smarter Image Generator. It generates MidJourney-ready image prompts from a script using the ChatGPT API. The prompts are broken into visual beats and displayed with timestamps. Our UI supports manual and automated workflows. We're now seeking an experienced Chrome extension developer to take over development, polish the user experience, and help scale the tool.
What’s Already Working:
Upload .txt script or paste directly into the popup
Split script into visual beats (by word count or GPT)
Generate visual prompts via ChatGPT (based on selected style preset)
Style presets include:
Friendly name
Comma-delimited styles (e.g. "monochrome, cinematic")
Custom system prompt (used with ChatGPT)
Prompts are generated, numbered, and include timestamp filenames
Automation mode allows prompts to be batch processed
Manual mode allows user to choose from MidJourney-generated images
Prompts include start/end time for video editor syncing
Settings saved with API key validation (color feedback)
Buttons open MidJourney or embedded settings view inside the popup
Remaining Features / Fixes:
Here’s what needs to be completed or improved based on our working code:
Bugs / Fixes:
Ensure all buttons (Settings, Open MidJourney, Start) always work after popup reopens
Script text and filename should persist even after closing the popup
Generated prompts should not reset unless a new file is uploaded or pasted
Display generated prompts as clean, scrollable HTML (not inside text boxes)
Retry button logic still references systemPrompt error and needs cleanup
Improvements:
Allow user to hide or close the embedded Settings iframe inside the popup
Add toggle for “Include Start/End Timestamps in Filename”
Allow user to define image naming convention (e.g. [beatId]-[summary])
Display thumbnails of generated MidJourney images inside the extension (optional)
Local history/log of previously generated prompts for recovery
Ideal Developer:
Deep experience with Chrome extension APIs (manifest v3+)
Strong knowledge of DOM scripting, JS modules, and async APIs
Familiar with MidJourney Web UI behavior and injection constraints
Familiarity with ChatGPT API, prompt engineering, and error handling
Bonus: experience with image or video automation/editor workflows
Delivery:
Work will be done directly on top of our current working extension (ZIP provided)
Code must be modular, commented, and cleanly structured
We’ll review all changes, iterate collaboratively, and expand scope over time
The remaining tasks for the extension—fixing bugs, polishing the UI, improving the prompt workflow, and adding minor features like timestamp toggles and filename customization—should take approximately 20 to 30 hours to complete. This estimate includes time for testing, revisions, and clear communication throughout the process.
Bid for those many hours