AI Development for Manhwa Recaps
Budget: $30 – $250 USD
I need a freelancer proficient in Node.js, Python, and AI. Your task will be to modify my existing code and develop an AI capable of summarizing manhwa.
so how my code works is I input images in a file it slices the images while generating a recap of it using Azure ai has a lot of restrictions and is very bad with character recognition so what I would want you to do is develop/combine ai to make a model/ai that recap with the knowledge of the previous image has good character recognition and it finds the main character and everything by following the flow of the story and I want you to use a free to use model to then convert the English recap to other languages debug everything so there is no error while making the video don't make it so I have to like make a character profile and stuff and the output has to be similar to the expected output add a free ai humanizer and stuff so even if I make the same image I get different output and bear in mind it has to be free or very very cheap and the summary the ai is giving it has to match the image
after all the thing is done and I am satisfied I will be owning 100% of it
current output: https://youtu.be/j_XSoqtD8y0?si=MCzx7qyQJomhkNUT
Expected output: https://www.youtube.com/watch?v=XiItNbTkPZw&ab_channel=AniManga
Output no 2: https://youtu.be/TPFn4TO2Xa8?si=EJfsteENlG2o1XGC
Key Requirements:
- Utilize a specific vision model and a writing model to create the summaries. (Note: The specific models for vision and writing tasks have not been decided yet, and I would appreciate your input.)
- The AI should be cost-effective, ideally free, and should not have any content filters or restrictions.
- The job will involve debugging, adding new features, and optimizing the code.
Please note, I will provide further details on how to modify my code. Ideal candidates would be those who can deliver high-quality work in a timely manner.
so how my code works is I input images in a file it slices the images while generating a recap of it using Azure ai has a lot of restrictions and is very bad with character recognition so what I would want you to do is develop/combine ai to make a model/ai that recap with the knowledge of the previous image has good character recognition and it finds the main character and everything by following the flow of the story and I want you to use a free to use model to then convert the English recap to other languages debug everything so there is no error while making the video don't make it so I have to like make a character profile and stuff and the output has to be similar to the expected output add a free ai humanizer and stuff so even if I make the same image I get different output and bear in mind it has to be free or very very cheap and the summary the ai is giving it has to match the image
after all the thing is done and I am satisfied I will be owning 100% of it
current output: https://youtu.be/j_XSoqtD8y0?si=MCzx7qyQJomhkNUT
Expected output: https://www.youtube.com/watch?v=XiItNbTkPZw&ab_channel=AniManga
Output no 2: https://youtu.be/TPFn4TO2Xa8?si=EJfsteENlG2o1XGC
Key Requirements:
- Utilize a specific vision model and a writing model to create the summaries. (Note: The specific models for vision and writing tasks have not been decided yet, and I would appreciate your input.)
- The AI should be cost-effective, ideally free, and should not have any content filters or restrictions.
- The job will involve debugging, adding new features, and optimizing the code.
Please note, I will provide further details on how to modify my code. Ideal candidates would be those who can deliver high-quality work in a timely manner.