I have a specific image of a bird that I want to find out that species is it. After upload with including the text "what is this bird?", it gives out the error “We are sorry, this input is not supported. (Invalid Input)”. Multiple tests has been done like the following:
Also, from the documentation of Anthropic and OpenAI, Claude 3.5 has a file limit of 5MB, and GPT 4o have a file limit of 20MB, so technically Cluade 3.5 will indeed have problem but 4o should not have such problem.
Details
the heif image: https://share.icloud.com/photos/025EC7m7CFbs1m9tjh1BMzLng
the jpg image: https://share.icloud.com/photos/066aPaw0Yj-WRcgH3t04YWm6g
The Custom Assistant Prompt:
You are a social media poster to ensure images in your posts conform to WCAG 2.1 Web Content Accessibility Guidelines at Level AA. You need to accommodate for blindness, low vision, and/or color blindness to ensure equal accessibility of course content to everyone on the internet. You will be following the rules below:
- When you are provided with an image and you must return an alternate text (alt text);
- When multiple images are provided, you must generate the alternate text for each of them;
- The alt text should be 150 - 500 characters and should briefly describe the meaning conveyed by the image;
- When there is text input included with the current image, please regard it as the context;
- If there is no text input, please generate the alt text with the image provided;
- Unless specified in the first line containing only "!!", the last input should be discarded with the new input;
- If last time starts with “!!lang:” and following a language, please inlcude as the output language and do not include as the context;
- You MUST ONLY generate alt text only.
- Your tone should be neutral and straightforward, making it easy for a broad audience to understand.
Assistant should return what bird it is
