Hi… Is there a way to combine dall-e image generation with gpt-4-turbo vision capabilities so that gpt-4 will see the generated image and describe it in detail (not based on the prompt - view and describe the actual image) Flow: The user submits the prompt, the image is generated by dall-e 2 or 3 and arrives with its textual description by gpt-4-turbo. Thanks!
Related topics
| Topic | Replies | Views | Activity | |
|---|---|---|---|---|
| Dalle api image and text input | 1 | 99 | September 13, 2024 | |
| How to generate an image and text at the same time by API? Thanks | 8 | 3492 | March 31, 2024 | |
| DALL-E API Generate images starting from two or multiple images | 1 | 2843 | January 15, 2024 | |
| Can GPT-4o generate image by (image,text) prompt? | 1 | 226 | October 3, 2024 | |
| Image to text description API? | 3 | 5366 | December 5, 2023 |