Equal to DALL·E 3!
Finally, we have the Gemini 1.5 Pro API, which can replace DALLE3! What else do you need for a bicycle!
The open source community has always dreamed of: DALLE3 interactive and prompt word generation capabilities + countless SD model drawing capabilities. This is unfortunate
Million contexts, multimodal + multi-round dialogues, marking/pushback
We are adding the just-released Gemini 1.5 Pro API to the previous Gemini in ComfyUI plug-ins!
This time, the 1.5 model directly supports multimodal + multi-round conversations, and can read video, audio and other files (the upper limit is 20G). The upper limit of tokens supported for input reaches 1.048,576. However, the current rate limit is relatively strict, only 2 times per minute
If you want to learn more, you can click on the link below the video.
Thank you for watching this video. If you like it, please subscribe and like it. thank
X post:
https://x.com/ZHOZHO672070/status/1777987475203330260
Video: