Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Being able to generate images #24

Open
MrCsabaToth opened this issue Aug 11, 2024 · 2 comments
Open

Being able to generate images #24

MrCsabaToth opened this issue Aug 11, 2024 · 2 comments
Labels
enhancement New feature or request multi modal Multi Modality related

Comments

@MrCsabaToth
Copy link
Member

Gemini can generate images. We should enhance the image chat to be able to receive an image (or images) from the model. We can present them in a carousel and let the user pick or download.
Ref #9

@MrCsabaToth MrCsabaToth added the enhancement New feature or request label Aug 11, 2024
@MrCsabaToth MrCsabaToth added the multi modal Multi Modality related label Aug 21, 2024
@MrCsabaToth
Copy link
Member Author

Gemini Advanced itself is relying on Imagen3. This is the way https://www.theverge.com/2024/8/28/24230445/google-gemini-create-ai-generated-people-imagen-3

@MrCsabaToth
Copy link
Member Author

We should now wait out Gemini 2.0 in 2025 will be able to natively generate images!

You can start experimenting with the Gemini 2.0 model (gemini-2.0-flash-exp) using the Vertex AI in Firebase SDKs.
Right now, our SDKs support text output from text, code, image, PDF, audio, video, and video with audio inputs. Support for the Multimodal Live API as well as native audio and image output will be coming in 2025!

Screenshot_2024-12-15_13-59-13

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
enhancement New feature or request multi modal Multi Modality related
Projects
None yet
Development

No branches or pull requests

1 participant