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

upgrade the open-flagminto-v2 #54

Open
numb3r3 opened this issue Jun 29, 2023 · 3 comments
Open

upgrade the open-flagminto-v2 #54

numb3r3 opened this issue Jun 29, 2023 · 3 comments

Comments

@numb3r3
Copy link
Member

numb3r3 commented Jun 29, 2023

The open-flagminto-v2 has just been released: https://laion.ai/blog/open-flamingo-v2/ We need to adopt it in opengpt for better compatible with huggingface.

@mvsoom
Copy link

mvsoom commented Aug 1, 2023

Would be great:)

@saahil
Copy link
Collaborator

saahil commented Aug 4, 2023

@mvsoom Hello, thanks for your feedback! Can you please tell us your use-case for which you'd like to use Flamingo v2?

@mvsoom
Copy link

mvsoom commented Aug 4, 2023

Hi saahil :) I want to use its capability for interleaving text and images for describing a single scene consisting of several webcam pictures taken at regular intervals. So this goes a bit beyond image captioning because there are $N$ correlated images in the prompt. An example for $N=2$ is attached (this is a random picture I found on the web).
web-rtc-demo
Example prompt for $N=2$:

<pic_1_description> Webcam capture taken 1 sec ago</pic_1_description> <pic_2_description> Webcam capture taken 0 sec ago</pic_2_description> Describe the scene consisting of these 2 images which are taken at 1 sec intervals

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

3 participants