Minigpt 4_vicuna 13b



The minigpt-4_vicuna-13b model is designed for image-to-text tasks such as image captioning and interpretation. Upon receiving an image URL and a question or prompt about that image as input, it uses its Vicuna-13B transformer to generate a detailed, descriptive response. For instance, if given a photo and asked "Why is this photo funny?", it generates an interpretive response about the content of the image. It's been optimized for humor understanding, irony detection, and narrative generation of up to 500 new tokens.

Use cases

The minigpt-4_vicuna-13b AI model, designed for image question and captioning use, possesses a wide range of potential use-cases. From analyzing images to create descriptive or humorous explanations, this model could be helpful in creating engaging social media captions or enhancing visually impaired users' web browsing by providing audio descriptions of visual content. Similarly, it could be used in education or entertainment, for creating captivating narratives for visual content or engaging games that revolve around interpreting images. The AI's ability to create creative, detailed, and direct responses based on image input also shows potential in professional sectors such as advertising, to generate compelling ad content, or in customer service, to decode customer queries based on shared visuals. Furthermore, the technology might be utilized by law enforcement or investigative journalists, to generate narratives or hypotheses based on visual evidence.



Cost per run
Avg run time

Creator Models

Op Replay Clipper$?411
Minigpt 4_​vicuna 13b$?0
Minigpt 4_vicuna 7b$?7,730
Minigpt 4_​vicuna 7b$?0

Similar Models

Try it!

You can use this area to play around with demo applications that incorporate the Minigpt 4_vicuna 13b model. These demos are maintained and hosted externally by third-party creators. If you see an error, message me on Twitter.

Currently, there are no demos available for this model.


Summary of this model and related resources.

Model NameMinigpt 4_vicuna 13b
MiniGPT-4 w/ Vicuna-13B (Image Question/Captioning Use)
Model LinkView on Replicate
API SpecView on Replicate
Github LinkView on Github
Paper LinkNo paper link provided


How popular is this model, by number of runs? How popular is the creator, by the sum of all their runs?

Model Rank
Creator Rank


How much does it cost to run this model? How long, on average, does it take to complete a run?

Cost per Run$-
Prediction Hardware-
Average Completion Time-