In cases where you want to build for all runtimes, you can still develop with ESM and use npm dependencies with a tool like pika.dev. This will transform the imports on-the-fly to their respective absolute path. Source: about 3 years ago

Isn't there only two open multimodal LLMs, LLaVA and mini-gpt4? Source: 12 months ago

So we use MiniGPT-4 for image parsing, and yep it does return a pretty detailed (albeit not always accurate) description of the photo. You can actually play around with it on Huggingface here. Source: about 1 year ago

We use MiniGPT-4 first to interpret the image and then pass the results onto GPT-4. Hopefully, once GPT-4 makes its multi-modal functionality available, we can do it all in one request. Source: about 1 year ago

But I would like to bring up that there are some multi models(llava, miniGPT-4) that are built based on censored llama based models like vicuna. I tried several multi modal models like llava, minigpt4 and blip2. Llava has very good captioning and question answering abilities and it is also much faster than the others(basically real time), though it has some hallucination issue. Source: about 1 year ago

Https://minigpt-4.github.io/ <-- free image recognition, although not powered by true GPT-4. Source: about 1 year ago