Directus Reviews

MiniGPT-4 Reviews

Directus mentions (118)

• How to Deploy Directus as a Backend-as-a-Service (BaaS) on Koyeb

  Directus is an open data platform built to serve as a headless CMS, API, or Backend-as-a-Service (BaaS) for other applications. It is designed to make data accessible to people of all technical levels and to make it easy to build data-centric applications. Directus is extensible and can be integrated with many different frontend technologies to create stable, well-structured development and user experiences. - Source: dev.to / about 1 month ago

• Form to DB

  I don't know, it's something I've wanted many times. Recently I discovered https://directus.io/ which comes pretty close and it's open source. - Source: Hacker News / 3 months ago

• A list of SaaS, PaaS and IaaS offerings that have free tiers of interest to devops and infradev

  Directus — Headless CMS. A completely free and open-source platform for managing assets and database content on-prem or in the Cloud. There are no limitations or paywalls. - Source: dev.to / 4 months ago

• A Year of Self-Hosting: 6 Open-Source Projects That Surprised Me in 2023

  The Backend to Build Anything or Everything | Directus. - Source: dev.to / 6 months ago

• Prismic.io is increasing our price by *1900%* over Christmas

  I using Directus CMS on several projects with pretty complicated flows, api extensions etc. probably there will be some work if you move. I liked Directus is because it's standard SQL I can always move my DB and documents to another solution. I don't use their hosted solution but they have an unlimited offering for $100 / month. Source: 6 months ago

MiniGPT-4 mentions (8)

• Multimodal LLM for infographics images

  Isn't there only two open multimodal LLMs, LLaVA and mini-gpt4? Source: 11 months ago

• Upload a photo of your meal and get roasted by ChatGPT

  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

• Upload a photo of your meal and get roasted by ChatGPT

  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

• Give some love to multi modal models trained on censored llama based models

  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

• Where can buy an openai account with GPT-4 access?

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