🔥 7 days Hackathon
🦾 The first Stable Diffusion XL hackathon
✨ Even more models available! Use GPT-4, ChatGPT, Whisper, Cohere and AI21 and more!
🛠️ Incorporate Stable Diffusion 2.0 and Vercel software to your projects
🚀 Create your complete product MVP
🤝 Find co-founders and mentors on the lablab.ai platform

Stable Diffusion 2.0 AI Hackathon

No-rank

Apprentice

Triips

Clove

clove

The basic idea is that we scrape the site and use all that data to create a story about it, then once we get that we split that story insto smaller chunks that get drawing using stable diffussion text to image api. Once we get those we match them to the audio and send all that to clove backend to create a video out of it. 
The idea is to help understand complex subjects with visual and audio aids, this is still very exploratory and likely only useful for  specific use cases.
One of the downsides is that each video requires quite a bit of images so I have hit the max requests api limit, but I think I was able to find ways to minimize that. 

Provide a link to a scientific paper and get back a explainer (with still photos) video 

Paper to Explainer video

Stable Diffusion is a latent text-to-image diffusion model capable of generating stylized and photo-realistic images. It is pre-trained on a subset of of the LAION-5B dataset and the model can be run at home on a consumer grade graphics card so everyone can create stunning art within seconds.

Stable Diffusion

ChatGPT is a large language model trained by OpenAI to generate human-like text in a conversational style. It is a variant of the GPT-3 model, which was specifically designed to be used to generate text in response to user input. The ChatGPT model has been trained on a vast amount of text data, including conversations and other types of human-generated text, which allows it to generate text that is similar in style and content to human conversation. ChatGPT can be used to generate responses to questions, code, make suggestions, or provide information in a conversational manner, and it is able to do so in a way that is often indistinguishable from human-generated text. The initial model has been trained using Reinforcement Learning from Human Feedback (RLHF), using methods similar to InstructGPT, but with slight differences in the data collection setup. The model is trained using supervised fine-tuning, where human AI trainers provided conversations in which they played both sides—the user and an AI assistant. The trainers would have had access to model-written suggestions to help them compose their responses.

ChatGPT

Whisper is a general-purpose speech recognition model. It is trained on a large dataset of diverse audio and is also a multi-task model that can perform multilingual speech recognition as well as speech translation and language identification.

Whisper

One of the best AI labs in the world. By using the Cohere platform we are able to use one of the best and most powerful language models for our own! There are many tutorials, including our own one, that show how to use Cohere.

Cohere

AI21 Labs is a platform for building AI applications. It provides a suite of tools and guides for building AI applications and training models. AI21 Labs helps developers and businesses use cutting-edge language models, with no NLP expertise required. Access powerful language models using an API that makes you smile

AI21 Labs

Vercel is a platform designed for developers, providing speed, reliability, and scalability to create and deploy web applications. With built-in CI/CD, zero configuration, and deep integrations with popular Git providers such as GitHub, GitLab, and Bitbucket, Vercel streamlines the development process, making it easy for teams to collaborate and iterate on their projects.

Vercel

OpenAI Codex is an artificial intelligence platform that enables developers to translate natural language into code. 

Codex

Access large language models that can understand text and take appropriate action — like highlight a post that violates your community guidelines, or trigger accurate chatbot responses

Cohere Classify

Turn text into numerical representations of language for deeper insights at scale. Embed makes it possible to algorithmically categorize and score text quickly to extract meaning.

Cohere Embed

GPT-3 stands for Generative Pre-trained Transformer 3 and it is an autoregressive language model that uses deep learning to produce human-like text. It is the third-generation language prediction model in the GPT-n series created by OpenAI. GPT-3 is currently in open beta.

GPT-3

YOLOv7 is the new state-of-the-art object detector in the YOLO family. According to the paper, it is the  most accurate and fastest real-time object detection to date.

YOLOv7

GPT-4 is OpenAI's 4th generation Generative Pre-trained Transformer. It is a multimodal large language model that uses deep learning to produce human-like text, accepting image and text inputs. GPT-4 is OpenAI's most advanced system, producing safer and more useful responses

Triips Blonch@Triips

Events attended

Submissions made

I built with

Socials

🤝 Top Collabolators

Santiago Arias

🤓 Submissions

Paper to Explainer video

👌 Attended Hackathons

Stable Diffusion 2.0 AI Hackathon

📝 Certificates

Stable Diffusion 2.0 AI Hackathon | Certificate