Stable Diffusion

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.

About Stable Diffusion

Latent diffusion models (LDMs) are a type of image generation technique that work by iteratively "de-noising" data in a latent representation space, and then decoding the representation into a full image. This is in contrast to other popular image synthesis methods such as generative adversarial networks (GANs) and the auto-regressive technique used by DALL-E. The Stable Diffusion model is created by a collaboration between engineers and researchers from CompVis, Stability AI, and LAION and released under a Creative ML OpenRAIL-M license, wich means that it can be used for commercial and non-commercial purposes. The release of this file is the culmination of many hours of collective effort to compress the visual information of humanity into a few gigabytes. Furthermore, the model also supports image-to-image style transfer, as well as upscaling and generating an images from a simple sketch. Included is also an AI-based Safty Classifier, which understands concepts and other factors in generations to remove outputs that may not be desired by the model user.

Stable Diffusion Knowledge Base

Find out how it is working!

Stable Diffusion Paper

The Stable Diffusion paper describes the model and its training process in detail.

Paper Stable Diffusion Demo

You can play around with Stable Diffusion on Hugging Face

Hugging Face GitHub Repository

Visit the Stable Diffusion repository on GitHub

Stable Diffusion Boilerplates

Get started with technology!

Stable Diffusion Colab

A Colab notebook that shows how to use Stable Diffusion with GPU!

Python Stable Diffusion & Whisper Colab

A Colab notebook that shows how to use Stable Diffusion with Whisper!

Python Stable Diffusion Interpolation V2.2

A Colab notebook about Stable Diffusion Interpolation!

Stable Diffusion Tutorials

Explore the coding tutorials and how-to guides available on our website to help you get started and learn to build with Stable Diffusion artificial intelligence technology

Stable Diffusion Inpainting tutorial: Prompt Inpainting with Stable Diffusion

Stable Diffusion Inpainting tutorial: Prompt Inpainting with Stable Diffusion

Tutorial about how to use the Stable Diffusion model to inpaint images with a specific prompt and the help of Clipseg to create ai generated images

Stable Diffusion tutorial: How to make videos with Stable Diffusion? - Interpolation

Stable Diffusion tutorial: How to make videos with Stable Diffusion? - Interpolation

If you want to find out how to make video using interpolation process with Stable Diffusion - check this tutorial!

Stable Diffusion and OpenAI Whisper prompt guide: Generating pictures based on speech - Whisper & Stable Diffusion

Stable Diffusion and OpenAI Whisper prompt guide: Generating pictures based on speech - Whisper & Stable Diffusion

In this tutorial you will learn how to generate pictures based on speech using recently published OpenAI's Whisper and hot Stable Diffusion models!

How to create Stable diffusion API on a GCP VM instance

How to create Stable diffusion API on a GCP VM instance

In this tutorial I will show you how to create a stable diffusion API on a GCP VM instance in few minutes

Stable Diffusion prompt guide: Text-guided image-to-image generation with Stable Diffusion

Stable Diffusion prompt guide: Text-guided image-to-image generation with Stable Diffusion

Simple guide how to create proper prompts for stable diffusion.

Stable Diffusion tutorial: Creating an animated avatar of yourself with Stable Diffusion

In this tutorial I am going to show you how to create a Pixar animated style avatar of yourself using Stable Diffusion AI

The Stable Diffusion tutorial: Prototyping with the Stable Diffusion Web UI

The Stable Diffusion tutorial: Prototyping with the Stable Diffusion Web UI

Learn how to install the Stable Diffusion Web UI to validate your ideas

The Stable Diffusion tutorial: How to use Lexica, the Stable Diffusion AI art image search engine

The Stable Diffusion tutorial: How to use Lexica, the Stable Diffusion AI art image search engine

Lexica is a new image search engine that has millions of AI generated images by stable diffusion AI. This Stable Diffusion prompt guide tutorial shows how to use it and how you can use their API for your next project.

Stable Diffusion tutorial: Stable Diffusion Image Variations using lambda diffusers

Stable Diffusion tutorial: Stable Diffusion Image Variations using lambda diffusers

Generate variations on an input image using a fine-tuned version of Stable Diffusion

Stable Diffusion Guide: How to use our Stable Diffusion API

Stable Diffusion Guide: How to use our Stable Diffusion API

In this tutorial, we will show you how to use our Stable Diffusion API to generate images in seconds.

Stable Diffusion Hackathon projects

Solutions built with Stable Diffusion that have been created during our hackathons by the members of our community

NeoLocus

NeoLocus

A solution to help businesses place their products in custom environments using generative AI. For an e-commerce business, having an attractive listing of their inventory is crucial. Significant time and money is spent on: Photoshoots Mockups 3D renders For an e-commerce customer, the user journey for buying a furniture product faces challenges such as: Long research to find the perfect product. Imagining the product in their space. Product’s aesthetic fit with the rest of the space. So we have made a generative AI powered tool that helps Companies place their products in custom environments (with no prior knowledge on generative AI). This is done by custom trained diffusion models.

Sherlocks Phoenix

Sherlocks Phoenix

Our Sherlock's Phoeniks Search Squad solution is a facial recognition system that utilizes generative AI models like ChatGPT and stable diffusion, as well as computer vision techniques, to identify and locate missing persons in real time . The system will take input in the form of text describing the appearance of the missing person, as well as raw images such as sketches, CCTV footage, or blurry photos. The algorithm will then search through internal databases and internet/social media platforms like Facebook and Twitter to find matches and potentially identify the missing person. This system has the potential to significantly aid Police and Investigating agencies in their efforts to locate and bring missing persons home

Miraa

Miraa

Our app provides a fully digitalized package for our clients. We offer a range of services, including the creation of a logo, ads that can be used on social media platforms such as Facebook and Instagram, a website, and marketing videos. In order to enhance the quality of our videos, we use a technology called DeepFake. This technology generates faces which are then placed onto the video to create a more engaging advertisement. To create the ads, we use two different technologies called dalle and gpt3. Dalle is used to generate images, while gpt3 is used for text. The logo is also created using dalle for the image and gpt3 for the text under the image. For the website, we will use dalle for images and gpt3 to code the website itself. Additionally, we will be adding automation to our app to streamline the entire process. Impact:: Our app offers a comprehensive range of services that can potentially have a significant impact on the market. The fields in which our app can be used includes branding, digital marketing, web development, and video production.One potential way to use client data and requests of images for further work is to analyze the data to identify trends and patterns in the type of images that clients are requesting. This can help us to tailor our services to meet the specific needs and preferences of your clients. For example, if we notice that clients are frequently requesting certain types of images or logos, we could focus on developing more options in that style., our app has the potential to make a significant impact on the market and attract a wide range of clients.

The Future of AI podcast

The Future of AI podcast

An artificial intelligence podcast that is written by ChatGPT, GPT-3.5, Open-AI davinci, and human assistance. The art is generated by Stable Diffusion, Open Journey, and Dall-E 2. It is read by Natural Readers text-to-speech and Lifelike Speech Synthesis Google Cloud. The platform used is Anchor.fm and the availability of the podcast are in Google Podcasts, Apple Podcasts, Amazon Music, Spotify, Castbox, Pocket Casts, RadioPublic, and Stitcher. The podcast description is: "Join us as we explore the rapidly advancing world of artificial intelligence, and what it means for our future. In each episode, we'll discuss the latest AI research and developments, and how they are poised to impact various industries and aspects of our daily lives. From self-driving cars to intelligent virtual assistants, we'll delve into the potential and the challenges of this rapidly evolving technology. Tune in to stay up-to-date on the future of AI and its impact on society." Created and written by Artificial Intelligences and Cyber World. Currently the podcast has 12 episode in season 1 which has one episode for introduction and special and it has 5 episode currently for season 2. AI has come a long way since its inception and has been widely used in various fields such as healthcare, finance, and transportation. AI-powered machines and systems have the ability to learn and adapt to new situations without the need for human intervention. This ability of AI has made it an integral part of various industries and has brought about significant changes in the way we work and live. The current state of the AI industry is quite promising. The AI market is expected to grow from $9.5 billion in 2018 to $118.6 billion by 2025. The adoption of AI is increasing at a rapid pace and is being used in a variety of applications such as image recognition, speech recognition, and natural language processing. The use of AI in healthcare has also shown promising results, with AI-powered systems.

Cowork AI

Cowork AI

We believe that AI can help SMBs be more successful by saving time, generating, and reducing hiring cost. SMBs find social media challenging, time-consuming, and the alternatives to doing it by themselves are hiring a social media manager or ads agency which are costly. This is exacerbated by complex tech they need to navigate in doing this, such as understanding social media algorithms and data analyses on what performs better. We interviewed a pottery artist who said "Making Instagram Reels sucked the joy out of creating." We envision an AI social media manager that is affordable, effective and smart, while also always reliable, loyal and active. The AI social media manager will create more engaging and sales-generating contents in seconds instead of hours. All this can be done using text / natural language interface and data optimization in the background so SMBs do not have to navigate complex technical details. We also plan to improve the AI to the point that it can run SMBs social media independently, just like if you were to hire a coworker. This will enable SMBs to enjoy what they are doing more, be more efficient when doing business, and save business owners from stressful mistakes or failures.

TEXT TO HUMAN AI

TEXT TO HUMAN AI

We are building a Text-to-Video Human avatar generator. It is a pipeline of AI tools that works in 3 Steps: 1. Text-to-Speech (Creating a audio file from text input) 2. Text-to-Video (Creating a video from text input) 3. Text-to-Human (Using deep fake technology to make video less random and merge audio with lips of subject). This is just the beginning of AI media and the next natural steps for AI, it is better then most use cases because you have much more control of the subject who can actually interact with their environment, be trained easier and have movement which opens so many more doors in use cases then other technology out there in the same bracket. We have text-to-text, We have Text-to-video and we have text-to-video, Welcome to Text-To-Human.

Chrolove

Chrolove

Pictures generated by the Stable Diffusion are used for mental health therapeutic purposes. There are two main services, the free in-app plan and the premium chromotherapy in the metaverse. First of all, the main goal of the application is to be able to ask the users about their current mood and the reasons behind it to generate an image based on the theories of mental health and chroma therapy to improve overall mental health. The application first starts by asking about the overall mood of the user: Great, Good, Okay, Bad, Awful . Based on these questions the model generates an image that is soothing to the mood and improves the mood of the user throughout the day. Then, the metaverse is used to provide immersive chromotherapy in the metaverse for all. It consists of the panorama version or full-screen version of the picture being trained and generated using Stable Diffusion. Then, throughout the chromotherapy, we could let use relaxation-stimulating colors to provide immersive therapeutic experiences, whether it is the VR feature on ma mobile phone, the VR feature from a VR headset, the AR feature from an Apple device, and more that are compatible with Spatial XR.

Immersive Books

Immersive Books

Our application allows book readers to have a more immersive experience and grants artists, authors, and publishers the ability to craft their own story by fine-tuning their models.

Stable Diffusion Creator Tool

Stable Diffusion Creator Tool

This tool lets you create videos based off stable key frames and interpolate the results using custom apis.

Talk In threeD

Talk In threeD

This generative solution provides near real time (less than 20 secs) text to 3d model generation compared to current state of the art model Dreamfusion which takes 1 hr inference time for decent results. This will disruptive the way artists will do 3d modelling in future.

Show me a Story

Show me a Story

This app generates a story text, from GPT-2, and creates a visual image of the story. As the story keeps being generated, that is more sentences are written, the app creates images to visually represent the story.

Fast Ads

Fast Ads

Creating an online advertisement is not simple for small businesses since they usually do not have full-time employees with graphic design skills. Fast-Ads is an AI tool that will automate this online Ad creation process.

Same Same But Different

Same Same But Different

Designers typically face blockers in their initial stages of getting inspiration for their works. Without the risk of running into copyright or plagiarism laws, SSBD aims to provide a safe space to get similar-styled images with full originality.

forensic ai

forensic ai

Forensic.ai is AI Portrait Generator. It helps police officers easily generate portrait images of suspects based on victims' reports. Our system provides a form with fields to describe the physical characteristics of a suspect such as age, race, gender, weight, and height. These parameters will be concatenated into a prompt engineering algorithm that is fed into stable diffusion to generate a portrait image.

AI and early child development

AI and early child development

Visual storytelling is one of the many ways educators use to assist in the child's growth. However, often times educators will have to improvise when trying to find relevant material (movies or story books) that can help in guiding the child in a specific situation with the child's needs and accessibility accommodations. For example, a child with physical differences can be facing a situation from a different child and an educator is keen on addressing the situation. Therefore, developing a solution that can create custom images for storytelling based on the unique characteristics of the child can be very empowering to the educational system.

Novel view generation

Novel view generation

Synthesizing a novel view from different angles is an interest in many fields like VR, video enhancement, games, etc. However, this process has some limitations when given an image of an object from an unrecognizable angle. The proposed method combines image-to-image translation with stable diffusion by giving text as an additional parameter

Dimensational

Dimensational

Dimensational is a text-to-image topographic texture generator, in which by simply typing in the type of environment you wish to generate, you can almost immediately create a myriad of beautiful artistic patterns that replicate the beauty of our planet and many others.

Dreamixer

Dreamixer

Dreamixer is a Stable Diffusion based AI tool to generate comic strips from text. Dreamixer aims to democratize the comic strip creation process so everyone with an idea and aim to express it using comic strips is not blocked by his lack of graphics and designing skills. If you can express your idea as a comic strip script giving scene setting and dialogue, Dreamixer will do the rest. It will generate the comic strip with given scene setting and characters in a consistent style. It was also append the dialogues spoken by characters as a text bubble. Later on, we plan to give ability to our users to edit specific portions of the comic strip using in-painting and other advance Stable Diffusion features.

A machine making a human

A machine making a human

Name/Alias of the artist: Michael Name of the prompt used/title of the artwork: A machine making a human, 4k digital art Name of tool used: API: newnative.ai To make prompts more in line with what the user likes, I took inspiration from a simulated annealing algorithm. The user begins by giving a prompt of what they'd like to see. From there, a list of synonyms is produced, along with 100 common words and acronyms. The prompt it tweaked slightly and different words are added, removed or moved within the prompt based on user feedback within each stage. This results in an evolving image prompt more toward the user's preference.

Stable CAD Generator

Stable CAD Generator

Our project is an Innovative CAD generator using the Stable Diffusion module. It classifies the given image using tensorflow's MobileNetV2,after the image is successfully identified it passes it on to the Stable Diffusion API which generates a CAD/Blueprint based on the MobileNetV2's classification. This can solve the design problem of many people who work in engineering and architecture or anything relating to design, even though our main focus is on CADs. This can also be used as an educational tool in universities.We also plan on developing it further , for now this is only a prototype, its full potential is yet to come. For more information please check the presentation and the demonstration video, also don't forget to look at the github repo.

Join one of our AI hackathons to build modern artificial intelligence together with talented members of our lablab community

Build your AI Startup Hackathon. Episode 2

to be announced

Build your AI Startup Hackathon. Episode 2

🛠️ 7 days of Learning and Building 🤝 Come with your team or find one during the Hackathon 🦾 Free access to Generative AI models and Tech Tutorials 🏅 Win a place in the Early Stage StartUp Accelerator program 🚀 Join community of AI experts

ChatGPT API & Whisper API Global Hackathon

to be announced

ChatGPT API & Whisper API Global Hackathon

🗓️ 48 hours of building (24-26th March) 💻 Create innovative new apps with OpenAI's latest ChatGPT and Whisper APIs 💡 Learn from top AI professionals ⚒️ Combine new GPT 3,5 Turbo and Whisper APIs to build your AI app 🐱‍💻 Now is the time to register and let's get started!