A collection of LLM (large language models) resources that can be used to build products or perform reproducible research. The table of contents includes local LLMs, LLM-based tools, training and quantization resources, non-English models, and autonomous agents.

Latest news about AI

Awesome resources for in-context learning and prompt engineering: Mastery of the LLMs such as ChatGPT, GPT-3, and FlanT5, with up-to-date and cutting-edge updates.

Extensive wiki about Stable diffusion.

This page displays a list of 1,833 artists and their associated image tags, ordered by frequency of representation in the Stable Diffusion 1.4 Model. The tags are scraped from Wikidata and are a combination of "genres" and "movements". Each artist is represented by a set of four images and the prompts used to generate these images are also listed. The images were created with a CFG of 7.5, 50 steps, and the same seed, and may be NSFW. The page allows for filtering by artists or tags, and each artist's entry includes their associated tags, including art movements and genres, as well as their name and a set of prompt images.

Some examples listed in the prompt images include Thomas Kinkade, Vincent Van Gogh, Leonid Afremov, Claude Monet, Edward Hopper, Norman Rockwell, William-Adolphe Bouguereau, Albert Bierstadt, John Singer Sargent, Pierre-Auguste Renoir, Frida Kahlo, John William Waterhouse, Walt Disney, and Thomas Moran.

A list of custom ESRGAN models.

Enhanced SRGAN (ESRGAN) is an improvement of the Super-Resolution Generative Adversarial Network (SR-GAN) that is capable of generating realistic textures during single image super-resolution. ESRGAN improves three key components of SRGAN, including network architecture, adversarial loss, and perceptual loss, to enhance the visual quality of images. ESRGAN introduces the Residual-in-Residual Dense Block (RRDB) without batch normalization as the basic network building unit, borrows the idea from relativistic GAN to let the discriminator predict relative realness, and improves the perceptual loss by using the features before activation for stronger supervision. ESRGAN achieves better visual quality with more realistic and natural textures than SRGAN, winning the first place in the PIRM2018-SR Challenge.

A collection on Are.na related to Critical AI Studies

The text introduces Civitai, a platform that allows users to share and discover resources for creating AI art. Civitai provides users with custom models that they can train using their own data or download models created by other users. Models are machine learning algorithms that have been trained to generate art or media in a particular style. Users can use these models with AI art software to create unique works of art. Civitai's community is constantly sharing new and interesting models, making it a vibrant and supportive community of AI artists.

Prompt engineering is a relatively new discipline for developing and optimizing prompts to efficiently use language models (LMs) for a wide variety of applications and research topics. Prompt engineering skills help to better understand the capabilities and limitations of large language models (LLMs). Researchers use prompt engineering to improve the capacity of LLMs on a wide range of common and complex tasks such as question answering and arithmetic reasoning. Developers use prompt engineering to design robust and effective prompting techniques that interface with LLMs and other tools.

Motivated by the high interest in developing with LLMs, we have created this new prompt engineering guide that contains all the latest papers, learning guides, lectures, references, and tools related to prompt engineering.

A mega collection of all resources and news related to Stable Diffusion. Focused around AUTOMATIC1111's webui

The Generative AI Landscape is a collection of various awesome generative AI applications that are categorized into different sections such as animation and 3D modeling, architecture and interior design, art and image generator, avatars, chatbot, code and database assistant, content generation and SEO, creators toolkit, customer support, education and learning, email assistant, fashion, fun, gaming, gift ideas, healthcare, human resources and resume, legal, logo generator, music and audio generation, organization and automation, photo and image editing, plugins and extensions, research assistant, reviews and recommendations, sales and marketing, search engines, slides and web design, social networks and dating, speech, text, text to speech, translation and transcript, vacation and trip planner, video, writing assistant, and other. These applications use generative AI to create and assist in various tasks such as creating art and music, generating text and speech, designing logos and websites, and even planning trips.

DiffusionDB is a large-scale text-to-image prompt dataset containing 14 million images generated by Stable Diffusion using prompts and hyperparameters specified by real users. The dataset primarily consists of English text but also includes other languages such as Spanish, Chinese, and Russian. DiffusionDB provides two subsets, DiffusionDB 2M and DiffusionDB Large, split into 2,000 folders and 14,000 folders, respectively. The dataset includes metadata tables metadata.parquet and metadata-large.parquet, which can be used to access prompts and other attributes of images without downloading all the Zip files. The tables are stored in the Parquet format, making it efficient to query individual columns without reading the entire table.

An hypertextbook (guide) on setting up and using Stable Diffusion, a deep learning model. The hypertextbook is organized into chapters, starting with the basics of getting started and updating, followed by troubleshooting, using the Webui for text-to-image and image-to-image generation, prompting, and training. The later chapters cover developments, modifications, common questions, and resources related to Stable Diffusion. The hypertextbook is structured to guide newcomers from surface-level content to deep-level content.

This resource provides tools and tutorials at the intersection of AI and art, including courses, videos, books, tutorials, blogs, papers, methods, tools, datasets, products/apps, artists, and institutions/places. The resource covers various topics, including diffusion models, neural radiance fields, 3D and point clouds, image synthesis, GAN inversion, latent space interpretation, image matting, creative ML, deep learning, runtimes/deployment, text-to-image, creative coding, and Stable Diffusion. Additionally, it features inspiring people and places in the art and AI industry.

Another HuggingFace DreamBooth library browser :

The HuggingFace DreamBooth library browser currently contains 204 DreamBooth models. To use these models with AUTOMATIC1111's SD WebUI, users must convert them by downloading the model archive and using a script to create a .cktp file.

Dreambooth on Stable Diffusion is an implementation of Google's Dreambooth with Stable Diffusion. It enables people to fine-tune a text-to-image model with a few examples by using the idea of Dreambooth on Stable diffusion. This code repository is based on that of Textual Inversion, but it fine-tunes the whole diffusion model instead of just optimizing word embedding. The implementation makes minimum changes over the official codebase of Textual Inversion, and some components in Textual Inversion are not deleted, although they will never be used here.

A collection of wildcards to use with Stable Diffusion

Stable Diffusion is an open-source diffusion model used for generating images from textual descriptions. The input parameters for generating images include prompt, negative prompt, sampling steps, sampling method, ddim_eta, batch count/n_iter, batch size, CFG Scale, width, height, and seed. Increasing batch size and width requires more VRAM, while increasing CFG Scale results in images that resemble the prompt more closely but degrades image quality after a certain point. The seed is the starting point for the RNG, and varying input parameters only slightly can still produce good results using previously successful seeds.