A gentle illustrated introduction by Jay Alammar to how Stable Diffusion works, covering the components of Stable Diffusion, what diffusion is, painting images by removing noise, diffusion on compressed latent data, and the text encoder. It focuses on image generation from text only (text2img) and includes translations into Chinese and Vietnamese.
(Non-)Human is an art installation by Yuguang Zhang that explores the semi-human, semi-object territory. It conjures the hidden human-ness in objects and imagines a speculative world where a human exists in non-human forms. The initial piece is a bedsheet that tweaks and bends in the form of its owner. It uses tools including Arduino, webcam, PoseNet, Node.js, and a custom GAN.
Creates or edits images with generative models and visual controls.
Hypotenuse AI is an AI-first Product Experience Management platform for ecommerce that enriches and governs product information, generates on-brand content, and perfects catalog images. It offers AI auto-enrichment of product attributes, bulk generation of product descriptions, and AI enhancement of catalog images. It also provides AI agents for product content tasks and an AI product attribute mapping tool.
Muse is a text-to-image Transformer model that generates images from text prompts and supports image editing, including inpainting, outpainting and mask-free editing, without fine-tuning or inverting the model. It is trained on a masked modeling task in discrete token space using text embeddings from a pre-trained language model.
A community-driven archive of models and files from CivitAI, formerly named CivitAI Archive. It offers search, verification and tracking of AI models using SHA256 hashing across CivitAI, HuggingFace, TensorArt, SeaArt, PixAI and other platforms and torrents.
pixray-text2image is a public Replicate model that uses pixray to generate an image from a text prompt. It runs on Nvidia T4 GPU hardware, with predictions typically completing within 6 minutes, and is also open source and runnable on one's own computer with Docker.
Community notes
Be the first to share how this project worked for you.
Sign in with a verified account to leave a review or join the discussion.
Sign in to reviewKeep exploring
(Non-)Human is an art installation by Yuguang Zhang that explores the semi-human, semi-object territory. It conjures the hidden human-ness in objects and imagines a speculative world where a human exists in non-human forms. The initial piece is a bedsheet that tweaks and bends in the form of its owner. It uses tools including Arduino, webcam, PoseNet, Node.js, and a custom GAN.
Creates or edits images with generative models and visual controls.
Hypotenuse AI is an AI-first Product Experience Management platform for ecommerce that enriches and governs product information, generates on-brand content, and perfects catalog images. It offers AI auto-enrichment of product attributes, bulk generation of product descriptions, and AI enhancement of catalog images. It also provides AI agents for product content tasks and an AI product attribute mapping tool.
Muse is a text-to-image Transformer model that generates images from text prompts and supports image editing, including inpainting, outpainting and mask-free editing, without fine-tuning or inverting the model. It is trained on a masked modeling task in discrete token space using text embeddings from a pre-trained language model.
A community-driven archive of models and files from CivitAI, formerly named CivitAI Archive. It offers search, verification and tracking of AI models using SHA256 hashing across CivitAI, HuggingFace, TensorArt, SeaArt, PixAI and other platforms and torrents.
pixray-text2image is a public Replicate model that uses pixray to generate an image from a text prompt. It runs on Nvidia T4 GPU hardware, with predictions typically completing within 6 minutes, and is also open source and runnable on one's own computer with Docker.
