Live briefing
Everything about Stable Diffusion
Image-generating machine learning model
Stable Diffusion is a deep learning, text-to-image model released in 2022 based on diffusion techniques. The generative AI technology is the premier product of Stability AI and is considered to be a part of the ongoing AI boom. Wikipedia →
🧠Start here: a 6-step reading path
- Read the overview: Stable DiffusionA 5-minute orientation
- Skim a recent paper: Establishing Robust Generative Image Steganography via Popular Stable DiffusionInfluential work since 2022
- Pick up a classic book: An Introduction to Probability Theory and Its Applications [2/2]The most-reprinted book on the subject
- Read the landmark paper: Tempered stable LĂ©vy motion and transient super-diffusionCited 257 times
- Go sideways: Latent diffusion modelA closely related topic
- Go sideways: Text-to-image modelA closely related topic
đź“– Definitions
No dictionary entry for this exact phrase.
🗂️ The subject at a glance
🏆 Landmark papers (most cited)
Tempered stable LĂ©vy motion and transient super-diffusion
Fractional diffusion and LĂ©vy stable processes
Self-similar anomalous diffusion and Levy-stable laws
Stable patterns in a viscous diffusion equation
Collision-Stable Waves in Excitable Reaction-Diffusion Systems
Anomalous diffusion and fractional stable distributions
Evolutionarily Stable and Convergent Stable Strategies in Reaction–Diffusion Models for Conditional Dispersal
Stable DNA-based reaction–diffusion patterns
🆕 Influential since 2022
Establishing Robust Generative Image Steganography via Popular Stable Diffusion
StableNormal: Reducing Diffusion Variance for Stable and Sharp Normal
Watermarking for Stable Diffusion Models
Stable-Hair: Real-World Hair Transfer via Diffusion Model
Protecting copyright of stable diffusion models from ambiguity attacks
đź“š Books worth reading
An Introduction to Probability Theory and Its Applications [2/2]William Feller · 1966- 📕Terrestrial photosynthesis in a changing environmentJaume Flexas, Francesco Loreto · 2012
- 📕Sedimentary ModelingEvan K. Franseen · 1991
- 📕Multi-dimensional asymptotically stable 4th order accurate schemes for the diffusion equationSaul S. Abarbanel · 1996
- 📕Multi-dimensional asymptotically stable finite difference schemes for the advection-diffusion equationSaul S. Abarbanel · 1996
Markov processes, Gaussian processes, and local timesMichael B. Marcus · 2006
Physical Techniques in Biological ResearchDan H. Moore · 1968
Aperiodic CrystalsSiegbert Schmid · 2013
Ranked by number of editions on Open Library, a rough measure of how lasting a book is.
đź”— Related topics
- Latent diffusion model The latent diffusion model (LDM) is a diffusion model architecture developed by the CompVis (Computer Vision & Learning) group at LMU Munich. Introduced…
- Text-to-image model A text-to-image (T2I or TTI) model is a machine learning model which takes an input natural language prompt and produces an image matching that description…
- LAION LAION (acronym for Large-scale Artificial Intelligence Open Network) is a German non-profit organization which makes open-sourced artificial intelligence…
- Contrastive language–image pre-training Contrastive language–image pre-training (CLIP) is a technique for training a pair of neural network models, one for image understanding and one for text…
- Kandinsky (artificial intelligence) Kandinsky is a series of generative artificial intelligence models built by Sber. The models turn text prompts into images and short videos. Sber AI leads…
- AI art Artificial intelligence visual art, or AI art, is artistic content generated or assisted by artificial intelligence (AI) programs. The classification of…
- Imagen (text-to-image model) Imagen is a discontinued series of text-to-image models developed by Google DeepMind. They were developed by Google Brain until the company's merger with…
- Flux (text-to-image model) Flux is a family of text-to-image and image-to-image models developed by Black Forest Labs (BFL), based in Freiburg im Breisgau, Germany. Black Forest…