Search results
Feb 22, 2024 · Stable Diffusion 3 is a new AI model that generates images from text prompts, with improved performance and quality. Learn how to join the early preview waitlist and explore the technical details and safety features of this model.
- Stability AI Image Models — Stability AI
Experience unparalleled image generation capabilities with...
- Stability AI
Stable Diffusion 3 Medium is the latest and most advanced...
- Stability AI Image Models — Stability AI
Stable Diffusion Online is a free Artificial Intelligence image generator that efficiently creates high-quality images from simple text prompts. It's designed for designers, artists, and creatives who need quick and easy image creation.
Stability AI offers open models for text-to-image, image, video, audio, and 3D generation using generative AI technology. Learn about their latest models, such as Stable Diffusion 3, SDXL Turbo, and Stable Audio 2.0.
Stable Diffusion is a text-to-image model that generates photo-realistic images given any text input. What makes Stable Diffusion unique ? It is completely open source. The model and the code that uses the model to generate the image (also known as inference code). Highly accessible: It runs on a consumer grade laptop/computer.
- Overview
- News
- Requirements
- General Disclaimer
- Stable Diffusion v2
- Shout-Outs
- License
This repository contains Stable Diffusion models trained from scratch and will be continuously updated with new checkpoints. The following list provides an overview of all currently available models. More coming soon.
March 24, 2023
Stable UnCLIP 2.1
•New stable diffusion finetune (Stable unCLIP 2.1, Hugging Face) at 768x768 resolution, based on SD2.1-768. This model allows for image variations and mixing operations as described in Hierarchical Text-Conditional Image Generation with CLIP Latents, and, thanks to its modularity, can be combined with other models such as KARLO. Comes in two variants: Stable unCLIP-L and Stable unCLIP-H, which are conditioned on CLIP ViT-L and ViT-H image embeddings, respectively. Instructions are available here.
•A public demo of SD-unCLIP is already available at clipdrop.co/stable-diffusion-reimagine
December 7, 2022
Version 2.1
You can update an existing latent diffusion environment by running
xformers efficient attention
For more efficiency and speed on GPUs, we highly recommended installing the xformers library.
Tested on A100 with CUDA 11.4. Installation needs a somewhat recent version of nvcc and gcc/g++, obtain those, e.g., via
Then, run the following (compiling takes up to 30 min).
Upon successful installation, the code will automatically default to memory efficient attention for the self- and cross-attention layers in the U-Net and autoencoder.
Stable Diffusion models are general text-to-image diffusion models and therefore mirror biases and (mis-)conceptions that are present in their training data. Although efforts were made to reduce the inclusion of explicit pornographic material, we do not recommend using the provided weights for services or products without additional safety mechanis...
Stable Diffusion v2 refers to a specific configuration of the model architecture that uses a downsampling-factor 8 autoencoder with an 865M UNet and OpenCLIP ViT-H/14 text encoder for the diffusion model. The SD 2-v model produces 768x768 px outputs.
Evaluations with different classifier-free guidance scales (1.5, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0) and 50 DDIM sampling steps show the relative improvements of the checkpoints:
•Thanks to Hugging Face and in particular Apolinário for support with our model releases!
•Stable Diffusion would not be possible without LAION and their efforts to create open, large-scale datasets.
•The DeepFloyd team at Stability AI, for creating the subset of LAION-5B dataset used to train the model.
•Stable Diffusion 2.0 uses OpenCLIP, trained by Romain Beaumont.
•Our codebase for the diffusion models builds heavily on OpenAI's ADM codebase and https://github.com/lucidrains/denoising-diffusion-pytorch. Thanks for open-sourcing!
•CompVis initial stable diffusion release
The code in this repository is released under the MIT License.
The weights are available via the StabilityAI organization at Hugging Face, and released under the CreativeML Open RAIL++-M License License.
Stability AI offers a range of text-to-image models and APIs for image generation, captioning, classification, and search. Learn about Stable Diffusion 3, SDXL Turbo, and Japanese models.
Stable Diffusion is a deep learning, text-to-image model released in 2022 based on diffusion techniques. The generative artificial intelligence technology is the premier product of Stability AI and is considered to be a part of the ongoing artificial intelligence boom .
