ai4artists

(with )

: Paper predating Stable Diffusion describing a method for image synthesis and editing with diffusion based models

: Original paper that introduced Stable Diffusion and started it all

: Edit Stable Diffusion outputs by editing the original prompt

: Similar to prompt-to-prompt but instead takes an input image and a text description. Kinda like Style Transfer... but with Stable diffusion

: Similar to Textual Inversion but instead focused on manipulating subject based images (i.e. but )

: Like DreamBooth but capable of synthesizing multiple concepts

: prior work on sparse modeling (still needed/useful for NeRF)

: prior work on dense modeling (NeRF kinda replaces this)

: NeRF in the wild (alternative to MVS)

: Photorealistic NeRF from casual in-the-wild photos and videos (like from a cellphone)

: NeRF... but BETTER FASTER HARDER STRONGER

: Train NeRF models faster with fewer images by leveraging depth information

: caching for NeRF training to make it rlllly FAST

: text-to-3D using CLIP

: NeRF for robots (and cars)

: pretrained NeRF

NVIDIA Imaginaire

: 2D Image synthesis library

: The platform for creating and operating metaverse applications

: Content-Based Search for Deep Generative Models

: More efficient than diffusion or autoregressive text-to-image models used masked image modeling w/ transformers

: Official cloud hosted service

features

⭐️ : A user friendly UI for SD with additional to make common workflows easy

: Render scenes in Blender using a text prompt

Dream Textures (Blender)

: Plugin to render textures, reference images, and background with SD

SD Prompt Search

koi (Krita)

: SD plugin for for img2img generation

: Photoshop plugin (beta)

: Another Photoshop plugin

Stable Diffusion Studio

: Animation focused frontend for SD

DeepSpeed-MII

: Low-latency and high-throughput inference for a variety (20,000+) models/tasks, including SD

LAION Datasets

: Various very large scale image-text pairs datasets (notably used to train the open source models)

: Open Images is a dataset of ~9M images annotated with image-level labels, object bounding boxes, object segmentation masks, visual relationships, and localized narratives:

: 17,127 validated hours of transcribed speech covering 104 languages. Additionally many of the recorded hours in the dataset also include demographic metadata like age, sex, and accent that can help improve the accuracy of speech recognition engines

: Flickr Commons is a unique collection of historical photography from over 100 cultural institutions from all around the world, all with no known copyright restrictions

: Internet Archive is a non-profit library of millions of free books, movies, software, music, websites, and more

: a collection of 106,323,506 freely usable media files to which anyone can contribute

: Making images from Getty’s collections freely available for study, teaching, and enjoyment

: Focused on works now fallen into the public domain, the vast commons of out-of-copyright material that everyone is free to enjoy, share, and build upon without restrictions

: An ImageNet replacement for self-supervised pretraining without humans which can be used for high-quality pretraining while significantly reducing privacy concerns

: full body 1024 x 512px

AI powered video editor

AI powered image editor

AI powered features for the Creative Cloud suite

and

Sony CSL ( and )

Big list of Google Colab notebooks for generative text-to-image techniques as well as general tools and resources

Awesome Generative Deep Art

A curated list of Generative Deep Art / Generative AI projects, tools, artworks, and models