Invoke is a leading creative engine for Stable Diffusion models, empowering professionals, artists, and enthusiasts to generate and create visual media using the latest AI-driven technologies. The solution offers an industry leading WebUI, and serves as the foundation for multiple commercial products.

Outpainting with Stable Diffusion on an infinite canvas

Kandinsky 2 — multilingual text2image latent diffusion model

AI magics meet Infinite draw board.

Seamlessly extend any image in any direction with AI. Open-source web app powered by Gemini via OpenRouter, with Poisson-blended seams and best-of-3 variant picker.

About Invoke is a leading creative engine for Stable Diffusion models, empowering professionals, artists, and enthusiasts to generate and create visual media using the latest AI-driven technologies. The solution offers an industry leading WebUI, and serves as the foundation for multiple commercial products.

Discord bot and Interface for Stable Diffusion

Codebase for performing various experiments with Stable Diffusion, supported by the diffusers library.

Yet Another Stable Diffusion Discord Bot

Turn a sequence of ai generated outpainted images into an "infinite zoom"

A general purpose ComfyUI workflow for common use cases.

[ECCV2022] Official PyTorch implementation of the paper "Outpainting by Queries"

AI Image Generator is a powerful and user-friendly desktop application designed to help creators produce stunning, high-quality artwork, photorealistic renders, and creative concepts quickly and easily.

Stable Diffusion for Photoshop

An end-to-end guide and investigation into Stable Diffusion tooling — SD WebUI, models, LoRAs, and VAEs — for generating synthetic training data for military computer vision models.

This repository wraps the flux fill model as ComfyUI nodes. Compared to the flux fill dev model, these nodes can use the flux fill model to perform inpainting and outpainting work under lower VRM conditions

[CVPRW23] Implementation of ''FishDreamer: Towards Fisheye Semantic Completion via Unified Image Outpainting and Segmentation''

FakePartsBench: 25K+ AI-generated videos with pixel- and frame-level annotations of full and partial deepfakes.

Custom workflow nodes for ComfyUI — Flux pipelines, LoRA stacks, and advanced inpainting utilities.

In-N-Out: Towards Good Initialization for Inpainting and Outpainting (BMVC 2021)