Go to file
Alexander Eichhorn 3b2d2ef10a
fix(gguf): ensure dequantized tensors are on correct device for MPS (#8713)
When using GGUF-quantized models on MPS (Apple Silicon), the
dequantized tensors could end up on a different device than the
other operands in math operations, causing "Expected all tensors
to be on the same device" errors.

This fix ensures that after dequantization, tensors are moved to
the same device as the other tensors in the operation.

Co-authored-by: Lincoln Stein <lincoln.stein@gmail.com>
2026-01-02 00:45:50 +00:00
.dev_scripts Apply black 2023-07-27 10:54:01 -04:00
.github fix(docs) Bump versions in mkdocs github actions (#8722) 2026-01-01 19:31:33 -05:00
coverage combine pytest.ini with pyproject.toml 2023-03-05 17:00:08 +00:00
docker bugfix(docker) Ensure the correct extra install. 2025-07-17 04:19:22 +00:00
docs (chore) Prep for v6.10.0rc2 (#8701) 2025-12-26 18:26:04 -05:00
invokeai fix(gguf): ensure dequantized tensors are on correct device for MPS (#8713) 2026-01-02 00:45:50 +00:00
scripts refactor: model manager v3 (#8607) 2025-10-15 10:18:53 +11:00
tests feat(backend): add support for xlabs Flux LoRA format (#8686) 2025-12-24 20:18:11 +00:00
.dockerignore refactor Dockerfile; get rid of multi-stage build; upgrade to python 3.12 2025-04-04 18:42:13 +11:00
.editorconfig Merge dev into main for 2.2.0 (#1642) 2022-11-30 16:12:23 -05:00
.git-blame-ignore-revs Git blame ignore revs 2025-03-26 12:56:04 +11:00
.gitattributes refactor: model manager v3 (#8607) 2025-10-15 10:18:53 +11:00
.gitignore repo: update ignores 2025-07-18 08:08:15 -04:00
.gitmodules remove src directory, which is gumming up conda installs; addresses issue #77 2022-08-25 10:43:05 -04:00
.nvmrc update nodes schema / typegen 2025-04-04 18:42:13 +11:00
.pre-commit-config.yaml chore: update pre-commit syntax; add check for uv.lock needing an update 2025-04-15 07:41:32 +10:00
.prettierrc.yaml feat: automated releases via github action 2024-02-29 21:57:20 -05:00
flake.lock update flake (#7032) 2024-10-08 10:55:49 +11:00
flake.nix update flake (#7032) 2024-10-08 10:55:49 +11:00
InvokeAI_Statement_of_Values.md Add @ebr to Contributors (#2095) 2022-12-21 14:33:08 -05:00
LICENSE Update LICENSE 2023-07-05 23:46:27 -04:00
LICENSE-SD1+SD2.txt updated LICENSE files and added information about watermarking 2023-07-26 17:27:33 -04:00
LICENSE-SDXL.txt updated LICENSE files and added information about watermarking 2023-07-26 17:27:33 -04:00
Makefile build: remove installer & convert installer build script to only build the wheel 2025-04-04 18:42:13 +11:00
mkdocs.yml docs: add docs for low vram mode 2025-01-09 11:20:05 +11:00
pins.json chore: bump torch to 2.7.0 2025-05-19 12:29:51 +10:00
pyproject.toml (chore) Prep for v6.10.0rc2 (#8701) 2025-12-26 18:26:04 -05:00
README.md tidy: removing unused code paths 7 2025-10-15 10:46:16 +11:00
SECURITY.md Create SECURITY.md 2024-11-25 04:10:03 -08:00
Stable_Diffusion_v1_Model_Card.md Global replace [ \t]+$, add "GB" (#1751) 2022-12-19 16:36:39 +00:00
uv.lock chore: upgrade diffusers to 0.36.0 to support z image 2025-12-21 21:54:47 +05:30

project hero

Invoke - Professional Creative AI Tools for Visual Media

discord badge latest release badge github stars badge github forks badge CI checks on main badge latest commit to main badge github open issues badge github open prs badge translation status badge

Invoke is a leading creative engine built to empower professionals and enthusiasts alike. Generate and create stunning visual media using the latest AI-driven technologies. Invoke offers an industry leading web-based UI, and serves as the foundation for multiple commercial products.

  • Free to use under a commercially-friendly license
  • Download and install on compatible hardware
  • Generate, refine, iterate on images, and build workflows

Highlighted Features - Canvas and Workflows

Documentation

Quick Links
Installation and Updates - Documentation and Tutorials - Bug Reports - Contributing

Installation

To get started with Invoke, Download the Launcher.

Troubleshooting, FAQ and Support

Please review our FAQ for solutions to common installation problems and other issues.

For more help, please join our Discord.

Features

Full details on features can be found in our documentation.

Web Server & UI

Invoke runs a locally hosted web server & React UI with an industry-leading user experience.

Unified Canvas

The Unified Canvas is a fully integrated canvas implementation with support for all core generation capabilities, in/out-painting, brush tools, and more. This creative tool unlocks the capability for artists to create with AI as a creative collaborator, and can be used to augment AI-generated imagery, sketches, photography, renders, and more.

Workflows & Nodes

Invoke offers a fully featured workflow management solution, enabling users to combine the power of node-based workflows with the easy of a UI. This allows for customizable generation pipelines to be developed and shared by users looking to create specific workflows to support their production use-cases.

Invoke features an organized gallery system for easily storing, accessing, and remixing your content in the Invoke workspace. Images can be dragged/dropped onto any Image-base UI element in the application, and rich metadata within the Image allows for easy recall of key prompts or settings used in your workflow.

Other features

  • Support for both ckpt and diffusers models
  • SD1.5, SD2.0, SDXL, and FLUX support
  • Upscaling Tools
  • Embedding Manager & Support
  • Model Manager & Support
  • Workflow creation & management
  • Node-Based Architecture

Contributing

Anyone who wishes to contribute to this project - whether documentation, features, bug fixes, code cleanup, testing, or code reviews - is very much encouraged to do so.

Get started with contributing by reading our contribution documentation, joining the #dev-chat or the GitHub discussion board.

We hope you enjoy using Invoke as much as we enjoy creating it, and we hope you will elect to become part of our community.

Thanks

Invoke is a combined effort of passionate and talented people from across the world. We thank them for their time, hard work and effort.

Original portions of the software are Copyright © 2024 by respective contributors.