Releases: invoke-ai/InvokeAI
InvokeAI Version 2.0.1 - A Stable Diffusion Toolkit
The invoke-ai team is excited to be able to share the release of InvokeAI 2.0 - A Stable Diffusion Toolkit, a project that aims to provide enthusiasts and professionals both a suite of robust image creation tools. Optimized for efficiency, InvokeAI needs only ~3.5GB of VRAM to generate a 512x768 image (and less for smaller images), and is compatible with Windows/Linux/Mac (M1 & M2).
InvokeAI was one of the earliest forks of the core CompVis repo (formerly lstein/stable-diffusion), and recently evolved into a full-fledged community driven and open source stable diffusion toolkit named InvokeAI. Version 2.0.0 of the tool introduces an entirely new WebUI Front-end with a Desktop mode, and an optimized back-end server that can be interacted with via CLI or extended with your own fork.
Release 2.0.1 corrects an error that was causing the k* samplers to produce noisy images at high step counts. Otherwise the feature set is the same as 2.0.0.
This version of the app improves in-app workflows leveraging GFPGAN and Codeformer for face restoration, and RealESRGAN upscaling - Additionally, the CLI also supports a large variety of features:
- Inpainting
- Outpainting
- Negative Prompts (prompt unconditioning)
- Fast online model switching
- Textual Inversion
- Improved Quality for Hi-Resolution Images (Embiggen, Hi-res Fixes, etc.)
- And more...
Future updates planned included UI driven outpainting/inpainting, robust Cross Attention support, and an advanced node workflow for automating and sharing your workflows with the community.
What's Changed
- hotfix(venv): rename 'ldm' -> 'invokeai' by @tildebyte in #1014
- Fix two broken links in README by @Miserlou in #1026
- fixed old reference to ldm on activate env by @nunocoracao in #1029
- Fix the link to the weights download page by @Hkmu in #1041
- reintroduce fix for m1 from #579 missing after merge by @skurovec in #1055
- More mkdocs updates by @mauwii in #1057
- Add back old
dream.pyaslegacy_api.pyby @CapableWeb in #1070
New Contributors
- @Miserlou made their first contribution in #1026
- @nunocoracao made their first contribution in #1029
- @Hkmu made their first contribution in #1041
Full Changelog: v2.0.0...v2.0.1
Contributors
Assets 2
InvokeAI Version 2.0.0 - A Stable Diffusion Toolkit
The invoke-ai team is excited to be able to share the release of InvokeAI 2.0 - A Stable Diffusion Toolkit, a project that aims to provide enthusiasts and professionals both a suite of robust image creation tools. Optimized for efficiency, InvokeAI needs only ~3.5GB of VRAM to generate a 512x768 image (and less for smaller images), and is compatible with Windows/Linux/Mac (M1 & M2).
InvokeAI was one of the earliest forks of the core CompVis repo (formerly lstein/stable-diffusion), and recently evolved into a full-fledged community driven and open source stable diffusion toolkit named InvokeAI. Version 2.0.0 of the tool introduces an entirely new WebUI Front-end with a Desktop mode, and an optimized back-end server that can be interacted with via CLI or extended with your own fork.
This version of the app improves in-app workflows leveraging GFPGAN and Codeformer for face restoration, and RealESRGAN upscaling - Additionally, the CLI also supports a large variety of features:
- Inpainting
- Outpainting
- Negative Prompts (prompt unconditioning)
- Textual Inversion
- Improved Quality for Hi-Resolution Images (Embiggen, Hi-res Fixes, etc.)
- And more...
Future updates planned included UI driven outpainting/inpainting, robust Cross Attention support, and an advanced node workflow for automating and sharing your workflows with the community.
SD-Dream Version 1.14.1
This is identical to release 1.14 except that it reverts the name of the conda environment from "sd-ldm" back to the original "ldm".
Features from 1.14:
- Memory optimizations for small-RAM cards. 512x512 now possible on 4 GB GPUs.
- Full support for Apple hardware with M1 or M2 chips.
- Add "seamless mode" for circular tiling of image. Generates beautiful effects. (prixt).
- Inpainting support.
- Improved web server GUI.
- Lots of code and documentation cleanups.
SD-Dream Version 1.14
- Memory optimizations for small-RAM cards. 512x512 now possible on 4 GB GPUs.
- Full support for Apple hardware with M1 or M2 chips.
- Add "seamless mode" for circular tiling of image. Generates beautiful effects. (prixt).
- Inpainting support.
- Improved web server GUI.
- Lots of code and documentation cleanups.
SD-Dream Version 1.13
New features and bug fixes:
- Support image variations (see VARIATIONS.md) (Kevin Gibbons and many contributors and reviewers)
- Supports a Google Colab notebook for a standalone server running on Google hardware Arturo Mendivil
- WebUI supports GFPGAN/ESRGAN facial reconstruction and upscaling Kevin Gibbons
- WebUI supports incremental display of in-progress images during generation Kevin Gibbons
- A new configuration file scheme that allows new models (including upcoming stable-diffusion-v1.5) to be added without altering the code. (David Wager)
- Can specify --grid on dream.py command line as the default.
- Miscellaneous internal bug and stability fixes.
- Works on M1 Apple hardware (several contributors, but particular thanks to James Reynolds )
- Multiple bug fixes.