Guernika7.2.0 - App Store

Guernika is the ultimate tool for generating stunning images based on text prompts, creating variations of initial images, and inpainting images.

With Guernika, you can easily create high-quality, unique images using state-of-the-art Stable Diffusion models. Load your favorite model, provide a text prompt and let Guernika do the rest.

Additionally, you can use Guernika to generate variations of an initial image, giving you endless creative possibilities.

And when you need to update or repair an image, Guernika's inpainting feature allows you to seamlessly blend the changes into the rest of the image.

Guernika utilizes CoreML to fully take advantage of your Mac's hardware. This allows for faster and more efficient processing, resulting in smoother and more seamless performance. So not only will you be able to create beautiful images with ease, you'll be able to do so with lightning-fast speed. Whether you're a professional artist or just looking for a fun new way to create and edit images, Guernika has something for everyone. Download it now and start exploring your creative potential!

Version History - Support for Latent Consistency Models
- Small fixes and improvements 7.2.0 10/28/2023 - Improved support for Stable Diffusion XL ControlNet
- Fixes and improvements 6.4.0 09/09/2023 - Fast progress, now you can choose to either show a fast version of the current latent or decode it to get an improved version at the cost of slower diffusion 6.2.0 07/29/2023 - Shortcuts support
- Stable Diffusion XL
- Inpainting support for every model
- Improvements and bug fixes
- Denoised progress
- Textual inversion
- Prompt history
- Token count 6.1.1 07/28/2023 - Shortcuts support
- Stable Diffusion XL
- Inpainting support for every model
- Improvements and bug fixes
- Denoised progress
- Textual inversion 6.1.0 07/21/2023 - Loading on demand for models, it's no longer necessary to manually load and unload the models
- Memory and performance improvements 5.0.0 06/10/2023 - Performance improvements
- Fixes in img2img with different scale ratios 4.1.0 05/19/2023 - Added new Samplers: DDIM, Euler, EulerA, DPM++ 2M Karras
- Added support for Stable Diffusion 2 based models, no more black screens! This does require converting the models with the new Guernika Model Converter 4.0.0
- Improve alignment between Guernika's output and python implementation output.
- Some bugs fixes and performance improvements 4.0.0 04/24/2023 - Prompt weighting, tokens between () are taken more into account and tokens between [] will be taken less into account.
- Initial support for Textual Inversion embeddings, embeddings can be added when converting the TextEncoder.
- Added token count.
- Other fixes. 2.1 03/27/2023 - Add support for newer models
- General improvements 2.0 03/15/2023 - Fix symbolic links, newly added symbolic links should work after app relaunch
- Improvements on model downloading 1.9.1 02/27/2023 - Allow creating links to models on external storage
- Fix problems downloading models 1.9 02/24/2023 - Improve model downloading
- Keep screen on while performing long task 1.8 02/13/2023 - Add initial support for Instruct Pix2Pix model, generate image variation using instruction ("make it look like a gold statue")
- Fixes 1.6 01/28/2023 - Improve support for different output sizes
- Allow choosing compute units 1.4 01/11/2023 - Added DPMSolver sampler
- Allow disabling progress images
- General fixes and improvements 1.3 01/08/2023 1.2 01/08/2023