AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |
Back to Blog
□□ > edit bluebird.jpg -p "make the bird wear a cowboy hat " -prompt-strength 10 □□ > edit freckled_woman.jpg -p "make her a cyborg " -prompt-strength 13 □□ > edit bowl_of_fruit.jpg -p "replace the fruit with strawberries " □□ > edit dog.jpg -p "make the dog red " -prompt-strength 5 □□ > edit scenic_landscape.jpg -p "make it winter " -prompt-strength 20 Much smaller featureset compared to the command line tool. Generate images via API or web interface. Run API server and StableStudio web interface (alpha) broken: most samplers, tile/details controlnet, and model memory management.deprecated: support for Stable Diffusion versions 1.4, 2.0, and 2.1.deprecated: support for python 3.8, 3.9.feature: better logging output: color, error handling.feature: detect if wrong torch version is installed and provide instructions on how to install proper version.feature: added -size parameter for more intuitive sizing (e.g.self-attention guidance which makes details of images more accurate.On the plus side, refiners supportsĬutting edge features (SDXL, image prompts, etc) which will be added to imaginairy soon. This was a huge rewrite which is why some features are not yet supported.□ imaginairy is now backed by the refiners library.or use aimg videogen to generate a video from an image.add -videogen to any image generation to create a short video from the generated image.
0 Comments
Read More
Leave a Reply. |