About model: Style model for Stable Diffusion mimicking pulp illustration/old magazine covers. It has one trigger word but doesn't need it to work. It works out-of-the-box. License and support: This model is open source so you can share, merge or use for monetization as you like (that will apply to other versions as well) If you like what I am doing and you want to support my current and upcoming projects: here is my coffee jar Installation: As it is model based on 2.1 to make it work you need to use .yaml file with name of a model (vector-art.yaml). The yaml file is included here as well to download. Simply copy paste to the same folder as selected model file. Usually this is the models/Stable-diffusion one.
Versions: Currently, there is only one version of this model. Next training will be based on resources I have used previously, but all captioned + new images.
Black images issue: 2.1 models need to have a web-ui config modified - if you are getting black images - go to your config file and add to COMMANDLINE_ARGS= --no-half - potentially it could work with --xformers instead (if supported). This line might slow your generations a bit but will not affect negatively your output. Purpose: For Prompts reference check the tooltip on the sample images.
I am working on a guide website for all my models. My goal is to create models useful for the design world. I personally don't see a lot of benefit in using models to "just create a beautiful image".
This model is a good starting point for poster elements/backgrounds or elements you can use in the process of T-shirt design (using photoshop and going with threshold method or other)
I find it also a good choice for book covers. Especially if you want to achieve result of book covers from 1930-70 style (horror, sci-fi, thriller and similar)
|