Magic - Photoreal
Introducing MPR, my first attempt at achieving photorealism with the Illustrious base model.
The above samples were all generated with "Euler a" at 30 steps with a CFG of 5 at a native resolution of 1080x1440. No post processing effects or Lora's were used for the samples as I wanted to demonstrate the bare bones of the model and what you can expect from just basic settings and simple prompts. Too many people misrepresent what their models can do by using Lora's, embeddings, hires fix and other post process effects with their sample images and I wanted to avoid any such misrepresentation. Works well with most sampling methods and schedulers but based on the testing I've done so far I would recommend using either Euler a, dpm sde, or dpm 2s a with a cfg between 3 - 7.
now available for on-site generation!
ENJOY!
Description
V2 is quite different to V1, with new knowledge bled from uniquely trained sdxl models over several iterations at low weights as not to introduce heavy bias or interfere too much with the Illustrious base. As a result, V2 can produce more realistic images and respond better to natural language whilst maintaining recognition of booru style prompts. It is also more susceptible to negative prompting now and the human female bias has been reduced along with better recognition of different ethnicities, This should make it easies to generate male and trans and even furry/alien characters than V1. In my testing so far it seems to maintain versatility but as expected from a realism model it still cannot match the versatility of Anime Illustrious models. Improved Versatility and character recognition will be the main focus for improvement with V3.