Freedom.Redmond is here!
You can currently test it at this link thanks to the makeai. run API.
I'm grateful for the GPU time from Redmond.AI that allowed me to finish this model!
This is a generalist model fine-tuned on SD 2.1 768X with a focus on generating images in >1024x.
The model has a high capacity to generate realistic, artistic images, cars, people, and a wide variety of themes. It's a versatile model.
This model will serve as the basis for a dozen models and LORAs that will come specialized in specific themes.
I highly recommend DPM+ SDE/2M or 2M SDE settings with 30 Steps. In resolution above 768x.
I also recommend testing some prompts with or without negative prompts as there are cases where the results are also interesting without negatives.
I really hope you like the model and use it.
I want to give a huge thanks to the people who helped me these past three months:
Mousewrites, PeePa, Kaz, Queria Star Morta, theovercomer8, Nawnie, Freon, Kohya
Follow me in my twitter to know before all about new models:
Update: I have authorized commercial use of the model in image generation services. You just have to explicitly credit me @artificialguybr (thanks if you link to my twitter account).