My checkpoint is a merge of Semi-Real MM, Spectacular 2.5D and Perfection 2.5D.
When deciding which checkpoints to combine, I first create an image with each potential checkpoint. All comparison images are created using the same LoRAs and prompts. Then I compare which lighting, face shape, body shape, color depth, etc., might work well together or not.
Therefore, I decided to proceed similarly with my demo images. I took the prompts from promotional images of the base checkpoints.
Suggested Negative Prompts:
lowres, bad anatomy, (worst quality:1.8), low quality, hands bad, (normal quality:1.3), bad hands, mutated hands and fingers, extra finger, extra legs, duplicate, cropped, jpeg, artifacts, long body, mutated, disfigured, bad proportions, bad feet, ugly, text font ui, missing limb, black bars, ugly hands, extra fingers, logo, patreon username, text, watermark, extra toes,
I use Euler A, 40 Steps, CFG 8, no Refiner, built-in VAE.
You can find my Checkpoint on Pixai, too.
Description
My Checkpoint is a merge of three semi-realistic Checkpoints. It's good in close-ups, seems to have problems rendering hands, and has good lighting effects and depth of detail.
FAQ
Comments (4)
If you merging models, the result is merged model. But your model is base model tag. Why?
Because there are only a few specific options for labeling a checkpoint category. "Base Model" in this case means it's not a merge trained on specific things: animals, certain characters, etc. It is a merge of different checkpoints belonging to the "base" category.
@lovingphi Aha....Ok. I got it. Thanks!
@LumenFall You're welcome!