Depends on what the model was trained on. A good way to test is to use a prompt that should give you nothing. I just tried stable diffusion with the prompt “.” and got an overhead shot of a rustic dinner table. I tried the dreamshaper and it gave me a headshot of a woman.
Is it drawing characters by default or are you providing additional context in the prompt?
no context only input is the username
Xyre Steps: 20, Sampler: DPM++ 3M SDE Karras, CFG scale: 7, Seed: 189656042, Size: 768x1280, Model hash: 74dda471cc, Model: realvisxlV20_v20Bakedvae, Clip skip: 2, RNG: CPU, Version: v1.6.0
Depends on what the model was trained on. A good way to test is to use a prompt that should give you nothing. I just tried stable diffusion with the prompt “.” and got an overhead shot of a rustic dinner table. I tried the dreamshaper and it gave me a headshot of a woman.