This LoRA can either make a realistic scene into a comic style one, or make a comic image into a photorealistic one.

Works both in I2I and T2I.

Note: This is a concept LoRA, not a style LoRA. The model knows what a comic is, the LoRA just plays on these weights. The training dataset does not contain any comic images.

The sample weights range from 0 to 8 (full effect). The last sample is a comic image generated in T2I and made realistic in I2I with negative (-4) slider weight (empty prompt).

Hope you like it!