takeON
SD 1.5 Standard Checkpoint
DownloadtakeON takeON_v2
In this second version I've trained only the half-drawn scene, I mean where the character is drawn and the background is in real life. The result is different, sometimes with colors and sometimes with a comic frame inside the image.
I've found interesting the output in the img2img or inpaint generation. You can see the results in the second image (original/img2img/inpaint).
This is a fine-tuned Stable Diffusion model (based on v1.5) trained on screenshots from 80s music video Take on me (from A-HA band). I made two versions of the model, the second one is slightly different, please read the description below. Use the token takeON in your prompts to use the style.