Edit model card


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). Use the token takeON in your prompts to use the style.

Download the ckpt file from "files and versions" tab into the stable diffusion models folder of your web-ui of choice.

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).


Characters and scenes rendered with this model: Character Samples prompt and settings used: [person/scene] in takeON_v2 style | Steps: 30, Sampler: Euler, CFG scale: 7.5

Characters rendered with img2img and inpaint: Character Samples prompt and settings used: [person] in takeON_v2 style | Steps: 30 - you can play around with settings

This model was trained with Dreambooth training by TheLastBen, using 64 images at 6400 steps with 25% of text encoder.



This model is open access and available to all, with a CreativeML OpenRAIL-M license further specifying rights and usage. The CreativeML OpenRAIL License specifies:

  1. You can't use the model to deliberately produce nor share illegal or harmful outputs or content
  2. The authors claims no rights on the outputs you generate, you are free to use them and are accountable for their use which must not go against the provisions set in the license
  3. You may re-distribute the weights and use the model commercially and/or as a service. If you do, please be aware you have to include the same use restrictions as the ones in the license and share a copy of the CreativeML OpenRAIL-M to all your users (please read the license entirely and carefully) Please read the full license here
Downloads last month
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.