Rotoscopee

🚀 Rotoscopee

This is a fine - tuned Stable Diffusion model based on v1.5. It is trained on screenshots from specific rotoscope animations, enabling users to generate images in a unique style by using the token "rotoscopee" in prompts.

🚀 Quick Start

This is a fine - tuned Stable Diffusion model (based on v1.5) trained on screenshots from the following rotoscope animations: A Scanner Darkly movie, Undone tv series, Tehran Taboo movie. Use the token rotoscopee in your prompts to use the style.

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

✨ Features

Character Rendering

Characters rendered with this model: prompt and settings used: [person] in rotoscopee style | Steps: 20, Sampler: Euler, CFG scale: 7

Landscape/Scene/Animal Rendering

Landscapes/scenes/animal rendered with this model: prompt and settings used: city/scene/dog in rotoscopee style | Steps: 20, Sampler: Euler, CFG scale: 7

⚠️ Important Note

The model works better on characters than landscape/scenes

🔧 Technical Details

This model was trained with Dreambooth training by TheLastBen, using 50 images at 5000 steps.

📄 License

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 claim 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