cjwbw / supermarionation

Finetuned Stable-diffusion from Gerry Anderson Supermarionation

  • Public
  • 1.9K runs
  • GitHub
Run with an API
Playground API Examples README Versions

Examples

View more

Run time and cost

This model costs approximately $0.0044 to run on Replicate, or 227 runs per $1, but this varies depending on your inputs. It is also open source and you can run it on your own computer with Docker.

This model runs on Nvidia T4 GPU hardware. Predictions typically complete within 20 seconds. The predict time for this model varies significantly based on the inputs.

Readme

weights from: https://huggingface.co/tuwonga/supermarionation trigger word: xxx in supermarionation style

supermarionation

This is a fine-tuned Stable Diffusion model (based on v1.5) trained on screenshots from Gerry Anderson Supermarionation stop motion animation movie, basically from Thunderbirds tv series. Use the token supermarionation 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. I’ve found interesting (and really funny ^^) the output in the img2img. You can see the results in the second and third pic (original/img2img). You can play around with denoising strength (40-70) and activate or not the restore face option.

supermarionation v2

In this version I’ve trained characters and vehicles. 47 images and 9400 steps, 20% text encoder.

– Characters and vehicles rendered with this model: Character Samples prompt and settings used: [person/vehicle] in supermarionation style | Steps: 30, Sampler: Euler, CFG scale: 7.5

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

Characters rendered with supermarionation in txt2img: Character Samples prompt and settings used: [person] in supermarionation style | Steps: 40 - you can play around with settings

Characters rendered with supermarionation in img2img: Character Samples prompt and settings used: [person] in supermarionation style | Steps: 40 - you can play around with settings

– Supermarionation v1 was trained with Dreambooth training by TheLastBen, using 43 images at 8600 steps with 18% of text encoder. –

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 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