Rubbercore1920scartoonstyle

🚀 RubberCore 1920s Cartoon Style

This is a text-to-image model that can generate 1920s cartoon-style images. It offers diverse and creative visual outputs.

🚀 Quick Start

The model is designed to generate images based on specific text prompts. You can use the provided examples in the widget section to get a sense of how it works.

✨ Features

• Text-to-Image Generation: Generate various 1920s cartoon-style images according to text prompts.
• Flexible Parameter Adjustment: You can adjust parameters such as LORA strength and use trigger words to achieve different styles.

📦 Installation

No specific installation steps are provided in the original document, so this section is skipped.

💻 Usage Examples

Basic Usage

The following are some example prompts and their corresponding generated image outputs:

- text: >-
    RU883R style, soviet traditional children rear view walking next to a crop
    field, a dirt trail, a river, some snow patches on the ground, early winter,
    at a distance stands an old rusty broken giant mechanical quadripedal feet
    war machine with wires hanging and a artillery canon and green paint, bulky
    body, inspired by Jakub Rozalski. Vintage 1920s cartoon.
  output:
    url: images/Rub_00001_.png
- text: >-
    RU883R style, A debonair pikachu is wearing a three piece business suit
    standing in an alleyway at night. He is holding a pistol and aiming it
    directly at the camera. There is a speech balloon that reads, "feeling
    lucky, punk?". Vintage 1920s cartoon. He has a very toothy sinister grin and
    the overall mood is sinister. He is wearing white gloves.
  output:
    url: images/Rub_00002_.png

Advanced Usage

When using the model, you may need to adjust some parameters to get better results:

• If your image is looking too flat and cartooney (and this is not what you want), adding common prompts that push realism (e.g., "35mm analog photograph") and then increasing the strength of the lora can yield much better results.
• When prompting a specific character that the base model may already know really well, experimenting with words like "surreal" while still including the "35mm photo" stuff can help push a fun stylized cartoon look and also keep some depth to the image.

📚 Documentation

Model description

PLEASE READ ALL OF THE CONTENTS BELOW BEFORE USING

I am finding the best results with DEIS / BETA combo on the ksampler. Standard shift value works fine (1.15 / 0.5).

Depending on the style you are trying to achieve, you will have to play with the LORA strength, with / without the trigger word (RU883R), and some other things I will list below:

If your image is looking too flat and cartooney (and this is not what you want), I've found adding common prompts that push realism (e.g., "35mm analog photograph") and then just upping the strength of the lora yield much better results.

Similar to the first point, when prompting a specific character that the base model may already know really well (see my Shrek example in the images), I found experimenting with words like "surreal", but still including the "35mm photo" stuff really helps push a fun stylized cartoon look but also keeps some depth to the image.

I've included all of the sample parameters I used to generate all of the images I've included. I urge you to look at those and see how I achieved the results I did.

THE TAKE AWAY HERE IS, THIS IS NOT A SET STRENGTH TO 1, PRESS GO, GET PERFECT IMAGES EVERY TIME. IT WILL TAKE SOME EXPERIMENTING ON YOUR END BUT I PROMISE YOU THE RESULTS CAN BE INCREDIBLE.

Trigger words

You should use RU883R to trigger the image generation.

Download model

Weights for this model are available in Safetensors format. Download them in the Files & versions tab.

📄 License

This model is licensed under the apache-2.0 license.